Higashino Lab. Maximizing User Gain in Multi-flow Multicast Streaming on Overlay Networks Y.Nakamura, H.Yamaguchi and T.Higashino Graduate School of Information.

Slides:



Advertisements
Similar presentations
Dynamic Replica Placement for Scalable Content Delivery Yan Chen, Randy H. Katz, John D. Kubiatowicz {yanchen, randy, EECS Department.
Advertisements

Multicasting in Mobile Ad hoc Networks By XIE Jiawei.
IP datagrams Service paradigm, IP datagrams, routing, encapsulation, fragmentation and reassembly.
Multicast in Wireless Mesh Network Xuan (William) Zhang Xun Shi.
Impact Analysis of Cheating in Application Level Multicast s 1090176 Masayuki Higuchi.
Network Layer Routing Issues (I). Infrastructure vs. multi-hop Infrastructure networks: Infrastructure networks: ◦ One or several Access-Points (AP) connected.
Multicast Fundamentals n The communication ways of the hosts n IP multicast n Application level multicast.
MQ: An Integrated Mechanism for Multimedia Multicasting By De-Nian Yang Wanjiun Liao Yen-Ting Lin Presented By- Sanchit Joshi Roshan John.
1 A Case For End System Multicast Yang-hua Chu, Sanjay Rao and Hui Zhang Carnegie Mellon University Largely adopted from Jonathan Shapiro’s slides at umass.
ZIGZAG A Peer-to-Peer Architecture for Media Streaming By Duc A. Tran, Kien A. Hua and Tai T. Do Appear on “Journal On Selected Areas in Communications,
A New Approach for the Construction of ALM Trees using Layered Coding Yohei Okada, Masato Oguro, Jiro Katto Sakae Okubo International Conference on Autonomic.
Computer Science ROMA: Reliable Overlay Multicast with Loosely Coupled TCP Connections Gu-In Kwon and John Byers Computer Science Dept. Boston University.
Network Coding for Large Scale Content Distribution Christos Gkantsidis Georgia Institute of Technology Pablo Rodriguez Microsoft Research IEEE INFOCOM.
Beneficial Caching in Mobile Ad Hoc Networks Bin Tang, Samir Das, Himanshu Gupta Computer Science Department Stony Brook University.
Network Layer4-1 Spanning trees r Suppose you have a connected undirected graph m Connected: every node is reachable from every other node m Undirected:
CMPE 150- Introduction to Computer Networks 1 CMPE 150 Fall 2005 Lecture 22 Introduction to Computer Networks.
Application Layer Multicast
Wireless Audio Conferencing System (WACS) Mehmet Ali Abbasoğlu Furkan Çimen Aylin Deveci Kübra Gümüş.
Chapter 10 Introduction to Wide Area Networks Data Communications and Computer Networks: A Business User’s Approach.
1 IP Multicasting. 2 IP Multicasting: Motivation Problem: Want to deliver a packet from a source to multiple receivers Applications: –Streaming of Continuous.
EE689 Lecture 12 Review of last lecture Multicast basics.
Multicast Communication
1 Algorithms for Bandwidth Efficient Multicast Routing in Multi-channel Multi-radio Wireless Mesh Networks Hoang Lan Nguyen and Uyen Trang Nguyen Presenter:
University of Nevada, Reno Virtual Direction Multicast for Overlay Networks Suat Mercan & Dr. Murat Yuksel HOTP2P’11.
CSE679: Multicast and Multimedia r Basics r Addressing r Routing r Hierarchical multicast r QoS multicast.
Receiver-driven Layered Multicast Paper by- Steven McCanne, Van Jacobson and Martin Vetterli – ACM SIGCOMM 1996 Presented By – Manoj Sivakumar.
1 Study on Adaptation of CDN Request-Routing to Scalable Conference System Toshiyuki KAWASAKI* Koji OKAMURA** * Graduate School of Information Science.
© 2004 Mobile VCE 1 An SMR Based Advance Resource Reservation Scheme For Combined Mobility and QoS Provisioning Hao Wang The University.
S305 – Network Infrastructure Chapter 5 Network and Transport Layers.
Communication (II) Chapter 4
Chapter 22 Network Layer: Delivery, Forwarding, and Routing
© Janice Regan, CMPT 128, CMPT 371 Data Communications and Networking Multicast routing.
Multicast Routing Protocols NETE0514 Presented by Dr.Apichan Kanjanavapastit.
CS An Overlay Routing Scheme For Moving Large Files Su Zhang Kai Xu.
© Janice Regan, CMPT 128, CMPT 371 Data Communications and Networking BGP, Flooding, Multicast routing.
