A Survey of Proxy Caching Mechanisms for Multimedia Data Streams

Size: px
Start display at page:

Download "A Survey of Proxy Caching Mechanisms for Multimedia Data Streams"

Transcription

1 A Survey of Proxy Caching Mechanisms for Multimedia Data Streams Chakchai So-In Department of Computer Science Washington University in St. Louis May 5, 2005 Abstract Although many web caching techniques have been developed to improve Web performance, existing proxy caching schemes do not support the multimedia data stream well. In this paper, we briefly describe the basic characteristics of steaming media caching and traditional web caching and discuss their dissimilarities. Then, we survey the proxy caching mechanisms for multimedia data streams, and finally outline potential research topics. Keywords: multimedia, proxy, caching, survey. 1 Introduction The vivid growth of the World Wide Web (WWW) has caused momentous increases in user latency and network congestion for Internet applications in bandwidth constrain. Most Internet traffic is HTTP activity, which consumes around 75 to 80% of all bandwidth capacity [14]. Also, most web access patterns are HTML text and images [9, 10, 18]. Due to these reasons, deploying a web proxy in the hope of satisfying future client requests without contacting the server directly can alleviate response time, server load, and network traffic substantially, particularly if the proxy has been placed at a share common interest group. There are several state-of-the art caching designs and techniques for web proxy caching, for instance, hierarchical and distributed caching schemes [41, 42], cache pre-fetching, cache resolution/ routing, cache location [55, 57], cache replacement policy [20], active and adaptive web caching [56, 49], and cache consistency [44]. However, in the past few years, requests for and deliveries of streaming video and audio over the Web have become much more popular [2, 15, 16] and this trend is expected to continue. Consequently, caching these objects has become increasingly vital to satisfy users and at the same time handle the huge 1 Internet network traffic. Currently, there is not very much detailed research or many other real applications aside from Squid [43], Cache Digest [60], CARP [59], ICP [58], and Summary Cache [48] for image and text caching in the proxy server. Thus, the design of efficient proxy caching techniques for multimedia data streams is still ongoing. Presently, there are surveys about web caching schemes [11, 12, 13, 20], but none of them have explored web multimedia caching techniques. In this paper, we direct the survey in different aspects of proxy caching mechanisms for multimedia data streams. Our purpose is not to argue for one technique against another, but rather to give an insight into each technique and put those techniques in a context where it may be possible to merge them in order to enhance proxy efficacy, Prefix Caching [3], for example. The rest of this paper is organized as follows: In the next section, we give details of the steaming media data caching idea and traditional web caching and their properties. Then, we discuss various kinds of streaming media caching strategies and cache replacement algorithms. After that, the Multicast and concerned QOS streaming media techniques are investigated. Collaborative proxy architecture is brought up next, and then web streaming media proxy pre-fetching and streaming media proxy security are examined afterward. Finally, we draw conclusions and suggest possible directions for future research. 2 Steaming Media Proxy Caching System Properties On the Internet, a streaming media proxy is placed near the clients [55, 57]. Typically the latency due to network capacity and delay between the proxy and the client seems negligible, but it is in fact quite large between the proxy and the content provider. Users request the media through the proxy, and if these objects have already been cached and

2 valid, they are returned immediately. If not, the proxy will fetch these requests from the content provider or even other proxies and send them back to the clients, as well as cache these objects locally. Also, in order for a client device to instantly play back the media, there must be enough initial blocks at the proxy server to mask the latency between it and the content server. Pre-fetching technique can be deployed from either the proxy or the client after the initial request, with the hope of meeting the remaining requests afterward [27, 30, 38, 53]. Streaming media data has different characteristics from traditional web data (text and image); hence, existing caching techniques are not appropriate for it. For example, typically the file size is very large (video and audio), even when compression techniques are applied, such as the standard MPEG and G series. It would be impractical to cache a whole three hour movie. That would consume disk usage in the proxy so large that there could be only a few movies on a whole disk. (Web video streams have a median size of 1.2 Mbytes, with 90% of the streams lasting less than 45 seconds, compared to from 1 to 2 Kbytes for HTML documents [21, 22]), Also, due to user demand, video size is becoming larger and larger as more network bandwidth becomes available. Because of limited disk space and big file sizes, instead of memory caching [23, 24, 25, 26], most streaming data may be better cached on disk as either whole or partial [31] video objects. Of course, there are the trade-offs in deciding the ratio of caching between memory and disk. One important factor to satisfy customer desire is delay sensitivity. By nature, unlike traditional traffic, a video stream should be real time and continuous. In order to support these features, a significant amount of disk buffer and network I/O bandwidth are required for a long period of time. Normally these real time traffics consume much network capacity, which may not be a fair disk usage. (Compared to memory, the size of a disk is much larger but lower in bandwidth; however, current disk-based caching algorithms are adapted from traditional memory caching [2]). Moreover, cache consistency [44] is not a major issue for streaming media caching. (Video files tend to be written just once but read many times. Once placed, they stay there forever, or until no more users are interested to watch it [8]). Finally, due to the lack of much streaming media caching research, it is quite difficult to trace exact client behavior [21, 22] from network traffic in order to achieve the optimum caching strategy; for example, 2 what should be cached if the clients query only a few portions of movie files, or how to implement caching strategy to support VCR-functionality in the case of a finite cache. 3 Steaming Media Proxy Caching Techniques We now survey some proxy caching mechanisms for multimedia data streams in the literature and describe their performance metrics and measurements. We group these caching techniques into five categories, namely, Cache Strategy and Replacement Policy, Multicasting and QOS, Distributed/ Collaboration Proxy Caching, Streaming Media Proxy Pre-fetching, and Streaming Media Proxy Caching Security. 3.1 Cache Strategy and Replacement Policy As the limitation of the proxy cache, there are two reasons for the delay in answering streaming media requests that make customers unsatisfied. First, proxy cache capacity is physically limited. And second, the requests generally are not answered until enough blocks of data have been gathered (delayed starts). In the worst case, the whole video may need to be cached. There would be far fewer problems if infinite disk space were available. But in practice, we have to deal with the finite cache; therefore, how to decide what should be cached to achieve the best benefit is the most difficult task. Also, whenever the cache capacity is exceeded, in order to achieve high caching performance, the need to choose a cache replacement policy makes much more difficult. (The standard measurement techniques are a variation of Least Recently Used (LRU: replaces requested objects which was least recently) and Least Frequently Used (LFU: replaces requested objects which was least frequently)) On the whole, users prefer to watch the beginning part and continue watching the whole video if they are interested in it, but they also may stop watching it in a few minutes owing to a lack of interest. Thus, the initial portion is much more important (more popular) than the later portions. In place of storing the whole content as text or image files, typical multimedia proxies store only a portion of each stream, mostly the beginning portion. Sen et al. proposed new caching strategy called Prefix Caching [3, 45] for the proxy to store only the initial frames of popular clips, depending on the received requests for those streams. Basically, whenever the client makes a new request through the proxy, the

3 proxy will pass through this request to the server. When the stream comes, it initiates transmission to the client and at the same time requests the remaining frames from the server. By using standard primitives in HTTP/1.1 and RTSP, this technique can work without requiring any changes to the server so as to identify and store the sequence of initial frames and request the remaining frames from the server. RTP is used to encapsulate packets that include sequence numbers and timestamps. These protocols enable the proxy to identify the frames in the prefix and schedule their transmission to the clients. Thus, when the client requests the video, the proxy must ask the server to initiate transmission of the remaining frames, instead of sending the entire stream from the beginning. In other words, the proxy invokes the range request operation in HTTP 1.1 to request the appropriate portion of the stream, and RTSP supports absolute positioning to initiate transmission with an offset from the beginning of the stream [3]. The size of the video prefix depends on the performance properties of the path between the server and the proxy, and on the target client playback delay, which is usually large enough to endure a few route-trip delays in order to absorb server-proxy latency, retransmission of lost packets, and the variability of TCP throughput. As a result, by applying this strategy, caching the beginning portion of each video file could mitigate the large playback delay problem and increase hit ratio and byte hit ratio as well as considerably reduce the network resource requirements. (Although the proxy does not store the entire video stream, depending on the total cache size, prefix caching still reduces the total amount of traffic between the server and the proxy, particularly for short video clips.) In addition to hiding delay, throughput, and loss effects between the server and the proxy, Prefix Caching also introduced workahead smoothing into the client playback buffer so as to reduce the network resource requirements. Because high quality video streams and mixed data types could make significant burstiness, transmitting large frames in advance of each burst can substantially reduce the peak rate and variability of the video stream. However, smoothing at the proxy would introduce more delay and require some buffering, since the proxy must accumulate an initial window of frame from the server. After prefix caching was deployed and proved that it brought clear benefit to cache 3 streaming media, many other techniques were investigated to adapt or modify it to their own use. Miao et al. [29] where prefix caching is called initial caching discussed additional initial caching and selective caching in an attempt to choose other parts of media streams to be cached in the proxy server if there is enough disk space left. It seems that the first approach requires a large decoder buffer. Hence, the selective caching chooses the frames to be cached partly based on knowledge of the user buffer size and video stream properties. That is, selective caching caches intermediate frames instead of frames immediately following the initial segment. This strategy could maximize the robustness of the video streams against network congestion while not violating the limited user buffer size. It also supported adding functionalities such as fast forward and rewind. In addition to prefix caching, Wu et al. [6] proposed grouping the number of block media streams received by the proxy server into variablesized segment, distance-sensitive with initial segment cache, Segment-Based Proxy Caching. A media file is divided into multiple equal size blocks which are the smallest unit of transfer. Multiple blocks are grouped into various sizes of segments. The segment size increases exponentially from the beginning of segment. In order to quickly discard the big proportion of the video segment that may once was popular but now has turned old, the size of segment i is 2 i-1 and the segment contains media blocks 2 i-1, 2 i-1 +1,., 2 i -1. The closer (higher priority) to the beginning a segment is, the smaller the segment size will be. The number of segments cached for each object is dynamically determined by both cache admission and cache replacement policies. Based on the reference frequency and the segment distance from the first portion, they attach different caching values to different segments. More segments are cached with higher reference frequencies. In the Segment-Based scheme, the less popular media is partially cached while the most popular media is fully cached. The number of initial segments cached depends dynamically on the popularity of an object. Thus, from our point of view, this technique would need more storage than others. Not only Segment-Based scheme but also other schemes mentioned above is based on the popularity [50], it is very difficult both to define what the popularity is and what criteria are used to define it. Yan and Lowenthal [51] evaluated Popularity-Aware cache replacement algorithms and

