Improved Load Balancing in Distributed Service Architectures

Size: px
Start display at page:

Download "Improved Load Balancing in Distributed Service Architectures"

Transcription

1 Improved Load Balancing in Distributed Service Architectures LI-CHOO CHEN, JASVAN LOGESWAN, AND AZIAH ALI Faculty of Engineering, Multimedia University, 631 Cyberjaya, MALAYSIA. Abstract: - The advancement in the field of Distributed Object-oriented Computing has motivated the development of flexible telecommunication architectures for the current telecommunication market. The Object-oriented Distributed Service Architectures utilize the principles of distributed object-oriented programming such that these telecom architectures are open, object-oriented, distributed and allow rapid and flexible development of new applications on all kinds of software and hardware platforms. Despite the location transparency offered by these architectures, performance problems occur due to the distributed nature of the computational objects in several different physical nodes, which causes overloading in the nodes and unnecessary inter-node communication. In this paper, we propose a new load balancing algorithm, Random Sender Initiated Algorithm, that is able to improve the system performance of the distributed service architecture. This newly developed algorithm has shown a better performance as compared to the benchmark load balancing algorithms. Key-Words: - Object-oriented Distributed Service Architectures, Load Balancing, Performance, TINA, Computational Objects, CO distribution. 1. Introduction The latest telecommunications market has been influenced much by the advancement in the computer and Information Technology fields. The development in the area of distributed objectoriented computing has provided a greater room for flexible telecommunication architectures to be developed. The object-oriented distributed service architectures, utilizing the concept of distributed processing and object orientation, are expected to cater for rapid service creation and good management of telecommunication services. Examples of these architectures include Intelligent Network (IN), Telecommunication Information Networking Architecture (TINA), and Open Service Access (OSA). The main idea of a good service architecture is the separation of the service logic and control from the actual call switching. Since the architectures are normally distributed, the service execution and control are carried out in several physical nodes in the network. In an object-oriented service architecture (see Fig. 1), a number of objects have to interact with one another during service execution, while instances of the same object type can be positioned on several different physical nodes. Different object distributions will result in different amounts of inter-node communication and different loading conditions on the nodes. This causes inconsistent system performance, an unresolved problem in object-oriented distributed service architectures (DSA). Three performance issues in DSA are [1]: Object Distribution, Overload Control Mechanism, and Load Balancing. The object distribution problem can be formulated as: How can the objects of the application be distributed in the network such that the service setup times and server loads can be optimised? The overload control problem may be devised as: What action should be taken during overload so that the Quality of Service (QoS) demands from both the services and users can be met. Consequently, the load balancing problem is very much related to a condition where given an object distribution, which object instance of a certain object type should be chosen during a task execution to ensure that no node is overloaded while another node has spare capacity [1].

2 a b c Network Fig. 1 An object-oriented distributed service architecture (DSA) Each of the performance issues above is a wide research topic and requires more in-depth study to explore possible solutions to improve system performance. Hence, in this paper, we only focus on the aspect of load balancing algorithm. Numerous papers have been published concerning load balancing and load sharing in computer networks. However, few of them discuss load balancing algorithm for DSA. This paper extends the work by Kihl et al [2] and McArdle et al. [3] with the aim to propose a load balancing algorithm which is able to perform better than the benchmark load balancing algorithms discussed in the above work. The proposed Random Sender Initiated Algorithm has been investigated under several simulation conditions and has exhibited better network performance than the benchmark algorithms, Shortest Queue Algorithm and Random Algorithm. The TINA architecture on which the simulation model is based on is described in the next section. 2. TINA The Telecommunications Information Networking Architecture (TINA), started in 199, is a proposed architecture to bring together two industries: telecommunications and information technology. The TINA Consortium (TINA-C) was formed in 1993, consisting of approximately 4 leading companies, including network operators, IT vendors and telecom vendors [4]. TINA combines a variety of new computing technologies and applies them coherently to a complete set of architectural principles to shape a future-safe telecommunication and information marketplace. TINA [5] provides a set of concepts and principles to be applied in the specification, design, implementation, deployment, execution, and operation of software for telecommunication systems. The overall architecture of TINA is c d d b partitioned into service architecture, network architecture, management architecture and computing architecture. More details on these architectures are available in Chapman and Montensi [6]. For this research work, the major architectures of interest are computing and service architectures. The service architecture defines a set of concepts and principles for the design, specification, implementation and management of telecommunication services. The computing architecture defines a set of concepts and principles for designing and building distributed software and software support environment. One important concept in TINA is session. A session represents the information used by all processes involved in the provision of a service for certain duration. Four types of sessions are available in TINA: a) Service session handles a single activation of service. b) User session deals with a user s interaction with a service session. c) Access session deals with user s authentication and authorisation. d) Communication session supports the communication needs of the service session and manages communication resources. Computational objects (COs) are programming and encapsulation units in TINA. The objects are able to interact with each other by exchanging information using two forms of computational interfaces. The operational interface allows the functions of the offering object to be invoked by other objects. The stream interface connects communication endpoints producing or consuming information flows, for example video or voice components. Another important concept in TINA is the Distributed Processing Environment (DPE). The DPE hides the complexity of distribution and heterogeneity from the service developer. Thus, the DPE provides access transparency, location transparency and failure transparency [6]. 3. Load Balancing Algorithms The main purpose of load balancing is to distribute the workload equally among all nodes in the network such that the situation where one node is idle or lightly loaded while others are heavily loaded, will not occur. Therefore, we expect that the average service time for a request would be minimised while the throughput is optimised by applying load balancing in a network. There are three different load balancing algorithms

