Cellular Network Traffic Scheduling using Deep Reinforcement Learning
|
|
- Aubrie Sharp
- 5 years ago
- Views:
Transcription
1 Cellular Network Traffic Scheduling using Deep Reinforcement Learning Sandeep Chinchali, et. al. Marco Pavone, Sachin Katti Stanford University AAAI 2018
2 Can we learn to optimally manage cellular networks? Delay Tolerant (DT) Traffic Pre-fetched content IoT: Map/SW updates Internet Real-time Mobile Traffic Delay Sensitive 2
3 Why is IoT/DT traffic scheduling hard? Utilization Acceptable Limit IoT Contending goals Max IoT/DT data IoT Loss to mobile traffic Network limits Optimal Control 3
4 Why is IoT/DT traffic scheduling hard? Melbourne Central Business District, Rolling Average = 1 min Shopping center O ce building Southern cross station Melbourne central station Diverse city-wide cell patterns Congestion C :00 11:00 13:00 15:00 17:00 19:00 21:00 Local time csandeep@stanford.edu 4
5 Our contributions 1. Identify inefficiencies in real cellular networks 4 weeks, 10 diverse cells in Downtown Melbourne, Australia 2. Data Driven, Deep Learning Network Model Our live network experiments match MDP dynamics 3. Adaptive RL scheduler Flexibly responds to operator reward functions Network State IoT Scheduler IoT rate csandeep@stanford.edu 5
6 Why Deep Learning? Congestion C Melbourne Central Business District, Rolling Average = 1 min Shopping center O ce building Southern cross station Melbourne central station 1. Learn time-variant network dynamics 2. Adapt to high-level network operation goals 3. Generalize to diverse cells 0 4. Abundance of network data 09:00 11:00 13:00 15:00 17:00 19:00 21:00 Local time csandeep@stanford.edu 6
7 Related Work 1. Dynamic Resource Allocation Electricity grid (Reddy 2011), call admission (Marbach 1998), traffic control (Chu 2016) 2. Data-driven Optimal Control + Forecasting Deep RL (Mnih 2013, Silver 2014, Lillicrap 2015) LSTM networks (Hochreiter 1997, Laptev 2017, Shi 2015) 3. Machine Learning for Computer Networks Cluster Resource Management (Mao 2016) Mobile Video Streaming (Mao 2017, Yin 2015) csandeep@stanford.edu 7
8 Data-driven problem formulation 1. Network State Space 2. IoT Scheduler Actions 3. Time-variant dynamics 4. Network operator policies Congestion IoT Scheduler Cell efficiency IoT rate Num Users Network state + forecasts 8
9 Primer on Cell Networks (Link Quality) Goal: Max safe IoT traffic V t over day csandeep@stanford.edu 9
10 RL setup (1): State Space Reward Current Network State Agent Action Environment Full State with Temporal Features Network state Stochastic Forecast (LSTM) Horizon: Day of T mins csandeep@stanford.edu 10
11 RL setup (2): Action Space Reward IoT Traffic Rate: Agent Action Environment IoT Volume per minute: Network state Utilization gain: 11
12 RL setup (3): Transition Dynamics 1.6 Controlled tra c Reward 1.5 Agent Action Environment Congestion C Background dynamics Network state :10 20:15 20:20 Local time csandeep@stanford.edu 12
13 RL setup (4): Operator Rewards Reward Overall weighted reward Agent Action Environment 1. IoT traffic volume What-if model Network state 2. Loss to regular users Goal: Find Optimal Operator Policy 3. Traffic below network limit 13
14 Evaluation 14
15 Evaluation Criteria 1. Robust performance on diverse cell-day pairs 2. Ability to exploit better forecasts 3. Interpretability Congestion IoT Scheduler Cell efficiency IoT rate Num Users Network state + forecasts 15
16 1. RL generalizes to several cell-day pairs 100 Respond to operator priorities α 1 8tilization gain V IoT /V 0 (%) Significant gains: FCC Spectrum Auction (Reardon 2016): $4.5B for 10 MHz of spectrum 14.7% median gain for α = 2 Significant cost savings [simulated] 0 TUain Test csandeep@stanford.edu 16
17 2. RL effectively leverages forecasts RL Benchmark Richer LSTM forecasts 17
18 3a. RL exploits transient dips in utilization Controlled Congestion Utilization gain Congestion C Original Heuristic control DDPG control Transient Dip 0 9:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 Local time Utilization gain VIoT /V0 (%) Heuristic control DDPG control 0 9:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 Local time 18
19 3b. RL smooths network throughput Controlled Congestion Resulting Throughput Congestion C Original Heuristic control DDPG control 0 9:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 Local time Throughput B (MBps) Original Heuristic control DDPG control Throughput limit 0.0 9:00 10:00 11:00 12:00 13:00 14:00 15:00 16:00 Local time csandeep@stanford.edu 19