4 also compared their performance with standard LRU and distance algorithms. Considering cache replacement policy, Wu et al. [6] used the reference frequency (LRU stack based, including full video and prefix/suffix LRU schemes) of an object and the segment distance as caching replacement policy variables. Because they gave highest priority to the beginning portion (the smallest segment), the next replacement segment is always the next largest segment in their policy. Byte hit ratio and fraction of requests with delayed starts were used as the main performance metrics. The impact of cache size, the skew in video popularity, video length, user viewing behavior, total number of distinct media, and the cache capacity for initial segments were also explored. From event-driven simulation results, whenever they compared this technique with full video caching and prefix/suffix caching, where a small portion of the cache is dedicated for caching the prefixes, while the rest of the cache is for the suffix, it both increased byte hit ratio and lowered the number of requests that require delayed starts. This was true especially in the cases of limited cache size, high fluctuation of the set of hot media over time, large media file size, and lesser initial blocks before stopping playing the media. Since web objects are relatively large compared to file blocks, disk-based caching policy is usually applied. Resource-Based Caching Technique, RBC, was proposed by Tewari et al. [2] in order to cope with the heterogeneous requirements of multiple data type caching, each with different cache resource usage. RBC chooses the granularity of the entity to be cached dynamically so as to minimally use the limited cache resources (bandwidth and space; disks are limited by both bandwidth and space). RBC replaces the cache entities based on the caching resource usage and caching gain. RBC s event-driven simulation model defines the distribution across data types, the access skew, and the object size. The simulation used different web-server access logs as the workload (NLANR, NCSA, NASA, and DEC). Compared with WLRU-n, LRU-MIN, Frequency, and LRU-2, RBC outperforms these replacement algorithms in both continuous media and mixed continuous and non-continuous media objects. It has both higher byte hit ratio (10-50% higher for the space concerned and 80% higher for the bandwidth concerned) and a higher hit ratio (36% higher for the space concerned and 90% higher for the bandwidth concerned). 4 Although RBC s efficiency was claimed to outperform LFU (byte hit ratio), when looking at the comparison over a much broader region of the system design space, and especially when considering the impact of increasing disk space and bandwidth, Almeida et al. [4] argued for a relative performance of these policies and also concluded that RBC would outperform LFU only if the system has excess disk bandwidth and the cache size is small. Pooled RBC [4], an overall RBC enhancement, was also implemented to cover all the deficits of the RBC scheme. However, both Pooled RBC and RBC still have a commonly shared complexity in implementation and high time allocation and consumption. To mitigate this complexity, Hybrid LFU/ Interval Caching has been also proposed [4]. LFU simply caches the whole or partial files that are estimated to have the highest access frequency. Interval Caching (IC) optimally sets the smallest intervals or runs to be fitted in the main memory cache [23]. The proposed hybrid design was much simpler and at least equally effective use of its main memory [24, 25, 26] or disk [2]. Hybrid LFU/IC policy works differently from traditional LFU, in that it estimates file access frequency before deciding to cache the files. Also, LFU/IC caches intervals as well as files or popular file segments. In a simulation with a synthetic workload using workload characteristics including system parameters such as file access frequency, file access probabilities (Zipf-like based), request rate, cache size, and disk bandwidth [18, 19, 21], LFU/IC performed as well as or better than both Pooled RBC and LFU. However, according to the RBC trace simulation, not only LFU but also a variation of LRU, which usually is the main performance comparison metric, was evaluated. A possible future experiment may test a hybrid of LRU and IC. Rejaie et al. [1] described the replacement policy for multi-layered support. Because multilayered multimedia streams are able to adjust their quality, the replacement algorithm can make a multivalued decision for caching of multimedia data streams instead of atomic policy (keep it or throw it away). To allow the proxy to perform fine grained cache replacement, each layer of the encoded stream is divided into equal-size pieces called segments. Replacement is performed in the granularity of a segment. Each segment can be as small as a single packet or as big as several minutes of a stream. Having small segments prevents the cache space from becoming fragmented, while large segments

5 require less coordination overhead. As a result, as the popularity of a stream decreases, its quality and its size are reduced before it is finally flushed from the cache. Also, to hide the startup latency, it is preferred to keep the initial segments of a layer in the cache. Also, to minimize variation in quality, it is preferred to give higher priority for contiguous segments of a layer. 3.2 Multicasting and QOS Existing solutions for streaming media are not scalable because they use a separate unicast stream for each request; therefore, they require a stream to travel from the server to the client across the Internet for every request. Thus, the clients must endure high start-up latency and unpredictable playback quality due to network congestion. Besides, a server load increases linearly with the number of receivers, and these factors all cause streaming multimedia to create serious network congestion problems. Proxy-assisted caching and proxy-assisted selective caching were explored by Sen et al. [3]. Both of them employed a central-server-based periodic broadcast scheme (source-specific multicast: Greedy Disk-conserving Broadcast, GDB) to efficiently utilize central server and network resources, while at the same time exploiting proxy servers to significantly reduce service latency experienced by the clients. For example, to ensure near instantaneous playback, the central server directs the client to immediately fetch the initial frames of the video object that is staged at a prefixbased proxy server that is the closet to the client. Proxy-assisted caching technique combines the server-push and client-pull video delivery paradigms. It dedicates a certain number of server channels for periodic broadcasting. Whenever a new request arrives, the client joins an on-going multicast group at any time rather than wait for the next broadcast cycle to retrieve the multicast stream from the central server. It retrieves the missing initial frames from the proxy server via a separate unicast channel. Thus, the clients can play back the prefixes as they are received from the proxy, while at the same time temporarily storing the video data received from the broadcast channel to the disk, so it can reduce the service latency substantially. This technique is particularly effective for hot (frequently accessed) video objects. In addition, a second approach, Proxyassisted selective caching technique, has been used 5 to merge the proxy-assisted caching technique (server-push) for delivery of hot video objects with the proxy-assisted controlled multicast technique (client-pull) for delivery of cold video objects to account for the diverse video access patterns. The main design technique is to determine when to apply proxy-assisted caching and when to apply controlled multicast. Thus, a simple and straightforward criterion for classifying video objects based on their access patterns have been put into practice: a video object is considered hot if the expected total number of channels required delivering it using caching is less than that required using controlled multicast; otherwise, the video object is considered cold. Consequently, in simulations that compared the total number of channels and the number of server channels, proxyassisted selective caching technique achieved higher performance over existing techniques in terms of both server/network resource requirements and service latency. Considering the needs for congestion control and co-existence with TCP-based flows such as HTTP in the Internet, proxy caching techniques which are aware of congestion control are highly effective in the transmission of multimedia streams [1, 28, 34]. The size of multimedia streams can be changed by adjusting their quality, mainly in response to highly heterogeneous access to the Internet. There are many ways to adjust the quality but in [1], Rejaie et al. introduced a layered encoding technique and they claimed that this coding provides a perfect opportunity for a proxy cache to cope with variations in the quality of a cached stream. If the cached stream is structured properly, the proxy is able to cope with variations in quality during subsequent playback by playing only a subset of layers from the cache, or by simultaneous playback from the cache and fetching additional layers from the original server. With end-to-end architecture for the delivery of layered-encoded streams, the compressed data is split into a base layer which contains the most essential low quality information and other layers which provide optional enhancement information. The more layers played back, the better the quality becomes. The number of active layers is directly determined by the average bandwidth between the proxy and interested clients [1]. However, from my own point of view a trade off between time and implementation complexity and CPU consumption could define the optimum number of layers.