3 implemented in our simulations - two benchmark algorithms and the proposed algorithm. The benchmark algorithms, Shortest Queue Algorithm and Random Algorithm, as described in [3] have been chosen for our investigation to enable performance evaluation of the proposed algorithm. The advantage of these algorithms is that they allow the theoretical upper bounds (or close to the upper bounds) of the performance measures to be achieved. However, each of these algorithms has its weaknesses in the real world implementation. The following briefly describes the benchmark algorithms: a) Random Algorithm: An instance of a computational object (CO) is chosen randomly and fairly from the node that contains instances of the particular CO type. The benefits of this algorithm is that it does not require any exchange of load information which results in less inter-communication cost and this algorithm is simple in term of implementation. However, the shortcoming of this algorithm is it is possible for a job to be sent to a node which is more heavily loaded even if there are other lightly loaded nodes around, as no load information is taken into account in the job assignment. b) Shortest Queue Algorithm: A node that consists of the instance of the particular CO type with shortest job queue will always be selected. This algorithm can be assumed to be the ideal algorithm if the service times for all COs are almost the same. Nevertheless, the DPE does not have all the load information of all other nodes in the real life. DPE has to get the information from other nodes from time to time and frequent exchange of information is cost-intensive. This becomes the performance bottleneck for the system itself. The newly proposed algorithm is as follows: a) Random Sender Initiated Algorithm: This algorithm is proposed to overcome the drawback of the Random Algorithm. It is implemented based on the thresholding concept. A CO will be chosen randomly from each node that contains instances of that CO type. If the selected node has less than threshold value T, jobs in its queue, then the job will be sent to it. However, if the job queue of the selected node is more than T jobs, other nodes (which consist of the instances of that CO type) will be probed one at a time to determine its job queue until a node with less than T jobs in its job queue is found. The job will be transferred to this node with less that T jobs in its queue. The poll limit is M which means that the number of probing made should be less than M. The advantage of this algorithm is that most likely a job will not be transferred to a heavily loaded node because the load information of a node is taken into consideration when making job assignment decisions. The algorithm also further ensures that the probing activity will not cause performance bottleneck through the setting of a polling limit. 4. Simulation Model A generic TINA service described by [7] is used for our investigations. Ten different CO types belonging to the user and retailer domains are used in this service. The objects involved in the user domain are Provider Agent, User Application (UAP), Generic Session End Point (GSEP), and Terminal Communication Session Manager (TCSM). The retailer domain consists of Initial Agent (IA), User Agent (UA), Communication Session Manager (CSM), Service Session Manager (SSM), User Session Manager (USM), Service Factory and User Session Manager (USM). New Arrival CO type USER of user 1 CO type USER of user 2 CO type USER of user N CO type SSM Distributed Processing Environment (DPE) Fig. 2 Simulation Model CO type USM CO type CSM CO type SF CO type AGENT Node 1 Node 2 Node Y The objective of this paper is to investigate the performance of the proposed load balancing algorithm against the benchmark load balancing algorithm in a TINA network. The DPE is the interface between the objects and the nodes, handling all communication of nodes and between nodes. The model is further simplified by modelling the COs. Firstly, as all the COs in the user domain normally reside on the same physical

4 node close to the user, these objects are modelled as one USER object. Secondly, the IA and UA COs are modelled as AGENT object. The other objects still remain the same as USM, SSM, CSM and SF. The simplified simulation model is shown in Fig. 2 and is based on the simulation model implemented in [2] and [3]. The network contains Y fully connected nodes with the assumption that the underlying network is extremely fast such that the switching times are insignificant. The new arrivals (requests) to the system are modelled as a Poisson stream and each request is randomly sent to one of the USER objects. The communication between different nodes require additional transmission times, which have been modelled as the added execution times for the sender and receiver nodes. Each node acts as a processor, which executes tasks in the system. The tasks that are unable to be served immediately are put into a FIFO queue in the node. The execution of tasks is based on a simple timesharing method that runs simultaneously in all nodes. The execution time for a task is highly dependent on the type of computational object involved and also whether the DPE service is used. If the CO uses the DPE service, the execution time will be multiplied with a certain factor. 5. Investigation This section discusses the simulation conditions and simulation parameters used in this paper. A focused CO distribution is used in the simulation, with node 1 and node 2 containing the USER object, node 3 contains the objects AGENT, USM, SSM, SF and CSM, node 4 consists of AGENT and USM objects, Node 5 contains the objects AGENT, USM and SSM and consequently node 6 has AGENT and SF. Table 1: Signalling Model and Execution Times Object type Number of normal signals Number of DPE service request Execution time (in ms) USER 1-1 AGENT USM 11-1 SSM CSM 2-4 SF 5-2 The focused or unbalanced distribution mimics the realistic situation of a distributed network, where nodes of different computing power exists, denoted in the DSA simulation by the number and types of CO it possesses. The load in the network is to be balanced across these nodes. A load balancing algorithm is effectively needed in focused distributions as balanced distributions do not require further load balancing. The number of signals and DPE requests that is necessary for a call setup and also the execution times for each object type are given in Table 1. The load balancing algorithms discussed earlier have been evaluated under three different simulation conditions with the simulation parameters as shown above. The simulation conditions are discussed as follows: a) Case 1: The load balancing algorithms is tested under the free condition where the communication cost between 2 nodes for wrapping and unwrapping of the communications protocol is not taken into account. For this simulation condition, we denote the algorithms as Random Algorithm (), Shortest Queue Free Algorithm (SQF) and Random Sender Initiated Free Algorithm (RSIF) respectively. The simulation for the free condition is necessary to evaluate the performance of RSIF against the SQF in the ideal condition without including the communication cost between different nodes and the query cost. It is assumed that the DPE has immediate information on the loading of other nodes. Another condition for Case 1 is that the job queue for each node in the network has infinite capacity (similar to the condition with no overload control). b) Case 2: The algorithms are tested under the expensive condition where the communication cost between two nodes for wrapping and unwrapping of communications protocol is taken into consideration. The purpose of having the expensive condition is that this mimics a real network, which incurs communication cost and query cost.. The algorithms are denoted as Random Algorithm (), Shortest Queue Expensive Algorithm (SQEX) and Random Sender Initiated Expensive Algorithm (RSIEX) respectively. Since the selects a node randomly to transfer a job, thus, the presence of communication cost and query cost has no effect on its performance. For this test case, it is still assumed that the job queue of each node has infinite capacity. c) Case 3: The algorithms (, SQEX, and RSIEX) are still tested under the expensive

5 condition However, in the real network, each node has its own capacity, so the node gets overloaded once it exceeds its maximum capacity. Therefore for this test case, the job queue for each node is limited to a finite capacity, J, to enable performance investigation for each algorithm to be carried out in a realistic finite queue length condition. 6. Results and Discussions The performance outcomes for the load balancing algorithms are represented by the mean completion time for one successful session (request) and also system throughput. Random Sender Initiated Algorithm is capable of performing as well as the SQF, which assumed to be the ideal algorithm. Mean Completion Time (s) SQEX RSIEX Mean Completion Time (s) SQF RSIF (a) Mean Completion Time per Session (a) Mean Completion Time per Session Percentage (%) RSIEX (b) Throughput SQEX Percentage (%) RSIF SQF (b) Throughput Fig. 3: Results for Case 1 The results for Case 1 are shown in Fig. 3. From the results, we observed that the throughput remains 1% for all load balancing algorithms as no sessions are rejected when the job queue is of infinite length. Evaluating the performance of the algorithms, we see that the performs badly, as compared with the SQF and RSIF. The reason for this is that the does not use the load information in each node to make the job transfer decision. Thus, when the number of new arrivals to the system increases, becomes incapable of distributing the load equally in the network. The results also exhibit that the proposed algorithm, Fig. 4: Results for Case 2 The results in Fig. 4 illustrate the mean completion time per session and throughput for Case 2, the more practical simulation condition. As the job queue of each node has unlimited capacity, the throughput for all algorithms still remain at 1% at any arrival rate. Nevertheless, we observe that the mean completion times per session are higher for the SQEX and RSIEX, especially at higher arrival rates as compared to SQF and RSIF (in Case 1). Fig 4(a) shows that the SQEX has become unstable and unable to give the performance readings when arrival rates are more than 4s -1. This is because when the cost for communication between different nodes and cost for querying other nodes for information have to be considered in the Shortest Queue Algorithm, the frequent exchange of load information that required by this algorithm to find a node with shortest queue to transfer a task across will overload the system. On the hand, the RSIEX is able to perform relatively stable and results in the lowest (best) mean completion time per session especially at higher arrival rates among all algorithms. The reason for