20 Conclusion Modern networks are evolving Delay tolerant traffic (IoT updates, pre-fetched content) Data-driven optimal control LSTM forecasts + RL controller 14.7% simulated gain -> significant savings Future work: Operational network tests Decouple prediction and control Questions: csandeep@stanford.edu csandeep@stanford.edu
21 Extra slides 21
22 2. RL effectively leverages forecasts Better forecasts enhance performance Discretized MDP for offline optimal Reward R Ā =5 Ā =20 Ā =40 Ā = S Richer LSTM forecasts Approach Cts MDP csandeep@stanford.edu 22
Cellular Network Traffic Scheduling with Deep Reinforcement Learning
Cellular Network Traffic Scheduling with Deep Reinforcement Learning Sandeep Chinchali 1, Pan Hu 2, Tianshu Chu 3, Manu Sharma 3, Manu Bansal 3, Rakesh Misra 3 Marco Pavone 4 and Sachin Katti 1,2 1 Department
More informationData Driven Networks. Sachin Katti
Data Driven Networks Sachin Katti Is it possible for to Learn the control planes of networks and applications? Operators specify what they want, and the system learns how to deliver CAN WE LEARN THE CONTROL
More informationData Driven Networks
Data Driven Networks Is it possible for to Learn the control planes of networks and applications? Operators specify what they want, and the system learns how to deliver CAN WE LEARN THE CONTROL PLANE OF
More informationSlides credited from Dr. David Silver & Hung-Yi Lee
Slides credited from Dr. David Silver & Hung-Yi Lee Review Reinforcement Learning 2 Reinforcement Learning RL is a general purpose framework for decision making RL is for an agent with the capacity to
More informationDeep Reinforcement Learning
Deep Reinforcement Learning 1 Outline 1. Overview of Reinforcement Learning 2. Policy Search 3. Policy Gradient and Gradient Estimators 4. Q-prop: Sample Efficient Policy Gradient and an Off-policy Critic
More informationUsing Reinforcement Learning to Optimize Storage Decisions Ravi Khadiwala Cleversafe
Using Reinforcement Learning to Optimize Storage Decisions Ravi Khadiwala Cleversafe Topics What is Reinforcement Learning? Exploration vs. Exploitation The Multi-armed Bandit Optimizing read locations
More informationMIND: Machine Learning based Network Dynamics. Dr. Yanhui Geng Huawei Noah s Ark Lab, Hong Kong
MIND: Machine Learning based Network Dynamics Dr. Yanhui Geng Huawei Noah s Ark Lab, Hong Kong Outline Challenges with traditional SDN MIND architecture Experiment results Conclusion Challenges with Traditional
More informationLecture 18: Video Streaming
MIT 6.829: Computer Networks Fall 2017 Lecture 18: Video Streaming Scribe: Zhihong Luo, Francesco Tonolini 1 Overview This lecture is on a specific networking application: video streaming. In particular,
More informationSelf Programming Networks
Self Programming Networks Is it possible for to Learn the control planes of networks and applications? Operators specify what they want, and the system learns how to deliver CAN WE LEARN THE CONTROL PLANE
More informationIntroduction to Reinforcement Learning. J. Zico Kolter Carnegie Mellon University
Introduction to Reinforcement Learning J. Zico Kolter Carnegie Mellon University 1 Agent interaction with environment Agent State s Reward r Action a Environment 2 Of course, an oversimplification 3 Review:
More informationA Brief Introduction to Reinforcement Learning
A Brief Introduction to Reinforcement Learning Minlie Huang ( ) Dept. of Computer Science, Tsinghua University aihuang@tsinghua.edu.cn 1 http://coai.cs.tsinghua.edu.cn/hml Reinforcement Learning Agent
More information10703 Deep Reinforcement Learning and Control
10703 Deep Reinforcement Learning and Control Russ Salakhutdinov Machine Learning Department rsalakhu@cs.cmu.edu Policy Gradient I Used Materials Disclaimer: Much of the material and slides for this lecture
More informationNC-CELL: Network Coding-based Content Distribution in Cellular Networks for Cloud Applications
-CELL: Network Coding-based Content Distribution Introduction Results Mobile cloud applications is one of the fastest growing markets: Mobile data traffic will rise up to 15 EB per month by 218 By 217
More informationPartially Observable Markov Decision Processes. Mausam (slides by Dieter Fox)