6 Given constrained disk space, heuristics models, so-called Distributing Layered Encoded, were analyzed by Kangasharju et al. [33] to determine which videos and which layers in the videos should be cached in a finite-capacity cache based on an analytical stochastic knapsack model, 2- resource problems. (Intuitively, more popular videos should have first priority and preference would also be given to the lower base layers.) In numerical experiments, their heuristics perform well. The best performance was achieved by the revenue density heuristic model. Based on these multi-layered coding schemes, a fine grained replacement algorithm for layered-encoded multimedia streams and prefetching schemes to smooth out the variations in quality of a cached stream during subsequent playbacks were again proposed in [1]. End-to-end congestion control was performed by the Rate Adaptation Protocol (RAP), and error control function was performed by the error control (EC). The quality of the transmitted stream was adjusted by the Quality Adaptation (QA) module at the server. Combining this information with the average retransmission rate provided by the error control module, the QA module adjusts the quality of the transmitted stream by adding or dropping layers accordingly. The clients usually buffer some data by slightly delaying the playback of the first packet. Rate adaptation happens on a timescale of round-trip times, but layers are added and dropped on a longer timescale. A combination of receiver buffering and quality adaptation is able to cope with variations of available bandwidth [1]. Huang et al. proposed a Proxy-Based Traffic Flow Control Scheme [46] to regulate the presentation quality according to the presently available bandwidth, either dropping or adding video layers when the network situation gets either congested or smooth. Additionally, the proposed traffic flow control provides layered video stream buffering control to smooth out video playback. A retransmission technique is also adopted to reduce the possibility of loosing important video frames. With this proposed traffic flow control scheme, coming server-proxy client multimedia presentation systems can have better bandwidth utilization and presentation quality [46]. 3.3 Distributed/ Collaboration Proxy Caching Almost all of the techniques above are based on relatively simple proxy architecture without any collaboration among the proxies themselves. 6 Although hierarchical/ distributed [40, 41, 42, 43] web caching techniques work efficiently for traditional data (caching a whole file), these techniques do not work well in support of continuous data media, for the many reasons we have mentioned above. Hence, MiddleMan [8] and SOCCER [5] were implemented in order to focus on the design of an efficient collaborative proxy/ caching architecture for streaming media streams. Acharya and Smith [8] deployed the MiddleMan as a collection of proxy servers that cache video files within Local Area Network (LAN). It was distributed among N servers, and on each server, each video file is partitioned into N blocks for load balancing. It can have a large aggregate cache while placing minimal load on each participating client. In this architecture, coordinators are used to organize the collection of caching the video proxy servers. A coordinator is a process which is hosted by each proxy. It keeps track of the files and redirects requests accordingly. It also makes use of the proxies to manage the copied video files stored at each machine and makes cache replacement decisions for the entire system. A main feature of this scheme is that it can partially cache video streams by random access, which is supported by HTTP 1.1. The proxy is served by sending a portion of the video to the client while the remainder is obtained from the main video web server. Another feature of the scheme is it ability to fragment cached videos into equal sized file blocks in order to support the cached title spread across multiple storage proxies. In the simulations where proxy cache size and cache replacement policies are main parameters, larger global cache sizes increase the overall hit rate. Caching algorithm comparisons (FIFO, LRU, LRUk, and HitsLRUpick) with the byte hit ratio as the performance metric showed that LRU-k provides the highest hit rates, but a variation of LRU, HistLRUpick, yielded good hit rates as well as effective load balancing. Additionally, HistLRUpick could achieve high cache hit rates even with a relatively small cache size. Also, by caching videos relatively close to the clients and ensuring that a large number of video requests are satisfied locally, it reduces overall start-up delays and the possibility of adverse Internet conditions disrupting video playback. From the server side, MiddleMan significantly reduces load by intercepting a large number of server accesses.

7 Although this scheme improves overall distributed caching performance, many issues still need to be addressed. For example, fault tolerance (if a coordinator crashes), fast forward and rewind support (how to request the right block sequence from the coordinators), security and authentication (how to deny unauthorized users access), and proxy cluster cooperation (scalable issue) are concerns. One claimed completion scheme for caching multimedia data streams combining multicasting and caching techniques, SOCCER (Self-Organizing Cooperative Caching Architecture), was proposed by Hofmann et al. [5, 36]. This scheme includes segmentation of streaming objects, dynamic caching, and self-organizing cooperative caching. A helper agent, the key component inside the network, communicates via a state distribution protocol and forms dynamic meshes for forwarding streaming media. With regard to segmentation technique, a new logical unit has been presented, the chunk. A chunk is a number of contiguous segments within an object. Every k segments form a chunk starting from the beginning of an object. Each chunk is then cached independently using prefix caching [3] allocation and replacement policy. By varying the chunk size, a trade-off is achieved between the maximum number of gaps and the segment replacement flexibility. Instead of static caching, dynamic caching makes use of the streaming nature which offers further bandwidth saving. Based on patching technique, dynamic caching has been implemented in order to hide the temporal distance between the requests. Moreover, Self organizing cooperative caching is a mechanism for scalable state distribution that enables caches to learn about the state of remote caching systems. Using this mechanism, loosely coupled cache meshes can be formed to forward a streaming object to various receivers. According to a simulation (based on ns2) with two performance metrics (network load and sender load), self-organizing cooperative caching can significantly reduce the network and server load compared to the hierarchical proxy caching. The overhead for state distribution becomes almost negligible when using the proposed distribution protocol based on Expanding Ring Advertisement (ERA). The result shows heavily loaded systems will benefit from segmentation of media objects and from dynamic caching [5] Streaming Media Proxy Pre-fetching One interesting enhanced streaming proxy caching technique is so-called pre-fetching, which is used principally to smooth out the client playback. This technique was mentioned in most papers, but none of them gave much detail. For example, Rajaie et al. [1] applied the pre-fetching technique in order to support the conservative approach. To ensure intime delivery of requested segments, the proxy continuously monitors its round-trip-time to the active servers. This enables the proxy to issue a request ahead of time to absorb the delay in delivery. They also claimed that although all the pre-fetched segments during a session may not be played back, they are still cached with the hope that will be used for the next request. Jung et al. [38] proposed an on-demand cumulative pre-fetching, proactive pre-fetching, to enhance data availability of large multimedia files. Traditionally, repetitive pre-fetching attempts to fetch large objects would waste network resources with no guarantee of success. The idea behind this technique was to improve the availability of large multimedia data by pre-fetching the failed data whenever a request fails twice. Compared to conventional a proxy pre-fetching technique, if an error occurs; it will stop fetching and send error message to the client. Cumulative fetching which supplements the data in successive retrievals was implemented to avoid the abusive use of network because of high transfer failure rate. As a result, within a few trials with minimal additional bandwidth requirement, this scheme could substantially reduce the error rate (by 40%), save network bandwidth between the proxy and the server (by 13.18%), and increase byte hit rate (by 8.1%) for large multimedia data. In order to reduce mainly the backbone WAN bandwidth requirement, Video Staging technique and network-conscious approach via intelligent utilization of the disk bandwidth and storage space available at proxy servers attached to the LANs has been introduced by Wang and Zhang et al [27, 30]. The main idea for this technique is to pre-fetch a predetermined amount of video data and store it priori at the proxy server (staging). Using the video staging technique, only part of video data is retrieved directly from the central video server across the backbone WAN, whereas the rest of the video data is delivered to users from proxy servers attached to the LANs.

8 In contrast to the common pre-fetching technique used in the proxy web server, where data files are cached in and purged out of the proxy web server based on online prediction of the random user access pattern, the video staging technique determines the video data to be staged at the proxy video server based on several important factors such as the effectiveness of video staging and user access pattern. Also, the video data are staged at the proxy server for a quite long period of time instead of caching in and being removed dynamically. Wang and Zhang et al also evaluated heuristic algorithms for designing a multiple video staging scheme in a proxy server with a given video access profile for the associated LAN. As a result, this technique provides a cost-effective and scalable solution to the problem of the end-to-end video delivery over widearea networks from the simulation based on MPEG- 1 video traces [27]. Although it seems that a pre-fetching technique gives much benefit in smoothing out client playback, fetching has a significantly negative impact on network traffic. It would be fruitless and waste too much network capacity and temporary proxy storage to retrieve subsequent streams with no user interest. Thus, intelligent fetching algorithm should be developed in order to fetch the most future frequent precisely. 3.4 Streaming Media Proxy Caching Security Most streaming media caching techniques usually emphasize how to improve caching efficiency within both time and space constraints for the finite cache (caching strategy and cache replacement algorithm). However, the use of the streams increases the threat that perhaps, multimedia data streams are exposed to unauthorized access. As we know, every stream has to be requested through the proxy web server, so whoever access to this proxy could gain control to video information. Apart from encrypting the entire stream at the application level on the server side (Qiao [52] discussed the comparison of MPEG encryption algorithms), an intensive survey found just a few papers work around how to make this stream secure. There was not even much performance evaluation of encryption and authentication techniques applied to streams at the video proxy server. Yeung et al. [39] proposed a secure proxy architecture framework called A secure video proxy. Asymmetric Reversible Parametric Sequences with the standard computability assumptions, a multi-key RSA technique, is a 8 framework to provide data confidentiality during transmission, end-to-end data confidentiality, data confidentiality against proxy intruders, and data confidentiality against member collusion. A set of encryption configuration parameters to trade off proxy encryption throughput against the viewing quality of the video by unauthorized parties was also discussed. In empirical result, in terms of both PSNR and the visual quality, high encryption throughput and tremendously low video quality can be achieved concurrently during unauthorized access. Yeung et al. also discussed the problems of naïve security approaches using a secret key between the server and the proxy, the server, the proxy, and the clients (end-to-end encryption), and using a secret key heterogeneously between the server-proxy pair and the proxy-client pairs. Then, an encryption framework for a secure proxy was presented; that is, first the multimedia proxy cached only encrypted video data and data decryption is at the end point only. Second, this proxy performs encryption operations only; data encryption and decryption operations are based on the well accepted encryption theory that it is computationally infeasible to extract the original multimedia data without knowledge of the expected decryption key. Finally membership collusion is avoided. 4 Conclusions In this paper, many multimedia caching strategies and techniques have been addressed. The strategy for choosing which streams to be cached focused mostly on the first portion of each stream, Techniques such a Prefix Caching [3], Selective Caching [29], and Segment-Based Caching [6] are based on the cache size and also the popularity. One common concern is how to optimize cache replacement policy; RBC was proposed in [2]. Pooled RBC and a new hybrid LFU/interval caching strategy [4] have been proposed to supplant the traditional RBC. A Proxy-assisted technique [7] employed the use of the multicasting. A fine grained replacement algorithm and end to end architecture for layered-encoded multimedia streams was presented [1]. Proxy-Based Traffic Flow Control Scheme [46] was proposed to adjust the presentation quality according to the currently available bandwidth. A combination of segmentation of streaming, dynamic caching and self-organizing cooperative caching was proposed in SOCCER [5]. MiddleMan was an example for video caching proxy server collaboration [8]. Pre-fetching techniques for