6 the better RSIEX performance than is that RSIEX takes the load information into account when making job transfer decision, thus it is able to select a less heavily loaded node to send the job to for execution. Comparing with the SQEX, RSIEX is less costly as it does not make as many queries of load information. SQEX has to explicitly probe the job queue in each node of the network before the DPE can make the job assignment decision to a node. M ean Completion Time (s) Throughput (%) R A SQ EX R SIE X A rrival Rate (1/s) (a) Mean Completion Time per Session SQEX RSIEX (b) Throughput Fig. 5: Results for Case 3 Fig. 5 shows the simulation results for the realistic situation. We observe from Fig. 5(b) that the throughput is no longer 1% for all algorithms at higher arrival rates due to the limited processing capacity of each node. When there are more arrivals to the system, some nodes in the system reach their maximum capacity and get overloaded. To protect the node, some sessions (requests) have to be rejected. Therefore, we see that the throughput decreases when the arrival increases. From the results, we also observe that RSIEX is able to produce the highest throughput at all arrival rates compared to the other algorithms. At the same time, RSIEX still achieves a relatively low mean completion time per session for almost all arrival rates in comparison with SQEX and. 7. Conclusions This paper describes the proposal of a newly developed algorithm which could be utilized in a distributed service architecture (DSA) environment. From the results achieved and discussed in the paper, it is seen that the Random Sender Initiated Algorithm is capable of better performance than the benchmark load balancing algorithms. The advantage of this proposed algorithm is that it takes the load information of the nodes into account before a job assignment decision is made, and at the same time the mechanism used is not as costly as compared to the Shortest Queue Algorithm when implemented in a realistic network. The performance issue in DSA still remains an open issue. Further research needs to be carried out in this field to identify and explore possible solutions for the unresolved performance problems to fully realise the benefits of DSA. Acknowledgement: The authors wish to thank Dr. M. Kihl and Mr. N. Widell from Lund Institute of Technology (Sweden), Dr. S.W. Lee and Dr. I. Chai from Multimedia University (Malaysia), who have contributed with invaluable comments and support in this research. References: [1] N. Widell, Performance Simulation of TINA Network, published Lic. Thesis, Lund Institute of Technology, 22. [2] M. Kihl, N. Widell & C. Nyberg, Load Balancing Algorithms for TINA Networks, 16 th Int. Teletraffic Congress, Edinburg, United Kingdom, 1999, pp [3] C. McArdle, N. Widell, C. Nyberg, E. Lilja, E., J. Nystrom, & T. Curran, Simulation of a Distributed CORBA-based SCP. 7 th Intl. Conf. On Intelligence and Services in Networks, Athens, Greece, 2, pp [4] P. Coppo & Y. Inoue, The Four Dimensions OF TINA Success, TINA Intl. Conf., Paris, France, 2, pp [5] H. Berndt, P. Graubmann & T. Hamada, TINA: Its Achievements and its Future Directions, IEEE Comsoc, Comm. Surveys, March 2, pp [6] M. Chapman & S. Montesi, Overall Concepts and Principles of TINA, TINA Consortium [7] R. Minetti & E. Utsunomiya, The TINA Service Architecture, TINA Workshop 96, Heidelberg, Germany, 1996.

McArdle, Conor; Widell, Niklas; Nyberg, Christian; Lilja, Erik; Nyström, Jenny; Curran, Tommy

McArdle, Conor; Widell, Niklas; Nyberg, Christian; Lilja, Erik; Nyström, Jenny; Curran, Tommy Simulation of a distributed CORBA-based SCP McArdle, Conor; Widell, Niklas; Nyberg, Christian; Lilja, Erik; Nyström, Jenny; Curran, Tommy Published in: Telecommunications and IT convergence : towards service

More information

Web-based E-commerce Service Provisioning using a TINA Retailer

Web-based E-commerce Service Provisioning using a TINA Retailer Web-based E-commerce Service Provisioning using a TINA Retailer S. Brassell A project report submitted to the faculty of Engineering, University of the Witwatersrand, Johannesburg, in partial fulfillment

More information

Network Load Balancing Methods: Experimental Comparisons and Improvement

Network Load Balancing Methods: Experimental Comparisons and Improvement Network Load Balancing Methods: Experimental Comparisons and Improvement Abstract Load balancing algorithms play critical roles in systems where the workload has to be distributed across multiple resources,

More information

Performance Evaluation of Scheduling Mechanisms for Broadband Networks

Performance Evaluation of Scheduling Mechanisms for Broadband Networks Performance Evaluation of Scheduling Mechanisms for Broadband Networks Gayathri Chandrasekaran Master s Thesis Defense The University of Kansas 07.31.2003 Committee: Dr. David W. Petr (Chair) Dr. Joseph

More information

8. CONCLUSION AND FUTURE WORK. To address the formulated research issues, this thesis has achieved each of the objectives delineated in Chapter 1.