Partially Observable Markov Decision Processes Mausam (slides by Dieter Fox) Stochastic Planning: MDPs Static Environment Fully Observable Perfect What action next? Stochastic Instantaneous Percepts Actions
More informationFour Steps to Help LTE Operators Prepare for 5G
ovum.informa.com Ovum TMT intelligence Four Steps to Help LTE Operators Prepare for 5G Julian Bright Senior Analyst CONNECTED CAR CONSUMER SERVICES: DATA MONETIZATION 3 2 FOUR STEPS TO HELP LTE OPERATORS
More informationPlanning and Control: Markov Decision Processes
CSE-571 AI-based Mobile Robotics Planning and Control: Markov Decision Processes Planning Static vs. Dynamic Predictable vs. Unpredictable Fully vs. Partially Observable Perfect vs. Noisy Environment What
More informationFemto-Matching: Efficient Traffic Offloading in Heterogeneous Cellular Networks
Femto-Matching: Efficient Traffic Offloading in Heterogeneous Cellular Networks Wei Wang, Xiaobing Wu, Lei Xie and Sanglu Lu Nanjing University April 28, 2015 1/1 Heterogeneous Cellular Networks femto-cell
More information5G and Licensed/Unlicensed Convergence
5G and Licensed/Unlicensed Convergence WBA Conference November 2016 Dave Wolter Wireless Trends Continued rapid growth of data demand IoT will drive growth in connected devices Wireless Everything Everywhere
More informationTopics in AI (CPSC 532L): Multimodal Learning with Vision, Language and Sound. Lecture 12: Deep Reinforcement Learning
Topics in AI (CPSC 532L): Multimodal Learning with Vision, Language and Sound Lecture 12: Deep Reinforcement Learning Types of Learning Supervised training Learning from the teacher Training data includes
More informationREINFORCEMENT LEARNING: MDP APPLIED TO AUTONOMOUS NAVIGATION
REINFORCEMENT LEARNING: MDP APPLIED TO AUTONOMOUS NAVIGATION ABSTRACT Mark A. Mueller Georgia Institute of Technology, Computer Science, Atlanta, GA USA The problem of autonomous vehicle navigation between
More informationBridging Link Power Asymmetry in Mobile Whitespace Networks Sanjib Sur and Xinyu Zhang
Bridging Link Power Asymmetry in Mobile Whitespace Networks Sanjib Sur and Xinyu Zhang University of Wisconsin - Madison 1 Wireless Access in Vehicles Wireless network in public vehicles use existing infrastructure
More informationChallenges in Ubiquitous Data Mining
LIAAD-INESC Porto, University of Porto, Portugal jgama@fep.up.pt 1 2 Very-short-term Forecasting in Photovoltaic Systems 3 4 Problem Formulation: Network Data Model Querying Model Query = Q( n i=0 S i)
More informationLecture 4 Wide Area Networks - Congestion in Data Networks
DATA AND COMPUTER COMMUNICATIONS Lecture 4 Wide Area Networks - Congestion in Data Networks Mei Yang Based on Lecture slides by William Stallings 1 WHAT IS CONGESTION? congestion occurs when the number
More informationReinforcement learning algorithms for non-stationary environments. Devika Subramanian Rice University
Reinforcement learning algorithms for non-stationary environments Devika Subramanian Rice University Joint work with Peter Druschel and Johnny Chen of Rice University. Supported by a grant from Southwestern
More informationAlternate PHYs
A whitepaper by Ayman Mukaddam 2018, LLC Page 1 of 12 Contents Modern 802.11 Amendments... 3 Traditional PHYs Review (2.4 GHz and 5 GHz PHYs)... 3 802.11ad Directional Multi-Gigabit - DMG PHY... 4 Frequency
More informationSwitch Packet Arbitration via Queue-Learning
Switch Packet Arbitration via QueueLearning Timothy X Brown Electrical and Computer Engineering University of Colorado Boulder, CO 803090530 timxb@coloradoedu Accepted in Advances in Neural Information
More informationMohammad 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 informationTopic 6: SDN in practice: Microsoft's SWAN. Student: Miladinovic Djordje Date:
Topic 6: SDN in practice: Microsoft's SWAN Student: Miladinovic Djordje Date: 17.04.2015 1 SWAN at a glance Goal: Boost the utilization of inter-dc networks Overcome the problems of current traffic engineering
More informationDealing with Limited Backhaul Capacity in Millimeter Wave Systems: A Deep Reinforcement Learning Approach
IEEE COMMUNICATIONS MAGAZINE, VOL.XXX, NO.XXX, MONTH YEAR 1 Dealing with Limited Backhaul Capacity in Millimeter Wave Systems: A Deep Reinforcement Learning Approach Mingjie Feng, Student Member, IEEE
More informationMarkov Decision Processes and Reinforcement Learning