9 streaming media were explored in [27, 30, 38] and finally, in [39] the secure video proxy was discussed. For performance evaluation, almost all caching schemes used trace-driven simulation. As far as we know, none of the evaluation techniques used the real network environment (Web video stream over the Internet) as a testbed. Some techniques simulated the unknown workload or workload according to client traced characteristics and some were based on web log traces. The evaluation would be more convincing if a real traced data streams were applied, because caching performance is principally workload dependent. It is also quite difficult to find suitable performance metrics for each technique, although the hit ratio and byte hit ratio are commonly used (average and maximum latency and total cost metrics may be considered). Comparing cache replacement policies, the results would be mire believable if standard techniques (For instance, FIFO, Size, LFU, variation of LRU, and Optimum) have been taken into account. In surveying previous research on Web streaming media proxy caching, our observation has been shown that only one or even a few techniques can not solve the open problems or come up with a unique optimum solution. Optimizing some parameters would affect others, and they all depend on what kind of network is employed. From our point of view, apart from all the techniques above, future research on steaming media caching should be in various areas. Optimizing techniques such as cache replacement, hierarchical and distributed streaming caching with multicasting (whenever the ISP fully supports IP multicast), are one such area. Another is intelligent cache pre-fetching for real applications. The goal remains to make proxy caching multimedia data streams scalable, robust, fault tolerate, and highly secure. 5 Acknowledgements We would like to thank Prof. J. Ballard and the anonymous engineering school reviewers at Washington University for their thoughtful comments on this paper and also special thanks to Prof. L. Xu who inspired my initiative. 6 References [1] R. Rejaie, M. Handley, H. Yu, and D. Estrin, Proxy caching mechanism for multimedia playback streams in the Internet,'' In Proc. International Web Caching Workshop, March [2] R. Tewari, H. M. Vin, A. Dan, and D. Sitaram, Resource-based caching for Web servers, In Proc. SPIE/ACM Conference on Multimedia Computing and Networking, January [3] S. Sen, J. Rexford, and D. Towsley, Proxy prefix caching for multimedia streams, In Proc. IEEE INFOCOM, April [4] J. M. Almeida, D. L. Eager, and M. K. Vernon, A hybrid caching strategy for streaming media files, In MMCN, [5] M. Hofmann, T. S. E. Ng, K. Guo, S. Paul, and H. Zhang, "Caching techniques for streaming multimedia over the Internet," Technical Report BL TM, April [6] K. Wu, P. S. Yu, and J. Wolf, "Segment-based proxy caching of multimedia streams," In Proc. WWW, Hongkong, China, May [7] L. Gao, Z. Zhang, D. F. Towsley, Proxyassisted techniques for delivering continuous multimedia streams, IEEE/ACM Trans. Netw. 11(6): , [8] S. Acharya and B. Smith, Middleman: A Video Caching Proxy Server, In Proc. the 10th International Workshop on Network and Operating System Support for Digital Audio and Video, June [9] A. Mahanti, C. Williamson, and D. Eager, Traffic analysis of a Web proxy caching hierarchy, IEEE Network, 14(3):16--23, [10] C. Cunha, A. Bestavros, and M. Crovella, Characteristics of WWW Client-based Traces, Technical Report, TR , Boston University, CS Dept, Boston, MA 02215, April [11] G. Barish, K. Obraczka, "World wide web caching: trends and techniques," IEEE Communications Magazine, vol. 38 pages , May

10 [12] J. Wang, A survey of web caching schemes for the Internet, ACM Computer Communications Review, 25(9):36--46, [13] B. D. Davison, A Survey of Proxy Cache Evaluation Techniques, 4th International Web Caching Workshop, [14] K. Thompson, G. Miller, and R. Wilder, Wide- area internet traffic patterns and characteristics, In Proc. 3 rd International Conference on Web Caching, [15] Real Networks, Internet homepage, [16] Microsoft Inc. Netshow service, streaming media for business, Internet homepage, [17] M. Abrams et. al, Caching Proxies: Limitations and Potentials, 4th International World-Wide-Web Conference, pages , December [18] M. Arlitt and C. Willliamson, Web Server Workload Characterization: The Search for Invariants, In Proc. ACM Sigmetrics Conf. on Measurement and Modeling of Computer Systems, Philadelphia, pages , May [19] L. Breslay, P. Cao, L. Fan, G. Phillips, S. Shenker, Web Caching and Zipf-like Distributions: Evidence and Implications, In Proc. IEEE Infocom, New York City, NY, pages , March [20] P. Stefan and B. Laszlo, A Survey of Web Cache Replacement Strategies, ACM Computing Surveys, Vol. 35, No. 4, December [21] S. Acharya and B. Smith, An experiment to characterize videos on the World Wide Web, In Proc. SPIE/ACM Conference on Multimedia Computing and Networking, January [22] S. Acharya, B. Smith and P. Parnes, Characterizing User Access To Videos On The World Wide Web, In Proc. PIE/ACM Conf. on Multimedia Computing and Networking, San Jose, CA, pages , January [23] A. Dan, D. Dias, R. Mukherjee, D. Sitaram, and R. Tewari, Buffering and caching in large scale video servers, In Proc. IEEE COMPCON, pages , [24] B. Ozden, R. Rastogi and A. Silberschatz, Buffer Replacement Algorithms for Multimedia Storage Systems, In Proc. International Conf. on Multimedia Computing and Systems, Hiroshima, Japan, pages , June [25] A. Dan and D. Sitaram, A Generalized Interval Caching Policy for Mixed Interactive and Long Video Environments, In Proc. Multimedia Computing and Networking Conference, San Jose, CA, January [26] A. Dan and D. Sitaram, Multimedia Caching Strategies for Heterogeneous Application and Server Environments, Multimedia Tools and Applications, vol. 4, pages , May [27] Y. Wang, Z.-L. Zhang, D. Du and D. Su, A network conscious approach to end-toend video delivery over wide area networks using proxy servers, In Proc. IEEE Infocom, San Francisco, CA, pages , March [28] R. Rejaie, H. Yu, M. Handley and D. Estrin, Multimedia Proxy Caching Mechanism for Quality Adaptive Streaming Applications in the Internet, In Proc. IEEE Infocom, Tel Aviv, Israel, March [29] Z. Miao and A. Ortega, Proxy Caching for Efficient Video Services Over the Internet, In Proc. Packet Video Workshop, Columbia University, NY, April [30] Z.L. Zhang, Y. Wang, D. H. C. Du, and D. Shu, Video Staging: A Proxy-Server-Based Approach to End-to-End Video Delivery over Wide-Area Networks, IEEE/ACM Transactions on Networking, 8(4): , [31] S. H. Park and K. D. C. E. J. Lim, Popularitybased Partial Caching for VOD Systems using a Proxy Server, In Workshop on Parallel and Distributed Computing in Image Processing, Video Processing and Multimedia, April [32] B. Wang, S. Sen, M. Adler, and D. Towsley, Optimal Proxy Cache Allocation For Efficient Streaming Media Distribution, In IEEE INFOCOM, June

11 [33] J. Kangasharju, F. Hartanto, M. Reisslein, and K. W. Ross, Distributing Layered Encoded Video through Caches, In Proc. IEEE INFOCOM, April [34] R. Rejaie and J. Kangasharju, Mocha: A Quality Adaptive Multimedia Proxy Cache for Internet Streaming, In Proc. the International Workshop on Network and Operating Systems Support for Digital Audio/ Video, June [35] H. Fahmi, M. Latif, S. Sedigh-Ali, A. Ghafoor, P. Liu, and L. H. Hsu, Proxy Servers for Scalable Interactive Video Support, IEEE Computer, 43(9):54.60, September [36] E. Bommaiah, K. Guo, M. Hofmann, and S. Paul, Design and Implementation of a Caching System for Streaming Media over the Internet, In IEEE Real-Time Technology and Applications Symposium (RTAS), June [37] M. Reisslein, F. Hartanto, and KW. Ross KW, Interactive video streaming with proxy Servers, In Proc. the 1st international workshop on intelligent multimedia computing and networking (IS&T/SPIE conference on multimedia Computing and networking (MMCN)), San Jose, February [38] J. Jung, D. Lee, and K. Chon, Proactive Web Caching with Cumulative Prefetching for Large Multimedia Data, In Proc. the 9 th International World Wide Web Conference, Amsterdam, Netherlands, May [39] S. F. Yeung, J. C. S. Lui, and D. K. Y. Yau, A Case for a Multi-Key Secure Video Proxy: Theory, Design, and Implementation, 10th ACM Multimedia, pages , [40] C.M. Bowman, P.B. Danzig, D.R. Hardy, U. Manber, M.F. Schwartz, and D.P. Wessels, Harvest: A scalable, customizable discovery and access system, Tech. Rep. CU-CS , University of Colorado at Boulder, USA, [41] A. Chankhunthod, P.B. Danzig, C. Neerdaels, M.F.Scwartz, and K.J. Worrell, A hierarchical internet object cache, In Proc. the Usenix Technical Conference, [42] P. Rodriguez, C. Spanner, E. W. Biersack, "Analysis of Web caching architectures: hierarchical and distributed caching, IEEE/ACM Transactions on Networking, Vol. 9(4), pages , August [43] L. Fan, P. Cao, J. Almeida, A. Z. Broder, "Summary cache: a scalable wide-area web cache sharing protocol, " IEEE/ACM Transactions on Networking, Vol. 8(3), pages , Jun [44] J. Gwertzman, M. Seltzer, World-Wide Web Cache Consistency, In Proc. Usenix Technical Conference, San Diego, CA, January [45] S. Gruber, J. Rexford, and A. Basso, Protocol Considerations for a Prefix-Caching Proxy for Multimedia Streams, Computer Networks, 33(1-6), June [46] C. Huang, T. Hsu, C. Chang, "A Proxy-based Adaptive Flow Control Scheme for Media Streaming," THE 2002 ACM SIGAPP SYMPOSIUM ON APPLIED COMPUTING (SAC 2002), [47] S. Jin, A. Bestavros, and A. Iyenger, Networkaware Partial Caching for Internet Streaming Media, ACM/Springer Multimedia System Journal, 9(4), October [48] D. Wessels, Squid Internet Object Cache, in online document available from May [49] L. Zhang, S. Michel, S. Floyd, V. Jacobson, K. Nguyen, and A. Rosenstein, Adaptive Web Caching: Towards a New Global Caching Architecture, In Proc. the Third International Caching Workshop, June [50] S. Jin and A. Bestavros, "Popularity-aware GreedyDual-Size Web proxy caching algorithms, " In Proc. IEEE ICDCS [51] H. Yan and D. K. Lowenthal, Popularity- Aware Cache Replacement in Streaming Environments," In Proc. International Conference on Parallel and Distributed Computing Systems, August [52] L. Qiao, and K. Nahrstedt, "Comparison of MPEG Encryption Algorithms", Computers and Graphics, Vol. 22, pages