8. CONCLUSION AND FUTURE WORK. To address the formulated research issues, this thesis has achieved each of the objectives delineated in Chapter 1. 134 8. CONCLUSION AND FUTURE WORK 8.1 CONCLUSION Virtualization and internet availability has increased virtualized server cluster or cloud computing environment deployments. With technological advances,

More information

QUALITY of SERVICE. Introduction

QUALITY of SERVICE. Introduction QUALITY of SERVICE Introduction There are applications (and customers) that demand stronger performance guarantees from the network than the best that could be done under the circumstances. Multimedia

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

Performance analysis and overload control of an open service access (OSA) architecture

Performance analysis and overload control of an open service access (OSA) architecture Performance analysis and overload control of an open service access (OSA) architecture Jens K. Andersson *, Christian Nyberg and Maria Kihl Department of Communication Systems, Lund Institute of Technology

More information

A New Call Admission Control scheme for Real-time traffic in Wireless Networks

A New Call Admission Control scheme for Real-time traffic in Wireless Networks A New Call Admission Control scheme for Real-time traffic in Wireless Networks Maneesh Tewari and H.S. Jamadagni Center for Electronics Design and Technology, Indian Institute of Science, Bangalore, 5612

More information

Control and Management of Home Networks Using a CORBA Enabled Residential Gateway

Control and Management of Home Networks Using a CORBA Enabled Residential Gateway Control and Management of Home Networks Using a CORBA Enabled Residential Y.C. Shou 1, R. Prasad, S. Mohapi and H.E. Hanrahan Centre for Telecommunications Access and Services School of Electrical and

More information

Estimation of the Effects of non-in Traffic on IN Service Control Point Congestion Control Performance

Estimation of the Effects of non-in Traffic on IN Service Control Point Congestion Control Performance SCHOOL OF ELECTRONIC ENGINEERING Internal Technical Report Estimation of the Effects of non-in Traffic on IN Service Control Point Congestion Control Performance F. Lodge, T. Curran. Dublin City University,

More information

A Comparative Study of Load Balancing Algorithms: A Review Paper

A Comparative Study of Load Balancing Algorithms: A Review Paper Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 5.258 IJCSMC,

More information

Operating Systems Unit 3

Operating Systems Unit 3 Unit 3 CPU Scheduling Algorithms Structure 3.1 Introduction Objectives 3.2 Basic Concepts of Scheduling. CPU-I/O Burst Cycle. CPU Scheduler. Preemptive/non preemptive scheduling. Dispatcher Scheduling

More information

Institute of Computer Technology - Vienna University of Technology. L73 - IP QoS Integrated Services Model. Integrated Services Model

Institute of Computer Technology - Vienna University of Technology. L73 - IP QoS Integrated Services Model. Integrated Services Model Integrated Services Model IP QoS IntServ Integrated Services Model Resource Reservation Protocol (RSVP) Agenda Integrated Services Principles Resource Reservation Protocol RSVP Message Formats RSVP in

More information

Performance Extrapolation for Load Testing Results of Mixture of Applications

Performance Extrapolation for Load Testing Results of Mixture of Applications Performance Extrapolation for Load Testing Results of Mixture of Applications Subhasri Duttagupta, Manoj Nambiar Tata Innovation Labs, Performance Engineering Research Center Tata Consulting Services Mumbai,

More information

CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS

CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS 28 CHAPTER 3 EFFECTIVE ADMISSION CONTROL MECHANISM IN WIRELESS MESH NETWORKS Introduction Measurement-based scheme, that constantly monitors the network, will incorporate the current network state in the

More information

Design Intentions. IP QoS IntServ. Agenda. Design Intentions. L73 - IP QoS Integrated Services Model. L73 - IP QoS Integrated Services Model

Design Intentions. IP QoS IntServ. Agenda. Design Intentions. L73 - IP QoS Integrated Services Model. L73 - IP QoS Integrated Services Model Design Intentions Integrated Services Model IP QoS IntServ Integrated Services Model Resource Reservation Protocol (RSVP) The Internet was based on a best effort packet delivery service, but nowadays the

More information

Advanced Topics UNIT 2 PERFORMANCE EVALUATIONS

Advanced Topics UNIT 2 PERFORMANCE EVALUATIONS Advanced Topics UNIT 2 PERFORMANCE EVALUATIONS Structure Page Nos. 2.0 Introduction 4 2. Objectives 5 2.2 Metrics for Performance Evaluation 5 2.2. Running Time 2.2.2 Speed Up 2.2.3 Efficiency 2.3 Factors

More information

Load Balancing Algorithm over a Distributed Cloud Network

Load Balancing Algorithm over a Distributed Cloud Network Load Balancing Algorithm over a Distributed Cloud Network Priyank Singhal Student, Computer Department Sumiran Shah Student, Computer Department Pranit Kalantri Student, Electronics Department Abstract

More information

A Handover Optimisation Scheme in Cellular Networks

A Handover Optimisation Scheme in Cellular Networks A Handover Optimisation Scheme in Cellular Networks A.Gueroui and S.Boumerdassi Laboratoire PRiSM, Université de Versailles 45, Avenue des Etats-Unis 78035 Versailles France Laboratoire CEDRIC, CNAM 292,

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

Optimizing Capacity-Heterogeneous Unstructured P2P Networks for Random-Walk Traffic

Optimizing Capacity-Heterogeneous Unstructured P2P Networks for Random-Walk Traffic Optimizing Capacity-Heterogeneous Unstructured P2P Networks for Random-Walk Traffic Chandan Rama Reddy Microsoft Joint work with Derek Leonard and Dmitri Loguinov Internet Research Lab Department of Computer

More information

Load Balancing Algorithms in Cloud Computing: A Comparative Study

Load Balancing Algorithms in Cloud Computing: A Comparative Study Load Balancing Algorithms in Cloud Computing: A Comparative Study T. Deepa Dr. Dhanaraj Cheelu Ravindra College of Engineering for Women G. Pullaiah College of Engineering and Technology Kurnool Kurnool

More information

MITIGATION OF SUBSEQUENT REQUEST PROBLEM IN PROBE BASED ADMISSION CONTROL FOR MULTICAST

MITIGATION OF SUBSEQUENT REQUEST PROBLEM IN PROBE BASED ADMISSION CONTROL FOR MULTICAST MITIGATION OF SUBSEQUENT REQUEST PROBLEM IN PROBE BASED ADMISSION CONTROL FOR MULTICAST 1 I. SATHIK ALI, 2 P. SHEIK ABDUL KHADER 1 Assoc. Prof., Dept. of Computer Applications, BSA university, Vandalur,

More information

DiffServ Architecture: Impact of scheduling on QoS

DiffServ Architecture: Impact of scheduling on QoS DiffServ Architecture: Impact of scheduling on QoS Abstract: Scheduling is one of the most important components in providing a differentiated service at the routers. Due to the varying traffic characteristics

More information

Re-usable service components based on the Parlay API and TINA for the Next Generation Network

Re-usable service components based on the Parlay API and TINA for the Next Generation Network Re-usable service components based on the Parlay API and TINA for the Next Generation Network Paresh Nana, Setumo Mohapi and Hu Hanrahan Centre for Telecommunications Access and Services (CeTAS) School

More information

PROXIMITY AWARE LOAD BALANCING FOR HETEROGENEOUS NODES Mrs. Yogita A. Dalvi Dr. R. Shankar Mr. Atesh Kumar