Lecture 14 and Marco Chiarandini Department of Mathematics & Computer Science University of Southern Denmark Slides by Stuart Russell and Peter Norvig Course Overview Introduction Artificial Intelligence
More informationCall Admission Control for Multimedia Cellular Networks Using Neuro-dynamic Programming
Call Admission Control for Multimedia Cellular Networks Using Neuro-dynamic Programming Sidi-Mohammed Senouci, André-Luc Beylot 2, and Guy Pujolle Laboratoire LIP6 Université de Paris VI 8, rue du Capitaine
More informationDeriving Network Traffic Signatures via Large Graphs
Deriving Network Traffic Signatures via Large Graphs hume@vt.edu www.hume.vt.edu Ahmed Abdelhadi (PI) Research Assistant Professor Outline Pattern of Life and IoT A Tractable Framework for POL Modeling
More informationMarkov Decision Processes. (Slides from Mausam)
Markov Decision Processes (Slides from Mausam) Machine Learning Operations Research Graph Theory Control Theory Markov Decision Process Economics Robotics Artificial Intelligence Neuroscience /Psychology
More informationMCIT. GSMA Workshop Manila, Philippines,, 21 AUGUST 2017
GSMA Workshop Manila, Philippines,, 21 AUGUST 2017 MCIT Spectrum Planning for Fixed and Land Mobile Services Division DG of Postal and Iinformation Technology Resources and Equipment Ministry of Communication
More informationMobile Edge Computing for 5G: The Communication Perspective
Mobile Edge Computing for 5G: The Communication Perspective Kaibin Huang Dept. of Electrical & Electronic Engineering The University of Hong Kong Hong Kong Joint Work with Yuyi Mao (HKUST), Changsheng
More informationSWAN: Software-driven wide area network. Ratul Mahajan
SWAN: Software-driven wide area network Ratul Mahajan Partners in crime Vijay Gill Chi-Yao Hong Srikanth Kandula Ratul Mahajan Mohan Nanduri Ming Zhang Roger Wattenhofer Rohan Gandhi Xin Jin Harry Liu
More informationQueue. Processor. Processor. + L1 Cache. Prefetch
computing for Prefetching Introspective project for CS252, Spring 2000) (Class Andrew Y. Ng and Eric Xing fang,epxingg@cs.berkeley.edu Berkeley UC Introspective computing Secondary processor (may be DSP
More informationDr. Evaldas Stankevičius, Regulatory and Security Expert.
2018-08-23 Dr. Evaldas Stankevičius, Regulatory and Security Expert Email: evaldas.stankevicius@tele2.com 1G: purely analog system. 2G: voice and SMS. 3G: packet switching communication. 4G: enhanced mobile
More informationWireless Connectivity technologies evolution for Internet of Things and Machine to Machine communication
International Conference: Regulatory activity in electronic communications sector, 28-29 September 2015 Budva, Montenegro Wireless Connectivity technologies evolution for Internet of Things and Machine
More informationGPU-BASED A3C FOR DEEP REINFORCEMENT LEARNING
GPU-BASED A3C FOR DEEP REINFORCEMENT LEARNING M. Babaeizadeh,, I.Frosio, S.Tyree, J. Clemons, J.Kautz University of Illinois at Urbana-Champaign, USA NVIDIA, USA An ICLR 2017 paper A github project GPU-BASED
More informationImproving Cellular Capacity with White Space Offloading
Improving Cellular Capacity with White Space Offloading Suzan Bayhan*, Liang Zheng*, Jiasi Chen, Mario Di Francesco, Jussi Kangasharju, and Mung Chiang * equal contribution WiOPT, Paris, France, May 15-19,
More informationQuality of Service (QoS)
Quality of Service (QoS) A note on the use of these ppt slides: We re making these slides freely available to all (faculty, students, readers). They re in PowerPoint form so you can add, modify, and delete
More informationSpectrum Sharing Unleashed. Kalpak Gude President, Dynamic Spectrum Alliance
Spectrum Sharing Unleashed Kalpak Gude President, Dynamic Spectrum Alliance Current Members 2016 Dynamic Spectrum Alliance 2 The Jetsons Future and Beyond! In some ways, the Jetsons future is already here:
More informationReinforcement Learning: A brief introduction. Mihaela van der Schaar
Reinforcement Learning: A brief introduction Mihaela van der Schaar Outline Optimal Decisions & Optimal Forecasts Markov Decision Processes (MDPs) States, actions, rewards and value functions Dynamic Programming
More informationCutting the Cord: A Robust Wireless Facilities Network for Data Centers
Cutting the Cord: A Robust Wireless Facilities Network for Data Centers Yibo Zhu, Xia Zhou, Zengbin Zhang, Lin Zhou, Amin Vahdat, Ben Y. Zhao and Haitao Zheng U.C. Santa Barbara, Dartmouth College, U.C.