12 [53] C. Huang, and T. Hsu, A User-Aware Prefetching Mechanism for Video Streaming, World Wide Web Journal, VOL. 6, NO. 4, pages , December [54] H. Schulzrinne, A. Rao, and R. Lanphier, Real Time Streaming Protocol (RTSP), Internet draft, IETF, August [55] P. Krishnan, D. Raz, and Y. Shavitt, The cachelocation problem, IEEE/ACM Transactions on Networking, October [56] P. Cao, J. Zhang, and K. Beach, "Active Cache: Caching Dynamic Contents on the Web", In Proc. IFIP, pages , Middleware, [57] A. Wierzbicki, Models for Internet Cache Location, In Proc. the 7th International Workshop on Web Content Caching and Distribution, Boulder, Colorado, August [58] D.Wessels and K. Claffy, Internet cache protocol (ICP), version 2, RFC [59] K.W. Ross, Hash Routing for Collections of Shared Web Caches, IEEE Network, 11, pages 37-44, [60] A. Rousskov and D.Wessels, Cache digests, Comput. Networks ISDN Syst., vol. 30, no , pages ,

A Proxy Caching Scheme for Continuous Media Streams on the Internet

A Proxy Caching Scheme for Continuous Media Streams on the Internet A Proxy Caching Scheme for Continuous Media Streams on the Internet Eun-Ji Lim, Seong-Ho park, Hyeon-Ok Hong, Ki-Dong Chung Department of Computer Science, Pusan National University Jang Jun Dong, San

More information

Impact of Frequency-Based Cache Management Policies on the Performance of Segment Based Video Caching Proxies

Impact of Frequency-Based Cache Management Policies on the Performance of Segment Based Video Caching Proxies Impact of Frequency-Based Cache Management Policies on the Performance of Segment Based Video Caching Proxies Anna Satsiou and Michael Paterakis Laboratory of Information and Computer Networks Department

More information

A Survey of Streaming Media Caching

A Survey of Streaming Media Caching A Survey of Streaming Media Caching Jiangchuan Liu Department of Computer Science The Chinese University of Hong Kong ljc@cse.cuhk.edu.hk Jianliang Xu Department of Computer Science Hong Kong Baptist University

More information

A Packet-Based Caching Proxy with Loss Recovery for Video Streaming

A Packet-Based Caching Proxy with Loss Recovery for Video Streaming A Packet-Based Caching Proxy with Loss Recovery for Video Streaming Kuan-Sheng Hsueh and Sheng-De Wang Department of Electrical Engineering, National Taiwan University {kshsueh, sdwang}@hpc.ee.ntu.edu.tw

More information

Streaming Flow Analyses for Prefetching in Segment-based Proxy Caching to Improve Media Delivery Quality

Streaming Flow Analyses for Prefetching in Segment-based Proxy Caching to Improve Media Delivery Quality Streaming Flow Analyses for Prefetching in Segment-based Proxy Caching to Improve Media Delivery Quality Songqing Chen Bo Shen, Susie Wee Xiaodong Zhang Department of Computer Science Mobile and Media

More information

Trace Driven Simulation of GDSF# and Existing Caching Algorithms for Web Proxy Servers

Trace Driven Simulation of GDSF# and Existing Caching Algorithms for Web Proxy Servers Proceeding of the 9th WSEAS Int. Conference on Data Networks, Communications, Computers, Trinidad and Tobago, November 5-7, 2007 378 Trace Driven Simulation of GDSF# and Existing Caching Algorithms for

More information

MULTIMEDIA PROXY CACHING FOR VIDEO STREAMING APPLICATIONS.

MULTIMEDIA PROXY CACHING FOR VIDEO STREAMING APPLICATIONS. MULTIMEDIA PROXY CACHING FOR VIDEO STREAMING APPLICATIONS. Radhika R Dept. of Electrical Engineering, IISc, Bangalore. radhika@ee.iisc.ernet.in Lawrence Jenkins Dept. of Electrical Engineering, IISc, Bangalore.

More information

Evaluating the Impact of Different Document Types on the Performance of Web Cache Replacement Schemes *

Evaluating the Impact of Different Document Types on the Performance of Web Cache Replacement Schemes * Evaluating the Impact of Different Document Types on the Performance of Web Cache Replacement Schemes * Christoph Lindemann and Oliver P. Waldhorst University of Dortmund Department of Computer Science

More information

Using Multicast for Streaming Videos across Wide Area Networks

Using Multicast for Streaming Videos across Wide Area Networks Using Multicast for Streaming Videos across Wide Area Networks Bing Wang ½, Subhabrata Sen ¾, Micah Adler ½ and Don Towsley ½ ½ Department of Computer Science University of Massachusetts, Amherst, MA 0003

More information

Reduction of Periodic Broadcast Resource Requirements with Proxy Caching

Reduction of Periodic Broadcast Resource Requirements with Proxy Caching Reduction of Periodic Broadcast Resource Requirements with Proxy Caching Ewa Kusmierek and David H.C. Du Digital Technology Center and Department of Computer Science and Engineering University of Minnesota

More information

A CONTENT-TYPE BASED EVALUATION OF WEB CACHE REPLACEMENT POLICIES

A CONTENT-TYPE BASED EVALUATION OF WEB CACHE REPLACEMENT POLICIES A CONTENT-TYPE BASED EVALUATION OF WEB CACHE REPLACEMENT POLICIES F.J. González-Cañete, E. Casilari, A. Triviño-Cabrera Department of Electronic Technology, University of Málaga, Spain University of Málaga,

More information

Accelerating Internet Streaming Media Delivery using Network-Aware Partial Caching

Accelerating Internet Streaming Media Delivery using Network-Aware Partial Caching Accelerating Internet Streaming Media Delivery using Network-Aware Partial Caching Shudong Jin Computer Science Department Boston University, Boston, MA 2115 jins@cs.bu.edu Azer Bestavros Computer Science

More information

A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers

A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers A Simulation-Based Analysis of Scheduling Policies for Multimedia Servers Nabil J. Sarhan Chita R. Das Department of Computer Science and Engineering The Pennsylvania State University University Park,

More information

Analysis of a Cyclic Multicast Proxy Server Architecture

Analysis of a Cyclic Multicast Proxy Server Architecture I. J. Communications, Network and System Sciences, 2008, 4, 285-385 Published Online November 2008 in SciRes (http://www.scirp.org/journal/ijcns/). Analysis of a Cyclic Multicast Proxy Server Architecture

More information

Proxy Ecology - Cooperative Proxies with Artificial Life

Proxy Ecology - Cooperative Proxies with Artificial Life Proxy Ecology - Cooperative Proxies with Artificial Life James Z. Wang Department of Computer Science Clemson University Clemson, SC 29634 864-656-7678 jzwang@cs.clemson.edu Ratan K. Guha Department of

More information

A Hybrid Caching Strategy for Streaming Media Files

A Hybrid Caching Strategy for Streaming Media Files A Hybrid Caching Strategy for Streaming Media Files Jussara M. Almeida a, Derek L. Eager b, Mary K. Vernon a a Department of Computer Science, University of Wisconsin-Madison 2 West Dayton Street, Madison,

More information

Proxy Caching for Media Streaming over the Internet

Proxy Caching for Media Streaming over the Internet Proxy Caching for Media Streaming over the Internet Jiangchuan Liu School of Computing Science Simon Fraser University Burnaby, BC, Canada csljc@ieee.org Jianliang Xu Department of Computer Science Hong

More information

Media Caching Support for Mobile Transit Clients

Media Caching Support for Mobile Transit Clients Media Caching Support for Mobile Transit Clients Hazem Gomaa Geoffrey Messier Robert Davies Department of Electrical and Computer Engineering University of Calgary Calgary, AB, Canada Email: {hagomaa,gmessier,davies}@ucalgary.ca

More information

Improving VoD System Efficiency with Multicast and Caching

Improving VoD System Efficiency with Multicast and Caching Improving VoD System Efficiency with Multicast and Caching Jack Yiu-bun Lee Department of Information Engineering The Chinese University of Hong Kong Contents 1. Introduction 2. Previous Works 3. UVoD