PROXIMITY AWARE LOAD BALANCING FOR HETEROGENEOUS NODES Mrs. Yogita A. Dalvi Dr. R. Shankar Mr. Atesh Kumar ISSN 2320-9194 1 International Journal of Advance Research, IJOAR.org Volume 1, Issue 9, September 2013, Online: ISSN 2320-9194 PROXIMITY AWARE LOAD BALANCING FOR HETEROGENEOUS NODES Mrs. Yogita A. Dalvi

More information

Boundary control : Access Controls: An access control mechanism processes users request for resources in three steps: Identification:

Boundary control : Access Controls: An access control mechanism processes users request for resources in three steps: Identification: Application control : Boundary control : Access Controls: These controls restrict use of computer system resources to authorized users, limit the actions authorized users can taker with these resources,

More information

A Heuristic Algorithm for Designing Logical Topologies in Packet Networks with Wavelength Routing

A Heuristic Algorithm for Designing Logical Topologies in Packet Networks with Wavelength Routing A Heuristic Algorithm for Designing Logical Topologies in Packet Networks with Wavelength Routing Mare Lole and Branko Mikac Department of Telecommunications Faculty of Electrical Engineering and Computing,

More information

DESIGN AND ANALYSIS OF ALGORITHMS. Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES

DESIGN AND ANALYSIS OF ALGORITHMS. Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES DESIGN AND ANALYSIS OF ALGORITHMS Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES http://milanvachhani.blogspot.in USE OF LOOPS As we break down algorithm into sub-algorithms, sooner or later we shall

More information

Performance of Multicast Traffic Coordinator Framework for Bandwidth Management of Real-Time Multimedia over Intranets

Performance of Multicast Traffic Coordinator Framework for Bandwidth Management of Real-Time Multimedia over Intranets Performance of Coordinator Framework for Bandwidth Management of Real-Time Multimedia over Intranets Chin Hooi Tang, and Tat Chee Wan, Member, IEEE ComSoc. Abstract Quality of Service (QoS) schemes such

More information

Performance Impact of I/O on Sender-Initiated and Receiver-Initiated Load Sharing Policies in Distributed Systems

Performance Impact of I/O on Sender-Initiated and Receiver-Initiated Load Sharing Policies in Distributed Systems Appears in Proc. Conf. Parallel and Distributed Computing Systems, Dijon, France, 199. Performance Impact of I/O on Sender-Initiated and Receiver-Initiated Load Sharing Policies in Distributed Systems

More information

QoS-aware resource allocation and load-balancing in enterprise Grids using online simulation

QoS-aware resource allocation and load-balancing in enterprise Grids using online simulation QoS-aware resource allocation and load-balancing in enterprise Grids using online simulation * Universität Karlsruhe (TH) Technical University of Catalonia (UPC) Barcelona Supercomputing Center (BSC) Samuel

More information

The effect of Mobile IP handoffs on the performance of TCP

The effect of Mobile IP handoffs on the performance of TCP Mobile Networks and Applications 4 (1999) 131 135 131 The effect of Mobile IP handoffs on the performance of TCP Anne Fladenmuller a and Ranil De Silva b a Alcatel CIT, Software Department, Route de Nozay,

More information

Prioritization scheme for QoS in IEEE e WLAN

Prioritization scheme for QoS in IEEE e WLAN Prioritization scheme for QoS in IEEE 802.11e WLAN Yakubu Suleiman Baguda a, Norsheila Fisal b a,b Department of Telematics & Communication Engineering, Faculty of Electrical Engineering Universiti Teknologi

More information

TSIN01 Information Networks Lecture 3

TSIN01 Information Networks Lecture 3 TSIN01 Information Networks Lecture 3 Danyo Danev Division of Communication Systems Department of Electrical Engineering Linköping University, Sweden September 10 th, 2018 Danyo Danev TSIN01 Information

More information

Mean Value Analysis and Related Techniques

Mean Value Analysis and Related Techniques Mean Value Analysis and Related Techniques 34-1 Overview 1. Analysis of Open Queueing Networks 2. Mean-Value Analysis 3. Approximate MVA 4. Balanced Job Bounds 34-2 Analysis of Open Queueing Networks Used

More information

Energy-Aware Routing in Wireless Ad-hoc Networks

Energy-Aware Routing in Wireless Ad-hoc Networks Energy-Aware Routing in Wireless Ad-hoc Networks Panagiotis C. Kokkinos Christos A. Papageorgiou Emmanouel A. Varvarigos Abstract In this work we study energy efficient routing strategies for wireless

More information

The Impact of the coming Standard IEC61850 on the Life-cycle of Open Communication Systems in Substations

The Impact of the coming Standard IEC61850 on the Life-cycle of Open Communication Systems in Substations The Impact of the coming Standard IEC61850 on the Life-cycle of Open Communication Systems in Substations Lars Andersson, Klaus-Peter Brand, Wolfgang Wimmer ABB Power Automation Ltd, Switzerland Abstract

More information

Distributed Scheduling. Distributed Scheduling

Distributed Scheduling. Distributed Scheduling CMSC 621, Advanced Operating Systems. Fall 2003 Distributed Scheduling Dr. Kalpakis Distributed Scheduling System performance can be improved by distributed load among heavy and light loaded nodes of the

More information

LOAD BALANCING USING THRESHOLD AND ANT COLONY OPTIMIZATION IN CLOUD COMPUTING

LOAD BALANCING USING THRESHOLD AND ANT COLONY OPTIMIZATION IN CLOUD COMPUTING LOAD BALANCING USING THRESHOLD AND ANT COLONY OPTIMIZATION IN CLOUD COMPUTING 1 Suhasini S, 2 Yashaswini S 1 Information Science & engineering, GSSSIETW, Mysore, India 2 Assistant Professor, Information

More information

CHAPTER 7 CONCLUSION AND FUTURE SCOPE

CHAPTER 7 CONCLUSION AND FUTURE SCOPE 121 CHAPTER 7 CONCLUSION AND FUTURE SCOPE This research has addressed the issues of grid scheduling, load balancing and fault tolerance for large scale computational grids. To investigate the solution

More information

Configuring QoS CHAPTER

Configuring QoS CHAPTER CHAPTER 34 This chapter describes how to use different methods to configure quality of service (QoS) on the Catalyst 3750 Metro switch. With QoS, you can provide preferential treatment to certain types

More information

Quality of Service in Telecommunication Networks

Quality of Service in Telecommunication Networks Quality of Service in Telecommunication Networks Åke Arvidsson, Ph.D. Ericsson Core Network Development, Sweden Main Message Traffic theory: QoS is (partly) about congestion. Congestion is partly caused