More informationDOCSIS FOR LTE SMALL CELL BACKHAUL ADDRESSING PERFORMANCE AND THROUGHPUT REQUIREMENTS FOR MOBILE BACKHAUL
DOCSIS FOR LTE SMALL CELL BACKHAUL ADDRESSING PERFORMANCE AND THROUGHPUT REQUIREMENTS FOR MOBILE BACKHAUL WHITE PAPER Small cells can be used to increase wireless network capacity, provide coverage in
More informationMobile AI: Challenges and Opportunities
Mobile AI: Challenges and Opportunities Mérouane Debbah Mathematical and Algorithmic Sciences Lab, Huawei Geneva, January 29th, 2018 1 Networks are becoming very complex 4G MBB Voice Data HD Video B2C
More informationTraining Intelligent Stoplights
Training Intelligent Stoplights Thomas Davids, Michael Celentano, and Luke Knepper December 14, 2012 1 Introduction Traffic is a huge problem for the American economy. In 2010, the average American commuter
More informationCutting the Cord: A Robust Wireless Facilities Network for Data Centers
Cutting the Cord: A Robust Wireless Facilities Network for Data Centers Yibo Zhu, Xia Zhou, Zengbin Zhang, Lin Zhou, Amin Vahdat, Ben Y. Zhao and Haitao Zheng U.C. Santa Barbara, Dartmouth College, U.C.
More informationWhat Is Congestion? Computer Networks. Ideal Network Utilization. Interaction of Queues
168 430 Computer Networks Chapter 13 Congestion in Data Networks What Is Congestion? Congestion occurs when the number of packets being transmitted through the network approaches the packet handling capacity
More informationPhD Thesis Defense Performance Improvements in Software-defined and Virtualized Wireless Networks
PhD Thesis Defense Performance Improvements in Software-defined and Virtualized Wireless Networks Chengchao Liang Supervisor: Prof. F. Richard Yu Department of Systems and Computer Engineering Carleton
More informationBetter Security via Randomization: A Game Theoretic Approach and its Operationalization at the Los Angeles International Airport
Better Security via Randomization: A Game Theoretic Approach and its Operationalization at the Los Angeles International Airport Milind Tambe, Fernando Ordonez CREATE: Homeland Security Center University
More informationCigré Colloquium SC D2 / India 2013 Paper D SMART, UTILITY-GRADE WI-FI MESH FOR DISTRIBUTION GRIDS
P. Schwyter, Ph.Schneider - ABB Switzerland Ltd. Cigré Colloquium SC D2 / India 2013 Paper D2-01-04 SMART, UTILITY-GRADE WI-FI FOR DISTRIBUTION GRIDS October 21, 2013 Slide 1 D2-01_04 Authors & Topics
More informationSwitch Packet Arbitration via Queue-Learning
Switch Packet Arbitration via QueueLearning Timothy X Brown Electrical and Computer Engineering Interdisciplinary Telecommunications University of Colorado Boulder, CO 803090530 timxb@coloradoedu Abstract
More informationBROADBAND AND HIGH SPEED NETWORKS
BROADBAND AND HIGH SPEED NETWORKS SWITCHING A switch is a mechanism that allows us to interconnect links to form a larger network. A switch is a multi-input, multi-output device, which transfers packets
More informationWireless Challenges : Computer Networking. Overview. Routing to Mobile Nodes. Lecture 25: Wireless Networking
Wireless Challenges 15-441: Computer Networking Lecture 25: Wireless Networking Force us to rethink many assumptions Need to share airwaves rather than wire Don t know what hosts are involved Host may
More informationPrediction-Based Admission Control for IaaS Clouds with Multiple Service Classes
Prediction-Based Admission Control for IaaS Clouds with Multiple Service Classes Marcus Carvalho, Daniel Menascé, Francisco Brasileiro 2015 IEEE Intl. Conf. Cloud Computing Technology and Science Summarized
More informationReJOIN: A Prototype Query Optimizer using Deep Reinforcement Learning. Ryan Marcus*, Brandeis University Olga Papaemmanouil, Brandeis University