More information

An Efficient Web Cache Replacement Policy

An Efficient Web Cache Replacement Policy In the Proc. of the 9th Intl. Symp. on High Performance Computing (HiPC-3), Hyderabad, India, Dec. 23. An Efficient Web Cache Replacement Policy A. Radhika Sarma and R. Govindarajan Supercomputer Education

More information

Evaluation of Performance of Cooperative Web Caching with Web Polygraph

Evaluation of Performance of Cooperative Web Caching with Web Polygraph Evaluation of Performance of Cooperative Web Caching with Web Polygraph Ping Du Jaspal Subhlok Department of Computer Science University of Houston Houston, TX 77204 {pdu, jaspal}@uh.edu Abstract This

More information

Accelerating Internet Streaming Media Delivery Using Network-Aware Partial Caching

Accelerating Internet Streaming Media Delivery Using Network-Aware Partial Caching Boston University OpenBU Computer Science http://open.bu.edu CAS: Computer Science: Technical Reports 2- Accelerating Internet Streaming Media Delivery Using Network-Aware Partial Caching Shudong, Jin

More information

On the Power of Cooperation in Multimedia Caching

On the Power of Cooperation in Multimedia Caching On the Power of Cooperation in Multimedia Caching Itai Dabran and Danny Raz Computer Science Department, Technion, Haifa 32, Israel Abstract. Real time multimedia applications such as Internet TV, Video

More information

An Cross Layer Collaborating Cache Scheme to Improve Performance of HTTP Clients in MANETs

An Cross Layer Collaborating Cache Scheme to Improve Performance of HTTP Clients in MANETs An Cross Layer Collaborating Cache Scheme to Improve Performance of HTTP Clients in MANETs Jin Liu 1, Hongmin Ren 1, Jun Wang 2, Jin Wang 2 1 College of Information Engineering, Shanghai Maritime University,

More information

Advanced Networking Technologies

Advanced Networking Technologies Advanced Networking Technologies Chapter 13 Caching Techniques for Streaming Media (Acknowledgement: These slides have been prepared by Dr.-Ing. Markus Hofmann) 1 What is Streaming? Streaming media refers

More information

Network-aware partial caching for Internet streaming media

Network-aware partial caching for Internet streaming media Multimedia Systems (23) Digital Object Identifier (DOI).7/s53-3-9- Multimedia Systems Springer-Verlag 23 Network-aware partial caching for Internet streaming media Shudong Jin, Azer Bestavros, Arun Iyengar

More information

Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network

Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network Hierarchical Content Routing in Large-Scale Multimedia Content Delivery Network Jian Ni, Danny H. K. Tsang, Ivan S. H. Yeung, Xiaojun Hei Department of Electrical & Electronic Engineering Hong Kong University

More information

Segment-Based Proxy Caching of Multimedia Streams

Segment-Based Proxy Caching of Multimedia Streams Segment-Based Proxy Caching of Multimedia Streams Kun-Lung Wu, Philip S. Yu and Joel L. Wolf IBM T.J. Watson Research Center 3 Saw Mill River Road Hawthorne, NY 1532 fklwu, psyu, jlwg@us.ibm.com ABSTRACT

More information

Comparison of Shaping and Buffering for Video Transmission

Comparison of Shaping and Buffering for Video Transmission Comparison of Shaping and Buffering for Video Transmission György Dán and Viktória Fodor Royal Institute of Technology, Department of Microelectronics and Information Technology P.O.Box Electrum 229, SE-16440

More information

Proxy Caching for Video on Demand Systems in Multicasting Networks

Proxy Caching for Video on Demand Systems in Multicasting Networks MER A MITSUBISHI EECTRIC RESEARCH ABORATORY http://wwwmerlcom roxy Caching for Video on Demand Systems in Multicasting Networks i Zhu, Gang Cheng, Nirwan Ansari, Zafer Sahinoglu, Anthony Vetro, and Huifang

More information

An Interactive Video Delivery and Caching System Using Video Summarization

An Interactive Video Delivery and Caching System Using Video Summarization An Interactive Video Delivery and Caching System Using Video Summarization Sung-Ju Lee, Wei-Ying Ma, and Bo Shen Hewlett-Packard Laboratories 1501 Page Mill Road Palo Alto, CA 930-112 {sjlee, boshen}@hpl.hp.com;

More information

Modelling and Analysis of Push Caching

Modelling and Analysis of Push Caching Modelling and Analysis of Push Caching R. G. DE SILVA School of Information Systems, Technology & Management University of New South Wales Sydney 2052 AUSTRALIA Abstract: - In e-commerce applications,

More information

5. Conclusion. 6. References

5. Conclusion. 6. References Delivery Techniques Developing hybrid bandwidth smoothing techniques that are aimed for both VCR interactivity as well as high-utilization of networ channels are required. This involves both the interaction

More information

Surveying Formal and Practical Approaches for Optimal Placement of Replicas on the Web

Surveying Formal and Practical Approaches for Optimal Placement of Replicas on the Web Surveying Formal and Practical Approaches for Optimal Placement of Replicas on the Web TR020701 April 2002 Erbil Yilmaz Department of Computer Science The Florida State University Tallahassee, FL 32306

More information

Network-Adaptive Video Coding and Transmission

Network-Adaptive Video Coding and Transmission Header for SPIE use Network-Adaptive Video Coding and Transmission Kay Sripanidkulchai and Tsuhan Chen Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213

More information

THE CACHE REPLACEMENT POLICY AND ITS SIMULATION RESULTS

THE CACHE REPLACEMENT POLICY AND ITS SIMULATION RESULTS THE CACHE REPLACEMENT POLICY AND ITS SIMULATION RESULTS 1 ZHU QIANG, 2 SUN YUQIANG 1 Zhejiang University of Media and Communications, Hangzhou 310018, P.R. China 2 Changzhou University, Changzhou 213022,

More information

HSM: A Hybrid Streaming Mechanism for Delay-tolerant Multimedia Applications Annanda Th. Rath 1 ), Saraswathi Krithivasan 2 ), Sridhar Iyer 3 )

HSM: A Hybrid Streaming Mechanism for Delay-tolerant Multimedia Applications Annanda Th. Rath 1 ), Saraswathi Krithivasan 2 ), Sridhar Iyer 3 ) HSM: A Hybrid Streaming Mechanism for Delay-tolerant Multimedia Applications Annanda Th. Rath 1 ), Saraswathi Krithivasan 2 ), Sridhar Iyer 3 ) Abstract Traditionally, Content Delivery Networks (CDNs)

More information

Streaming and Broadcasting over the Internet

Streaming and Broadcasting over the Internet Streaming and Broadcasting over the Internet Markus Hofmann and Krishan Sabnani, Bell Labs Research, Holmdel, NJ, USA Abstract As the number of people accessing the Internet grows and commerce becomes

More information

Improving object cache performance through selective placement

Improving object cache performance through selective placement University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2006 Improving object cache performance through selective placement Saied

More information

INF5071 Performance in distributed systems Distribution Part II

INF5071 Performance in distributed systems Distribution Part II INF5071 Performance in distributed systems Distribution Part II 5 November 2010 Type IV Distribution Systems Combine Types I, II or III Network of servers Server hierarchy Autonomous servers Cooperative

More information

Evaluation of traffic dispersion methods for synchronous distributed multimedia data transmission on multiple links for group of mobile hosts

Evaluation of traffic dispersion methods for synchronous distributed multimedia data transmission on multiple links for group of mobile hosts Int. J. Applied Systemic Studies, Vol. 3, No. 1, 2010 89 Evaluation of traffic dispersion methods for synchronous distributed multimedia data transmission on multiple links for group of mobile hosts Yoshia

More information

Proxy Caching Mechanism for Multimedia Playback Streams in the Internet

Proxy Caching Mechanism for Multimedia Playback Streams in the Internet Proxy Caching Mechanism for Multimedia Playback Streams in the Internet Reza Rejaie, Mark Handley, Haobo Yu, Deborah Estrin University of Southern California Department of Computer Science Information

More information

Characterizing Document Types to Evaluate Web Cache Replacement Policies

Characterizing Document Types to Evaluate Web Cache Replacement Policies Characterizing Document Types to Evaluate Web Cache Replacement Policies F.J. Gonzalez-Cañete, E. Casilari, Alicia Triviño-Cabrera Dpto. Tecnología Electrónica, Universidad de Málaga, E.T.S.I. Telecomunicación,

More information

An Analysis of the Number of ICP Packets on the Distributed WWW Caching System

An Analysis of the Number of ICP Packets on the Distributed WWW Caching System An Analysis of the Number of ICP Packets on the Distributed WWW Caching System Eiji Kawai, Ken-ichi Chinen, Suguru Yamaguchi and Hideki Sunahara Nara Institute of Science and Technology 8916-5 Takayama,

More information

IMPROVING LIVE PERFORMANCE IN HTTP ADAPTIVE STREAMING SYSTEMS

IMPROVING LIVE PERFORMANCE IN HTTP ADAPTIVE STREAMING SYSTEMS IMPROVING LIVE PERFORMANCE IN HTTP ADAPTIVE STREAMING SYSTEMS Kevin Streeter Adobe Systems, USA ABSTRACT While HTTP adaptive streaming (HAS) technology has been very successful, it also generally introduces

More information

COPACC: A Cooperative Proxy-Client Caching System for On-demand Media Streaming

COPACC: A Cooperative Proxy-Client Caching System for On-demand Media Streaming COPACC: A Cooperative - Caching System for On-demand Media Streaming Alan T.S. Ip 1, Jiangchuan Liu 2, and John C.S. Lui 1 1 The Chinese University of Hong Kong, Shatin, N.T., Hong Kong {tsip, cslui}@cse.cuhk.edu.hk