More information

User Based Call Admission Control Policies for Cellular Mobile Systems: A Survey

User Based Call Admission Control Policies for Cellular Mobile Systems: A Survey User Based Call Admission Control Policies for Cellular Mobile Systems: A Survey Hamid Beigy and M. R. Meybodi Computer Engineering Department Amirkabir University of Technology Tehran, Iran {beigy, meybodi}@ce.aut.ac.ir

More information

HARNESSING CERTAINTY TO SPEED TASK-ALLOCATION ALGORITHMS FOR MULTI-ROBOT SYSTEMS

HARNESSING CERTAINTY TO SPEED TASK-ALLOCATION ALGORITHMS FOR MULTI-ROBOT SYSTEMS HARNESSING CERTAINTY TO SPEED TASK-ALLOCATION ALGORITHMS FOR MULTI-ROBOT SYSTEMS An Undergraduate Research Scholars Thesis by DENISE IRVIN Submitted to the Undergraduate Research Scholars program at Texas

More information

Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS

Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS Chapter -5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS Chapter 5 QUALITY OF SERVICE (QOS) PLATFORM DESIGN FOR REAL TIME MULTIMEDIA APPLICATIONS 5.1 Introduction For successful

More information

Performance Modelling Lecture 12: PEPA Case Study: Rap Genius on Heroku

Performance Modelling Lecture 12: PEPA Case Study: Rap Genius on Heroku Performance Modelling Lecture 12: PEPA Case Study: Rap Genius on Heroku Jane Hillston & Dimitrios Milios School of Informatics The University of Edinburgh Scotland 2nd March 2017 Introduction As an example

More information

TINA-COMPLIANT SERVICE PROVISION AND NUMBERING IN UMTS

TINA-COMPLIANT SERVICE PROVISION AND NUMBERING IN UMTS Proceedings of 6th IEE Conference on Telecommunications, Conference Publication No. 451 Edinburgh, UK, 29 March - 1 April 1998 TINA-COMPLIANT SERVICE PROVISION AND NUMBERING IN UMTS Axel Küpper and Frank

More information

Requirements for TINA Platform towards Information Sharing Business. Long-term Trend of Telephone Business

Requirements for TINA Platform towards Information Sharing Business. Long-term Trend of Telephone Business TINA 99 Hawaii, USA: DPE Workshop 1 Requirements for TINA Platform towards Information Sharing Business April 12 1999 KITAMI, Kenichi NTT Information Sharing Laboratory Group Long-term Trend of Telephone

More information

A Semi-Distributed Load Balancing Algorithm Using Clustered Approach

A Semi-Distributed Load Balancing Algorithm Using Clustered Approach Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 6, June 2014, pg.843

More information

The application of TINA in multimedia services for the electronic super highway

The application of TINA in multimedia services for the electronic super highway The application of TINA in multimedia services for the electronic super highway Marten van Sinderen Luís Ferreira Pires Centre for Telematics and Information Technology University of Twente Enschede, the

More information

Comparison of the Quality of Service (QoS) on the IEEE e and the g Wireless LANs

Comparison of the Quality of Service (QoS) on the IEEE e and the g Wireless LANs ENSC 427: COMMUNICATION NETWORKS Comparison of the Quality of Service (QoS) on the IEEE 802.11e and the 802.11g Wireless LANs Spring 2010 Final Report Group 5 Yalda Hakki (yha17@sfu.ca) Rosy Johal (rja2@sfu.ca)

More information

SIMPLE MODEL FOR TRANSMISSION CONTROL PROTOCOL (TCP) Irma Aslanishvili, Tariel Khvedelidze

SIMPLE MODEL FOR TRANSMISSION CONTROL PROTOCOL (TCP) Irma Aslanishvili, Tariel Khvedelidze 80 SIMPLE MODEL FOR TRANSMISSION CONTROL PROTOCOL (TCP) Irma Aslanishvili, Tariel Khvedelidze Abstract: Ad hoc Networks are complex distributed systems that consist of wireless mobile or static nodes that

More information

Analysis of BE and rtps QoS in WiFi Network

Analysis of BE and rtps QoS in WiFi Network Armenian Journal of Physics, 2018, vol. 11, issue 4, pp.309-321 Analysis of BE and rtps QoS in WiFi Network (Proceedings of the Int. Conference on Microwave and THz Technologies and Wireless comm. ) Juwita

More information

ANALYSIS OF A DYNAMIC LOAD BALANCING IN MULTIPROCESSOR SYSTEM

ANALYSIS OF A DYNAMIC LOAD BALANCING IN MULTIPROCESSOR SYSTEM International Journal of Computer Science Engineering and Information Technology Research (IJCSEITR) ISSN 2249-6831 Vol. 3, Issue 1, Mar 2013, 143-148 TJPRC Pvt. Ltd. ANALYSIS OF A DYNAMIC LOAD BALANCING

More information

Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks

Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks X. Yuan, R. Melhem and R. Gupta Department of Computer Science University of Pittsburgh Pittsburgh, PA 156 fxyuan,

More information

OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI

OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI CMPE 655- MULTIPLE PROCESSOR SYSTEMS OVERHEADS ENHANCEMENT IN MUTIPLE PROCESSING SYSTEMS BY ANURAG REDDY GANKAT KARTHIK REDDY AKKATI What is MULTI PROCESSING?? Multiprocessing is the coordinated processing

More information

Mean Value Analysis and Related Techniques

Mean Value Analysis and Related Techniques Mean Value Analysis and Related Techniques Raj Jain Washington University in Saint Louis Saint Louis, MO 63130 Jain@cse.wustl.edu Audio/Video recordings of this lecture are available at: 34-1 Overview

More information

A Hybrid Load Balance Mechanism for Distributed Home Agents in Mobile IPv6

A Hybrid Load Balance Mechanism for Distributed Home Agents in Mobile IPv6 A Hybrid Load Balance Mechanism for Distributed Home Agents in Mobile IPv6 1 Hui Deng 2Xiaolong Huang 3Kai Zhang 3 Zhisheng Niu 1Masahiro Ojima 1R&D Center Hitachi (China) Ltd. Beijing 100004, China 2Dept.