ReJOIN: A Prototype Query Optimizer using Deep Reinforcement Learning Ryan Marcus*, Brandeis University Olga Papaemmanouil, Brandeis University 10/3/2018 These slides: http://rm.cab/ibm18 Join Order Enumeration
More informationNetSpeed ORION: A New Approach to Design On-chip Interconnects. August 26 th, 2013
NetSpeed ORION: A New Approach to Design On-chip Interconnects August 26 th, 2013 INTERCONNECTS BECOMING INCREASINGLY IMPORTANT Growing number of IP cores Average SoCs today have 100+ IPs Mixing and matching
More informationOver-The-Top (OTT) Aggregation Solutions
Over-The-Top (OTT) Aggregation Solutions Omkar Dharmadhikari, Wireless Architect odharmadhikari@cablelabscom CableLabs February 12, 2019 Agenda Introduction Why aggregation is important? Traditional Aggregation
More information360 Degree Video Streaming
360 Degree Video Streaming Yao Wang Dept. of Electrical and Computer Engineering Tandon School of Engineering New York University http://vision.poly.edu 360 Video Streaming https://www.youtube.com/watch?v=wsmjbmxputc
More informationWhen Network Embedding meets Reinforcement Learning?
When Network Embedding meets Reinforcement Learning? ---Learning Combinatorial Optimization Problems over Graphs Changjun Fan 1 1. An Introduction to (Deep) Reinforcement Learning 2. How to combine NE
More informationReinforcement Learning and Optimal Control. ASU, CSE 691, Winter 2019
Reinforcement Learning and Optimal Control ASU, CSE 691, Winter 2019 Dimitri P. Bertsekas dimitrib@mit.edu Lecture 1 Bertsekas Reinforcement Learning 1 / 21 Outline 1 Introduction, History, General Concepts
More informationImproving the Expected Quality of Experience in Cloud-Enabled Wireless Access Networks
Improving the Expected Quality of Experience in Cloud-Enabled Wireless Access Networks Dr. Hang Liu & Kristofer Smith Department of Electrical Engineering and Computer Science The Catholic University of
More informationKnowledge-Defined Networking: Towards Self-Driving Networks
Knowledge-Defined Networking: Towards Self-Driving Networks Albert Cabellos (UPC/BarcelonaTech, Spain) albert.cabellos@gmail.com 2nd IFIP/IEEE International Workshop on Analytics for Network and Service
More informationCongestion in Data Networks. Congestion in Data Networks
Congestion in Data Networks CS420/520 Axel Krings 1 Congestion in Data Networks What is Congestion? Congestion occurs when the number of packets being transmitted through the network approaches the packet
More informationWhat Is Congestion? Effects of Congestion. Interaction of Queues. Chapter 12 Congestion in Data Networks. Effect of Congestion Control
Chapter 12 Congestion in Data Networks Effect of Congestion Control Ideal Performance Practical Performance Congestion Control Mechanisms Backpressure Choke Packet Implicit Congestion Signaling Explicit
More informationValue Iteration. Reinforcement Learning: Introduction to Machine Learning. Matt Gormley Lecture 23 Apr. 10, 2019
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Reinforcement Learning: Value Iteration Matt Gormley Lecture 23 Apr. 10, 2019 1
More informationWeek 7: Traffic Models and QoS
Week 7: Traffic Models and QoS Acknowledgement: Some slides are adapted from Computer Networking: A Top Down Approach Featuring the Internet, 2 nd edition, J.F Kurose and K.W. Ross All Rights Reserved,
More informationPerformance and Evaluation of Integrated Video Transmission and Quality of Service for internet and Satellite Communication Traffic of ATM Networks
Performance and Evaluation of Integrated Video Transmission and Quality of Service for internet and Satellite Communication Traffic of ATM Networks P. Rajan Dr. K.L.Shanmuganathan Research Scholar Prof.