More information

Chapter The LRU* WWW proxy cache document replacement algorithm

Chapter The LRU* WWW proxy cache document replacement algorithm Chapter The LRU* WWW proxy cache document replacement algorithm Chung-yi Chang, The Waikato Polytechnic, Hamilton, New Zealand, itjlc@twp.ac.nz Tony McGregor, University of Waikato, Hamilton, New Zealand,

More information

Multimedia Networking

Multimedia Networking CMPT765/408 08-1 Multimedia Networking 1 Overview Multimedia Networking The note is mainly based on Chapter 7, Computer Networking, A Top-Down Approach Featuring the Internet (4th edition), by J.F. Kurose

More information

TCP PERFORMANCE FOR FUTURE IP-BASED WIRELESS NETWORKS

TCP PERFORMANCE FOR FUTURE IP-BASED WIRELESS NETWORKS TCP PERFORMANCE FOR FUTURE IP-BASED WIRELESS NETWORKS Deddy Chandra and Richard J. Harris School of Electrical and Computer System Engineering Royal Melbourne Institute of Technology Melbourne, Australia

More information

On the Feasibility of Prefetching and Caching for Online TV Services: A Measurement Study on

On the Feasibility of Prefetching and Caching for Online TV Services: A Measurement Study on See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/220850337 On the Feasibility of Prefetching and Caching for Online TV Services: A Measurement

More information

Loopback: Exploiting Collaborative Caches for Large-Scale Streaming

Loopback: Exploiting Collaborative Caches for Large-Scale Streaming Loopback: Exploiting Collaborative Caches for Large-Scale Streaming Ewa Kusmierek Yingfei Dong David Du Poznan Supercomputing and Dept. of Electrical Engineering Dept. of Computer Science Networking Center

More information

Audio Streams Merging Over ALMI

Audio Streams Merging Over ALMI Audio Streams Merging Over ALMI Christopher J. Dunkle, Zhen Zhang, Sherlia Y. Shi, Zongming Fei Department of Computer Science University of Kentucky 301 Rose Street, 2 nd floor Lexington, KY 40506-0495,

More information

Proxy Prefix Caching for Multimedia Streams

Proxy Prefix Caching for Multimedia Streams Proxy Prefix Caching for Multimedia Streams Subhabrata Seny, Jennifer Rexfordz, and Don Towsleyy ydept. of Computer Science znetworking & Distributed Systems University of Massachusetts AT&T Labs Research

More information

Using Multicast for Streaming Videos across Wide Area Networks

Using Multicast for Streaming Videos across Wide Area Networks Using Multicast for Streaming Videos across Wide Area Networks Bing Wang, Subhabrata Sen, Micah Adler and Don Towsley Department of Computer Science University of Massachusetts, Amherst, MA 0003 AT&T Labs-Research,

More information

Subway : Peer-To-Peer Clustering of Clients for Web Proxy

Subway : Peer-To-Peer Clustering of Clients for Web Proxy Subway : Peer-To-Peer Clustering of Clients for Web Proxy Kyungbaek Kim and Daeyeon Park Department of Electrical Engineering & Computer Science, Division of Electrical Engineering, Korea Advanced Institute

More information

Decentralized Hash-Based Coordination of Distributed Multimedia Caches

Decentralized Hash-Based Coordination of Distributed Multimedia Caches Decentralized Hash-Based Coordination of Distributed Multimedia Caches Anup Mayank Chinya Ravishankar Department of Computer Science and Engineering University of California, Riverside Riverside, CA 97

More information

Optimal Proxy Cache Allocation for Efficient Streaming Media Distribution

Optimal Proxy Cache Allocation for Efficient Streaming Media Distribution University of Massachusetts Amherst ScholarWorks@UMass Amherst Computer Science Department Faculty Publication Series Computer Science Optimal Proxy Cache Allocation for Efficient Streaming Media Distribution

More information

Stretch-Optimal Scheduling for On-Demand Data Broadcasts

Stretch-Optimal Scheduling for On-Demand Data Broadcasts Stretch-Optimal Scheduling for On-Demand Data roadcasts Yiqiong Wu and Guohong Cao Department of Computer Science & Engineering The Pennsylvania State University, University Park, PA 6 E-mail: fywu,gcaog@cse.psu.edu

More information

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 8, NO. 2, APRIL Segment-Based Streaming Media Proxy: Modeling and Optimization

IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 8, NO. 2, APRIL Segment-Based Streaming Media Proxy: Modeling and Optimization IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 8, NO. 2, APRIL 2006 243 Segment-Based Streaming Media Proxy: Modeling Optimization Songqing Chen, Member, IEEE, Bo Shen, Senior Member, IEEE, Susie Wee, Xiaodong

More information

Delay Constrained ARQ Mechanism for MPEG Media Transport Protocol Based Video Streaming over Internet

Delay Constrained ARQ Mechanism for MPEG Media Transport Protocol Based Video Streaming over Internet Delay Constrained ARQ Mechanism for MPEG Media Transport Protocol Based Video Streaming over Internet Hong-rae Lee, Tae-jun Jung, Kwang-deok Seo Division of Computer and Telecommunications Engineering

More information

Dynamic Broadcast Scheduling in DDBMS

Dynamic Broadcast Scheduling in DDBMS Dynamic Broadcast Scheduling in DDBMS Babu Santhalingam #1, C.Gunasekar #2, K.Jayakumar #3 #1 Asst. Professor, Computer Science and Applications Department, SCSVMV University, Kanchipuram, India, #2 Research

More information

Video Streaming Over the Internet

Video Streaming Over the Internet Video Streaming Over the Internet 1. Research Team Project Leader: Graduate Students: Prof. Leana Golubchik, Computer Science Department Bassem Abdouni, Adam W.-J. Lee 2. Statement of Project Goals Quality

More information

Cost-based cache replacement and server selection for multimedia proxy across wireless Internet

Cost-based cache replacement and server selection for multimedia proxy across wireless Internet University of Massachusetts Amherst From the SelectedWorks of Lixin Gao January 1, 2004 Cost-based cache replacement and server selection for multimedia proxy across wireless Internet Q Zhang Z Xiang WW

More information

COOCHING: Cooperative Prefetching Strategy for P2P Video-on-Demand System

COOCHING: Cooperative Prefetching Strategy for P2P Video-on-Demand System COOCHING: Cooperative Prefetching Strategy for P2P Video-on-Demand System Ubaid Abbasi and Toufik Ahmed CNRS abri ab. University of Bordeaux 1 351 Cours de la ibération, Talence Cedex 33405 France {abbasi,

More information

Quality Differentiation with Source Shaping and Forward Error Correction

Quality Differentiation with Source Shaping and Forward Error Correction Quality Differentiation with Source Shaping and Forward Error Correction György Dán and Viktória Fodor KTH, Royal Institute of Technology, Department of Microelectronics and Information Technology, {gyuri,viktoria}@imit.kth.se

More information

AN ASSOCIATIVE TERNARY CACHE FOR IP ROUTING. 1. Introduction. 2. Associative Cache Scheme

AN ASSOCIATIVE TERNARY CACHE FOR IP ROUTING. 1. Introduction. 2. Associative Cache Scheme AN ASSOCIATIVE TERNARY CACHE FOR IP ROUTING James J. Rooney 1 José G. Delgado-Frias 2 Douglas H. Summerville 1 1 Dept. of Electrical and Computer Engineering. 2 School of Electrical Engr. and Computer

More information

Multimedia Streaming. Mike Zink

Multimedia Streaming. Mike Zink Multimedia Streaming Mike Zink Technical Challenges Servers (and proxy caches) storage continuous media streams, e.g.: 4000 movies * 90 minutes * 10 Mbps (DVD) = 27.0 TB 15 Mbps = 40.5 TB 36 Mbps (BluRay)=

More information

Interactive Branched Video Streaming and Cloud Assisted Content Delivery

Interactive Branched Video Streaming and Cloud Assisted Content Delivery Interactive Branched Video Streaming and Cloud Assisted Content Delivery Niklas Carlsson Linköping University, Sweden @ Sigmetrics TPC workshop, Feb. 2016 The work here was in collaboration... Including

More information

Elimination Of Redundant Data using user Centric Data in Delay Tolerant Network

Elimination Of Redundant Data using user Centric Data in Delay Tolerant Network IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 9 February 2015 ISSN (online): 2349-6010 Elimination Of Redundant Data using user Centric Data in Delay Tolerant

More information

Mocha: A Quality Adaptive Multimedia Proxy Cache for Internet Streaming

Mocha: A Quality Adaptive Multimedia Proxy Cache for Internet Streaming Mocha: A Quality Adaptive Multimedia Proxy Cache for Internet Streaming Reza Rejaie AT&T Labs - Research Menlo Park, CA. 94025 reza@research.att.com Jussi Kangasharju Institut Eurecom Sophia Antipolis,

More information

To address these challenges, extensive research has been conducted and have introduced six key areas of streaming video, namely: video compression,

To address these challenges, extensive research has been conducted and have introduced six key areas of streaming video, namely: video compression, Design of an Application Layer Congestion Control for Reducing network load and Receiver based Buffering Technique for packet synchronization in Video Streaming over the Internet Protocol Mushfeq-Us-Saleheen

More information

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT

ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT ADAPTIVE AND DYNAMIC LOAD BALANCING METHODOLOGIES FOR DISTRIBUTED ENVIRONMENT PhD Summary DOCTORATE OF PHILOSOPHY IN COMPUTER SCIENCE & ENGINEERING By Sandip Kumar Goyal (09-PhD-052) Under the Supervision