More information

Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES

Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES DESIGN AND ANALYSIS OF ALGORITHMS Unit 1 Chapter 4 ITERATIVE ALGORITHM DESIGN ISSUES http://milanvachhani.blogspot.in USE OF LOOPS As we break down algorithm into sub-algorithms, sooner or later we shall

More information

Towards an Adaptive and Intelligent MPLS Network

Towards an Adaptive and Intelligent MPLS Network Towards an Adaptive and Intelligent MPLS Network Rana Rahim-Amoud, Leila Merghem-Boulahia, and Dominique Gaiti ISTIT, University of Technology of Troyes 12, rue Marie Curie, BP 2060, 10 010 TROYES CEDEX,

More information

Implementation of a leaky bucket module for simulations in NS-3

Implementation of a leaky bucket module for simulations in NS-3 Implementation of a leaky bucket module for simulations in NS-3 P. Baltzis 2, C. Bouras 1,2, K. Stamos 1,2,3, G. Zaoudis 1,2 1 Computer Technology Institute and Press Diophantus Patra, Greece 2 Computer

More information

A Mobile Agent-based Model for Service Management in Virtual Active Networks

A Mobile Agent-based Model for Service Management in Virtual Active Networks A Mobile Agent-based Model for Service Management in Virtual Active Networks Fábio Luciano Verdi and Edmundo R. M. Madeira Institute of Computing, University of Campinas (UNICAMP), Campinas-SP, Brazil

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

Title: Increasing the stability and robustness of simulation-based network assignment models for largescale

Title: Increasing the stability and robustness of simulation-based network assignment models for largescale Title: Increasing the stability and robustness of simulation-based network assignment models for largescale applications Author: Michael Mahut, INRO Consultants Inc. Larger-scale dynamic network models

More information

WIRELESS/MOBILE networking is one of the strongest

WIRELESS/MOBILE networking is one of the strongest IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, VOL. 53, NO. 3, MAY 2004 835 An Integrated Adaptive Bandwidth-Management Framework for QoS-Sensitive Multimedia Cellular Networks Sungwook Kim and Pramod K. Varshney,

More information

Towards a Hybrid Load Balancing Policy in Grid Computing System

Towards a Hybrid Load Balancing Policy in Grid Computing System Towards a Hybrid Load Balancing Policy in Grid Computing System Kuo Qin Yan, Shun Sheng Wang, Shu Ching Wang*, Chiu Ping Chang Chaoyang University of Technology 168, Jifong E. Rd., Wufong Township, Taichung

More information

Quality of Service II

Quality of Service II Quality of Service II Patrick J. Stockreisser p.j.stockreisser@cs.cardiff.ac.uk Lecture Outline Common QoS Approaches Best Effort Integrated Services Differentiated Services Integrated Services Integrated

More information

Final Exam for ECE374 05/03/12 Solution!!

Final Exam for ECE374 05/03/12 Solution!! ECE374: Second Midterm 1 Final Exam for ECE374 05/03/12 Solution!! Instructions: Put your name and student number on each sheet of paper! The exam is closed book. You have 90 minutes to complete the exam.

More information

Performance modeling of an Apache web server with bursty arrival traffic

Performance modeling of an Apache web server with bursty arrival traffic Performance modeling of an Apache web server with bursty arrival traffic Andersson, Mikael; Cao, Jianhua; Kihl, Maria; Nyberg, Christian Published in: IC'3 : proceedings of the international conference

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

12 PEPA Case Study: Rap Genius on Heroku

12 PEPA Case Study: Rap Genius on Heroku 1 PEPA Case Study: Rap Genius on Heroku As an example of a realistic case study, we consider a Platform as a service (PaaS) system, Heroku, and study its behaviour under different policies for assigning

More information

Delay-minimal Transmission for Energy Constrained Wireless Communications

Delay-minimal Transmission for Energy Constrained Wireless Communications Delay-minimal Transmission for Energy Constrained Wireless Communications Jing Yang Sennur Ulukus Department of Electrical and Computer Engineering University of Maryland, College Park, M0742 yangjing@umd.edu

More information

Abstract. Introduction and Motivations. Automatic Switched Optical Networks

Abstract. Introduction and Motivations. Automatic Switched Optical Networks Abstract Protection and restoration based resilience in Automatic Switched Optical Networks T. Jakab 1, Zs. Lakatos 2 Budapest University of Technology and Economics, Dept. of Telecommunications 1: Research

More information

23 An Overview of the Telecommunications Information Networking Architecture

23 An Overview of the Telecommunications Information Networking Architecture 23 An Overview of the Telecommunications Information Networking Architecture TINA Consortium c/o Bellcore 331 Newman Springs Rd. Red Bank, NJ 07701 USA Tel: + 1 908 758 2467 Fax: + 1 908 758 2865 1. INTRODUCTION

More information

Performance of UMTS Radio Link Control

Performance of UMTS Radio Link Control Performance of UMTS Radio Link Control Qinqing Zhang, Hsuan-Jung Su Bell Laboratories, Lucent Technologies Holmdel, NJ 77 Abstract- The Radio Link Control (RLC) protocol in Universal Mobile Telecommunication

More information

IMPROVING THE DATA COLLECTION RATE IN WIRELESS SENSOR NETWORKS BY USING THE MOBILE RELAYS

IMPROVING THE DATA COLLECTION RATE IN WIRELESS SENSOR NETWORKS BY USING THE MOBILE RELAYS IMPROVING THE DATA COLLECTION RATE IN WIRELESS SENSOR NETWORKS BY USING THE MOBILE RELAYS 1 K MADHURI, 2 J.KRISHNA, 3 C.SIVABALAJI II M.Tech CSE, AITS, Asst Professor CSE, AITS, Asst Professor CSE, NIST

More information

A Scalable Framework for Content Replication in Multicast-Based Content Distribution Networks

A Scalable Framework for Content Replication in Multicast-Based Content Distribution Networks A Scalable Framework for Content Replication in Multicast-Based Content Distribution Networks Yannis Matalas 1, Nikolaos D. Dragios 2, and George T. Karetsos 2 1 Digital Media & Internet Technologies Department,

More information

Load Balancing. Minsoo Ryu. Department of Computer Science and Engineering. Hanyang University. Real-Time Computing and Communications Lab.