More informationDesign and Evaluation of the Ultra- Reliable Low-Latency Wireless Protocol EchoRing
Design and Evaluation of the Ultra- Reliable Low-Latency Wireless Protocol EchoRing BWRC, September 22 nd 2017 joint work with C. Dombrowski, M. Serror, Y. Hu, S. Junges Machine-Type Communications: Origins
More informationQuality Optimal Policy for H.264 Scalable Video Scheduling in Broadband Multimedia Wireless Networks
Quality Optimal Policy for H.264 Scalable Video Scheduling in Broadband Multimedia Wireless Networks Vamseedhar R. Reddyvari Electrical Engineering Indian Institute of Technology Kanpur Email: vamsee@iitk.ac.in
More informationThroughput Maximization for Energy Efficient Multi-Node Communications using Actor-Critic Approach
Throughput Maximization for Energy Efficient Multi-Node Communications using Actor-Critic Approach Charles Pandana and K. J. Ray Liu Department of Electrical and Computer Engineering University of Maryland,
More informationAttend to details of the value iteration and policy iteration algorithms Reflect on Markov decision process behavior Reinforce C programming skills
CSC 261 Lab 11: Markov Decision Processes Fall 2015 Assigned: Tuesday 1 December Due: Friday 11 December, 5:00 pm Objectives: Attend to details of the value iteration and policy iteration algorithms Reflect
More informationITU Arab Forum on Future Networks: "Broadband Networks in the Era of App Economy", Tunis - Tunisia, Feb. 2017
On the ROAD to 5G Ines Jedidi Network Products, Ericsson Maghreb ITU Arab Forum on Future Networks: "Broadband Networks in the Era of App Economy", Tunis - Tunisia, 21-22 Feb. 2017 agenda Why 5G? What
More informationAbstract of the Book
Book Keywords IEEE 802.16, IEEE 802.16m, mobile WiMAX, 4G, IMT-Advanced, 3GPP LTE, 3GPP LTE-Advanced, Broadband Wireless, Wireless Communications, Cellular Systems, Network Architecture Abstract of the
More informationMachine Learning for Vehicular Networks
1 Machine Learning for Vehicular Networks Hao Ye, Le Liang, and Geoffrey Ye Li, Georgia Institute of Technology JoonBeom Kim, Lu Lu, and May Wu, Intel Corporation arxiv:1712.07143v1 [cs.it] 19 Dec 2017
More informationTHE O₂ SELF OPTIMISING NETWORK
THE O₂ SELF OPTIMISING NETWORK Our Network Story O2 THE O₂ STORY SO FAR.. We believe we are the most customer centric network. We listen to our customers & act accordingly. We are building a smart network
More informationOboe: Auto-tuning Video ABR Algorithms to Network Conditions
Oboe: Auto-tuning Video ABR Algorithms to Network Conditions Zahaib Akhtar, Yun Seong Nam, Ramesh Govindan, Sanjay Rao, Jessica Chen, Ethan Katz-Bassett, Bruno Ribeiro, Jibin Zhan, Hui Zhang : Co-primary
More informationDegrees of Freedom in Cached Interference Networks with Limited Backhaul
Degrees of Freedom in Cached Interference Networks with Limited Backhaul Vincent LAU, Department of ECE, Hong Kong University of Science and Technology (A) Motivation Interference Channels 3 No side information
More informationarxiv: v2 [cs.ni] 23 May 2016
Simulation Results of User Behavior-Aware Scheduling Based on Time-Frequency Resource Conversion Hangguan Shan, Yani Zhang, Weihua Zhuang 2, Aiping Huang, and Zhaoyang Zhang College of Information Science
More informationGUNREAL: GPU-accelerated UNsupervised REinforcement and Auxiliary Learning
GUNREAL: GPU-accelerated UNsupervised REinforcement and Auxiliary Learning Koichi Shirahata, Youri Coppens, Takuya Fukagai, Yasumoto Tomita, and Atsushi Ike FUJITSU LABORATORIES LTD. March 27, 2018 0 Deep
More informationMonte Carlo Tree Search PAH 2015
Monte Carlo Tree Search PAH 2015 MCTS animation and RAVE slides by Michèle Sebag and Romaric Gaudel Markov Decision Processes (MDPs) main formal model Π = S, A, D, T, R states finite set of states of the
More informationSurvey on Concurrent Multipath Scheduling for Real Time Video Streaming in Wireless Network
RESEARCH ARTICLE Survey on Concurrent Multipath Scheduling for Real Time Video Streaming in Wireless Network Rohit Salkute 1, Prof. D.G. Vyawahare 2 1(Computer Science and Engineering, SGBAU, Amravati
More informationRobust PCI Planning for Long Term Evolution Technology
From the SelectedWorks of Ekta Gujral Miss Winter 2013 Robust PCI Planning for Long Term Evolution Technology Ekta Gujral, Miss Available at: https://works.bepress.com/ekta_gujral/1/ Robust PCI Planning
More informationBII - Broadband for Industrial Internet
BII - Broadband for Industrial Internet Technology Overview BII (/Bee/, Broadband for Industrial Internet) is an innovative long range wireless broadband networking technology developed by Doodle Labs.