More information

Analysis of Resource Sharing and Cache Management in Scalable Video-on-Demand

Analysis of Resource Sharing and Cache Management in Scalable Video-on-Demand Analysis of Resource Sharing and Cache Management in Scalable Video-on-Demand Bashar Qudah and Nabil J. Sarhan Department of Electrical and Computer Engineering Wayne State University Detroit, MI 482,

More information

AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS

AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS AN IMPROVED STEP IN MULTICAST CONGESTION CONTROL OF COMPUTER NETWORKS Shaikh Shariful Habib Assistant Professor, Computer Science & Engineering department International Islamic University Chittagong Bangladesh

More information

Quality of Service in the Internet

Quality of Service in the Internet Quality of Service in the Internet Problem today: IP is packet switched, therefore no guarantees on a transmission is given (throughput, transmission delay, ): the Internet transmits data Best Effort But:

More information

Journal of Electronics and Communication Engineering & Technology (JECET)

Journal of Electronics and Communication Engineering & Technology (JECET) Journal of Electronics and Communication Engineering & Technology (JECET) JECET I A E M E Journal of Electronics and Communication Engineering & Technology (JECET)ISSN ISSN 2347-4181 (Print) ISSN 2347-419X

More information

Scalability And The Bandwidth Efficiency Of Vod Systems K.Deepathilak et al.,

Scalability And The Bandwidth Efficiency Of Vod Systems K.Deepathilak et al., Asian Journal of Electrical Sciences (AJES) Vol.3.No.1 2015 pp 33-37. available at: www.goniv.com Paper Received :08-03-2015 Paper Accepted:20-03-2015 Paper Reviewed by: 1. R. Venkatakrishnan 2. R. Marimuthu

More information

Chunk Scheduling Strategies In Peer to Peer System-A Review

Chunk Scheduling Strategies In Peer to Peer System-A Review Chunk Scheduling Strategies In Peer to Peer System-A Review Sanu C, Deepa S S Abstract Peer-to-peer ( P2P) s t r e a m i n g systems have become popular in recent years. Several peer- to-peer systems for

More information

Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems

Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems Differential Compression and Optimal Caching Methods for Content-Based Image Search Systems Di Zhong a, Shih-Fu Chang a, John R. Smith b a Department of Electrical Engineering, Columbia University, NY,

More information

Cache Design for Transcoding Proxy Caching

Cache Design for Transcoding Proxy Caching Cache Design for Transcoding Proxy Caching Keqiu Li, Hong Shen, and Keishi Tajima Graduate School of Information Science Japan Advanced Institute of Science and Technology 1-1 Tatsunokuchi, Ishikawa, 923-1292,

More information

Distributed Scheduling for the Sombrero Single Address Space Distributed Operating System

Distributed Scheduling for the Sombrero Single Address Space Distributed Operating System Distributed Scheduling for the Sombrero Single Address Space Distributed Operating System Donald S. Miller Department of Computer Science and Engineering Arizona State University Tempe, AZ, USA Alan C.

More information

Power and Locality Aware Request Distribution Technical Report Heungki Lee, Gopinath Vageesan and Eun Jung Kim Texas A&M University College Station

Power and Locality Aware Request Distribution Technical Report Heungki Lee, Gopinath Vageesan and Eun Jung Kim Texas A&M University College Station Power and Locality Aware Request Distribution Technical Report Heungki Lee, Gopinath Vageesan and Eun Jung Kim Texas A&M University College Station Abstract With the growing use of cluster systems in file

More information

Enhancing Downloading Time By Using Content Distribution Algorithm

Enhancing Downloading Time By Using Content Distribution Algorithm RESEARCH ARTICLE OPEN ACCESS Enhancing Downloading Time By Using Content Distribution Algorithm VILSA V S Department of Computer Science and Technology TKM Institute of Technology, Kollam, Kerala Mailid-vilsavijay@gmail.com

More information

Adaptive Real-time Monitoring Mechanism for Replicated Distributed Video Player Systems

Adaptive Real-time Monitoring Mechanism for Replicated Distributed Video Player Systems Adaptive Real-time Monitoring Mechanism for Replicated Distributed Player Systems Chris C.H. Ngan, Kam-Yiu Lam and Edward Chan Department of Computer Science City University of Hong Kong 83 Tat Chee Avenue,

More information

Variable Step Fluid Simulation for Communication Network

Variable Step Fluid Simulation for Communication Network Variable Step Fluid Simulation for Communication Network Hongjoong Kim 1 and Junsoo Lee 2 1 Korea University, Seoul, Korea, hongjoong@korea.ac.kr 2 Sookmyung Women s University, Seoul, Korea, jslee@sookmyung.ac.kr

More information

MaVIS: Media-aware Video Streaming Mechanism

MaVIS: Media-aware Video Streaming Mechanism MaVIS: Media-aware Video Streaming Mechanism Sunhun Lee and Kwangsue Chung School of Electronics Engineering, Kwangwoon University, Korea sunlee@adamskwackr and kchung@kwackr Abstract Existing streaming

More information

IN recent years, the amount of traffic has rapidly increased

IN recent years, the amount of traffic has rapidly increased , March 15-17, 2017, Hong Kong Content Download Method with Distributed Cache Management Masamitsu Iio, Kouji Hirata, and Miki Yamamoto Abstract This paper proposes a content download method with distributed

More information

Improving TCP Performance over Wireless Networks using Loss Predictors

Improving TCP Performance over Wireless Networks using Loss Predictors Improving TCP Performance over Wireless Networks using Loss Predictors Fabio Martignon Dipartimento Elettronica e Informazione Politecnico di Milano P.zza L. Da Vinci 32, 20133 Milano Email: martignon@elet.polimi.it

More information

Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks

Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks Impact of End-to-end QoS Connectivity on the Performance of Remote Wireless Local Networks Veselin Rakocevic School of Engineering and Mathematical Sciences City University London EC1V HB, UK V.Rakocevic@city.ac.uk

More information

Volume 3, Issue 9, September 2013 International Journal of Advanced Research in Computer Science and Software Engineering

Volume 3, Issue 9, September 2013 International Journal of Advanced Research in Computer Science and Software Engineering Volume 3, Issue 9, September 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Optimal Round

More information

ENHANCING ENERGY EFFICIENT TCP BY PARTIAL RELIABILITY

ENHANCING ENERGY EFFICIENT TCP BY PARTIAL RELIABILITY ENHANCING ENERGY EFFICIENT TCP BY PARTIAL RELIABILITY L. Donckers, P.J.M. Havinga, G.J.M. Smit, L.T. Smit University of Twente, department of Computer Science, PO Box 217, 7 AE Enschede, the Netherlands

More information

Quality of Service in the Internet

Quality of Service in the Internet Quality of Service in the Internet Problem today: IP is packet switched, therefore no guarantees on a transmission is given (throughput, transmission delay, ): the Internet transmits data Best Effort But:

More information

CCNA Exploration Network Fundamentals. Chapter 06 Addressing the Network IPv4

CCNA Exploration Network Fundamentals. Chapter 06 Addressing the Network IPv4 CCNA Exploration Network Fundamentals Chapter 06 Addressing the Network IPv4 Updated: 20/05/2008 1 6.0.1 Introduction Addressing is a key function of Network layer protocols that enables data communication

More information

The Last-Copy Approach for Distributed Cache Pruning in a Cluster of HTTP Proxies

The Last-Copy Approach for Distributed Cache Pruning in a Cluster of HTTP Proxies The Last-Copy Approach for Distributed Cache Pruning in a Cluster of HTTP Proxies Reuven Cohen and Itai Dabran Technion, Haifa 32000, Israel Abstract. Web caching has been recognized as an important way

More information

Optimal Proxy Cache Allocation for Efficient Streaming Media Distribution

Optimal Proxy Cache Allocation for Efficient Streaming Media Distribution 1 ptimal Proxy Cache Allocation for Efficient Streaming Media Distribution Bing Wang, Subhabrata Sen, Micah Adler and Don Towsley Department of Computer Science University of Massachusetts, Amherst, MA

More information

Mohammad Hossein Manshaei 1393

Mohammad Hossein Manshaei 1393 Mohammad Hossein Manshaei manshaei@gmail.com 1393 Voice and Video over IP Slides derived from those available on the Web site of the book Computer Networking, by Kurose and Ross, PEARSON 2 Multimedia networking:

More information

The Transmitted Strategy of Proxy Cache Based on Segmented Video

The Transmitted Strategy of Proxy Cache Based on Segmented Video The Transmitted Strategy of Proxy Cache Based on Segmented Video Zhiwen Xu, Xiaoxin Guo, Yunjie Pang, Zhengxuan Wang Faculty of Computer Science and Technology, Jilin University, Changchun City, 130012,

More information

Cost-based Pricing for Multicast Streaming Services

Cost-based Pricing for Multicast Streaming Services Cost-based Pricing for Multicast Streaming Services Eiji TAKAHASHI, Takaaki OHARA, Takumi MIYOSHI,, and Yoshiaki TANAKA Global Information and Telecommunication Institute, Waseda Unviersity 29-7 Bldg.,

More information

Assignment 5. Georgia Koloniari

Assignment 5. Georgia Koloniari Assignment 5 Georgia Koloniari 2. "Peer-to-Peer Computing" 1. What is the definition of a p2p system given by the authors in sec 1? Compare it with at least one of the definitions surveyed in the last

More information

ENHANCING QoS IN WEB CACHING USING DIFFERENTIATED SERVICES

ENHANCING QoS IN WEB CACHING USING DIFFERENTIATED SERVICES ENHANCING QoS IN WEB CACHING USING DIFFERENTIATED SERVICES P.Venketesh 1, S.N. Sivanandam 2, S.Manigandan 3 1. Research Scholar, 2. Professor and Head, 3. Research Scholar Department of Computer Science

More information