Load Balancing. Minsoo Ryu. Department of Computer Science and Engineering. Hanyang University. Real-Time Computing and Communications Lab. Load Balancing Minsoo Ryu Department of Computer Science and Engineering 2 1 Concepts of Load Balancing Page X 2 Load Balancing Algorithms Page X 3 Overhead of Load Balancing Page X 4 Load Balancing in

More information

Performing MapReduce on Data Centers with Hierarchical Structures

Performing MapReduce on Data Centers with Hierarchical Structures INT J COMPUT COMMUN, ISSN 1841-9836 Vol.7 (212), No. 3 (September), pp. 432-449 Performing MapReduce on Data Centers with Hierarchical Structures Z. Ding, D. Guo, X. Chen, X. Luo Zeliu Ding, Deke Guo,

More information

Cover sheet for Assignment 3

Cover sheet for Assignment 3 Faculty of Arts and Science University of Toronto CSC 358 - Introduction to Computer Networks, Winter 2018, LEC0101 Cover sheet for Assignment 3 Due Monday March 5, 10:00am. Complete this page and attach

More information

Ch 4 : CPU scheduling

Ch 4 : CPU scheduling Ch 4 : CPU scheduling It's the basis of multiprogramming operating systems. By switching the CPU among processes, the operating system can make the computer more productive In a single-processor system,

More information

Last Class: Processes

Last Class: Processes Last Class: Processes A process is the unit of execution. Processes are represented as Process Control Blocks in the OS PCBs contain process state, scheduling and memory management information, etc A process

More information

Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION

Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION Chapter -6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION Chapter 6 IMPROVED CONGESTION CONTROL MECHANISM FOR REAL TIME DATA TRANSMISSION 6.1 Introduction Supporting Quality of Service

More information

02 - Distributed Systems

02 - Distributed Systems 02 - Distributed Systems Definition Coulouris 1 (Dis)advantages Coulouris 2 Challenges Saltzer_84.pdf Models Physical Architectural Fundamental 2/58 Definition Distributed Systems Distributed System is

More information

UBR Congestion controlled Video Transmission over ATM Eltayeb Omer Eltayeb, Saudi Telecom Company

UBR Congestion controlled Video Transmission over ATM Eltayeb Omer Eltayeb, Saudi Telecom Company UBR Congestion controlled Video Transmission over ATM Eltayeb Omer Eltayeb, Saudi Telecom Company ABSTRACT The ATM unspecified bit rate (UBR) class of service some times referred to as best effort service-

More information

Performance Analysis of Cell Switching Management Scheme in Wireless Packet Communications

Performance Analysis of Cell Switching Management Scheme in Wireless Packet Communications Performance Analysis of Cell Switching Management Scheme in Wireless Packet Communications Jongho Bang Sirin Tekinay Nirwan Ansari New Jersey Center for Wireless Telecommunications Department of Electrical

More information

02 - Distributed Systems

02 - Distributed Systems 02 - Distributed Systems Definition Coulouris 1 (Dis)advantages Coulouris 2 Challenges Saltzer_84.pdf Models Physical Architectural Fundamental 2/60 Definition Distributed Systems Distributed System is

More information

Fair Time Sharing Protocol: a Solution for IEEE b Hot Spots

Fair Time Sharing Protocol: a Solution for IEEE b Hot Spots Fair Time Sharing Protocol: a Solution for IEEE 802.11b Hot Spots Anelise Munaretto 1,2, Mauro Fonseca 1,4, Khaldoun Al Agha 2,3, and Guy Pujolle 1 1 LIP6 Laboratory, University of Paris VI, 75015 Paris,

More information

Archna Rani [1], Dr. Manu Pratap Singh [2] Research Scholar [1], Dr. B.R. Ambedkar University, Agra [2] India

Archna Rani [1], Dr. Manu Pratap Singh [2] Research Scholar [1], Dr. B.R. Ambedkar University, Agra [2] India Volume 4, Issue 3, March 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Performance Evaluation

More information

McGill University - Faculty of Engineering Department of Electrical and Computer Engineering

McGill University - Faculty of Engineering Department of Electrical and Computer Engineering McGill University - Faculty of Engineering Department of Electrical and Computer Engineering ECSE 494 Telecommunication Networks Lab Prof. M. Coates Winter 2003 Experiment 5: LAN Operation, Multiple Access

More information

A Centralized Approaches for Location Management in Personal Communication Services Networks

A Centralized Approaches for Location Management in Personal Communication Services Networks A Centralized Approaches for Location Management in Personal Communication Services Networks Fahamida Firoze M. Tech. (CSE) Scholar, Deptt. Of CSE, Al Falah School of Engineering & Technology, Dhauj, Faridabad,

More information

Concurrent activities in daily life. Real world exposed programs. Scheduling of programs. Tasks in engine system. Engine system

Concurrent activities in daily life. Real world exposed programs. Scheduling of programs. Tasks in engine system. Engine system Real world exposed programs Programs written to interact with the real world, outside the computer Programs handle input and output of data in pace matching the real world processes Necessitates ability

More information

GRID SIMULATION FOR DYNAMIC LOAD BALANCING

GRID SIMULATION FOR DYNAMIC LOAD BALANCING GRID SIMULATION FOR DYNAMIC LOAD BALANCING Kapil B. Morey 1, Prof. A. S. Kapse 2, Prof. Y. B. Jadhao 3 1 Research Scholar, Computer Engineering Dept., Padm. Dr. V. B. Kolte College of Engineering, Malkapur,

More information

Scheduling Algorithms to Minimize Session Delays

Scheduling Algorithms to Minimize Session Delays Scheduling Algorithms to Minimize Session Delays Nandita Dukkipati and David Gutierrez A Motivation I INTRODUCTION TCP flows constitute the majority of the traffic volume in the Internet today Most of

More information

Internetworking Wireless Nodes to A Control Area Network

Internetworking Wireless Nodes to A Control Area Network Internetworking Wireless Nodes to A Control Area Network A. Kutlu, H. Ekiz, M.D. Baba, E.T. Powner School of Engineering University of Sussex Brighton U.K. ABSTRACT This paper discusses the design and

More information

Investigation of Algorithms for VoIP Signaling

Investigation of Algorithms for VoIP Signaling Journal of Electrical Engineering 4 (2016) 203-207 doi: 10.17265/2328-2223/2016.04.007 D DAVID PUBLISHING Todorka Georgieva 1, Ekaterina Dimitrova 2 and Slava Yordanova 3 1. Telecommunication Department,

More information

Supporting Service Differentiation for Real-Time and Best-Effort Traffic in Stateless Wireless Ad-Hoc Networks (SWAN)

Supporting Service Differentiation for Real-Time and Best-Effort Traffic in Stateless Wireless Ad-Hoc Networks (SWAN) Supporting Service Differentiation for Real-Time and Best-Effort Traffic in Stateless Wireless Ad-Hoc Networks (SWAN) G. S. Ahn, A. T. Campbell, A. Veres, and L. H. Sun IEEE Trans. On Mobile Computing

More information

Achieving Distributed Buffering in Multi-path Routing using Fair Allocation

Achieving Distributed Buffering in Multi-path Routing using Fair Allocation Achieving Distributed Buffering in Multi-path Routing using Fair Allocation Ali Al-Dhaher, Tricha Anjali Department of Electrical and Computer Engineering Illinois Institute of Technology Chicago, Illinois

More information