More informationSRA A Strategic Research Agenda for Future Network Technologies
SRA A Strategic Research Agenda for Future Network Technologies Rahim Tafazolli,University of Surrey ETSI Future Network Technologies ARCHITECTURE 26th 27th Sep 2011 Sophia Antipolis, France Background
More informationAnalysis of IEEE e for QoS Support in Wireless LANs
Analysis of IEEE 802.11e for QoS Support in Wireless LANs Stefan Mangold, Sunghyun Choi, Guido R. Hiertz, Ole Klein IEEE Wireless Communications, December 2003 Presented by Daeseon Park, Student No.2005-30231
More informationEnsemble of Specialized Neural Networks for Time Series Forecasting. Slawek Smyl ISF 2017
Ensemble of Specialized Neural Networks for Time Series Forecasting Slawek Smyl slawek@uber.com ISF 2017 Ensemble of Predictors Ensembling a group predictors (preferably diverse) or choosing one of them
More informationTrust Harris for LTE. Critical Conditions Require Critical Response
Trust Harris for LTE Critical Conditions Require Critical Response Harris LTE Solution Harris LTE Solution Harris LTE Networks Critical Conditions Require Critical Response. Trust Harris for LTE. Public
More informationSensor networks. Ericsson
Sensor networks IoT @ Ericsson NETWORKS Media IT Industries Page 2 Ericsson at a glance Organization & employees CEO Börje Ekholm Technology & Emerging Business Finance & Common Functions Marketing & Communications
More informationLearning to bounce a ball with a robotic arm
Eric Wolter TU Darmstadt Thorsten Baark TU Darmstadt Abstract Bouncing a ball is a fun and challenging task for humans. It requires fine and complex motor controls and thus is an interesting problem for
More informationCommunication and Computation in DCSP Algorithms
Communication and Computation in DCSP Algorithms Universitat de Lleida Cèsar Fernàndez Ramón Béjar.. Intelligent Information Systems Institute CORNELL Bhaskar Krishnamachari Carla Gomes September, 10th
More informationPLite.jl. Release 1.0
PLite.jl Release 1.0 October 19, 2015 Contents 1 In Depth Documentation 3 1.1 Installation................................................ 3 1.2 Problem definition............................................
More information04/11/2011. Wireless LANs. CSE 3213 Fall November Overview
Wireless LANs CSE 3213 Fall 2011 4 November 2011 Overview 2 1 Infrastructure Wireless LAN 3 Applications of Wireless LANs Key application areas: LAN extension cross-building interconnect nomadic access
More informationEmerging Connected Vehicle based
Exposing Congestion Attack on Emerging Connected Vehicle based Traffic Signal Control Qi Alfred Chen, Yucheng Yin, Yiheng Feng, Z. Morley Mao, Henry X. Liu Presented by Sezana Fahmida Outline Introduction
More information. 14 Byte for Acks. Due to this fact, the overhead is more relevant if the data contained in packets is sent to high rates:
QoS in IEEE 802.11 Issues Some issues are important for quality of service: the first one mentioned is the difference of performances expired by nodes based on their position in the network. Indeed, considering
More information5G enabling the 4th industrial revolution
5G enabling the 4th industrial revolution 1 Nokia 2016 Public First Industrial Revolution Second Industrial Revolution Third Industrial Revolution Fourth Industrial Revolution GSM 3G 4G 4.5G 4.9G 5G 5G
More informationUser 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 informationResource Allocation for LTE Multicast (embms): Group Partitioning and Dynamics
Resource Allocation for LTE Multicast (embms): Group Partitioning and Dynamics Jiasi Chen*, Mung Chiang*, Jeffrey Erman +, Guangzhi Li +, K. K. Ramakrishnan 1, Rakesh K Sinha + *Princeton University, +
More information