AD HOC WIRELESS MUTICAST ROUTING. Multicasting in wired networks In wired networks changes in network topology is rare In wired networks changes in network.
ON DESIGING END-USER MULTICAST FOR MULTIPLE VIDEO SOURCES Y.Nakamura, H.Yamaguchi, A.Hiromori, K.Yasumoto †, T.Higashino and K.Taniguchi Osaka University.
Application-Layer Multicast -presented by William Wong.
Overlay Network Physical LayerR : router Overlay Layer N R R R R R N.
CONGESTION CONTROL and RESOURCE ALLOCATION. Definition Resource Allocation : Process by which network elements try to meet the competing demands that.
A Case for End System Multicast Yang-hua Chu, Sanjay G. Rao, Srinivasan Seshan and Hui Zhang Presentation by Warren Cheung Some Slides from
Multicast Routing Algorithms n Multicast routing n Flooding and Spanning Tree n Forward Shortest Path algorithm n Reversed Path Forwarding (RPF) algorithms.
Streaming over Subscription Overlay Networks Department of Computer Science Iowa State University.
1 [3] Jorge Martinez-Bauset, David Garcia-Roger, M a Jose Domenech- Benlloch and Vicent Pla, “ Maximizing the capacity of mobile cellular networks with.
Chapter 22 Network Layer: Delivery, Forwarding, and Routing Part 5 Multicasting protocol.
Impact of Topology on Overlay Multicast Suat Mercan.
Load-Balancing Routing in Multichannel Hybrid Wireless Networks With Single Network Interface So, J.; Vaidya, N. H.; Vehicular Technology, IEEE Transactions.
© J. Liebeherr, All rights reserved 1 Multicast Routing.
Multicast Routing, Error Control, and Congestion Control.
CSC 600 Internetworking with TCP/IP Unit 7: IPv6 (ch. 33) Dr. Cheer-Sun Yang Spring 2001.
Björn Landfeldt School of Information Technologies NETS 3303 Networked Systems Multicast.
2007/03/26OPLAB, NTUIM1 A Proactive Tree Recovery Mechanism for Resilient Overlay Network Networking, IEEE/ACM Transactions on Volume 15, Issue 1, Feb.
This paper appears in: Computer Communications and Networks, ICCCN Proceedings.15th International Conference on 指導教授 : 許子衡 報告者 : 黃群凱 1.
KAIS T High-throughput multicast routing metrics in wireless mesh networks Sabyasachi Roy, Dimitrios Koutsonikolas, Saumitra Das, and Y. Charlie Hu ICDCS.
APPLICATION LAYER MULTICASTING
Multiuser Receiver Aware Multicast in CDMA-based Multihop Wireless Ad-hoc Networks Parmesh Ramanathan Department of ECE University of Wisconsin-Madison.
Rate-Based Channel Assignment Algorithm for Multi-Channel Multi- Rate Wireless Mesh Networks Sok-Hyong Kim and Young-Joo Suh Department of Computer Science.
On Reducing Mesh Delay for Peer- to-Peer Live Streaming Dongni Ren, Y.-T. Hillman Li, S.-H. Gary Chan Department of Computer Science and Engineering The.
August 23, 2001ITCom2001 Proxy Caching Mechanisms with Video Quality Adjustment Masahiro Sasabe Graduate School of Engineering Science Osaka University.
Global Internet 2005 A Comparative Study of Multicast Protocols: Top, Bottom, or In the Middle? Li Lao (UCLA), Jun-Hong Cui (UCONN) Mario Gerla (UCLA),
Efficient Resource Allocation for Wireless Multicast De-Nian Yang, Member, IEEE Ming-Syan Chen, Fellow, IEEE IEEE Transactions on Mobile Computing, April.
Chapter 6 outline r 6.1 Multimedia Networking Applications r 6.2 Streaming stored audio and video m RTSP r 6.3 Real-time, Interactive Multimedia: Internet.
1 A Case For End System Multicast Yang-hua Chu, Sanjay Rao and Hui Zhang Carnegie Mellon University.
A Multicast Routing Algorithm Using Movement Prediction for Mobile Ad Hoc Networks Huei-Wen Ferng, Ph.D. Assistant Professor Department of Computer Science.
Communication Networks Recitation 11. Multicast & QoS Routing.
Cost-Effective Video Streaming Techniques Kien A. Hua School of EE & Computer Science University of Central Florida Orlando, FL U.S.A.
Kapitel 19: Routing. Kapitel 21: Routing Protocols
Multicast Outline Multicast Introduction and Motivation DVRMP.
MZR: A Multicast Protocol based on Zone Routing
EE 122: Lecture 22 (Overlay Networks)
Presentation transcript:

Higashino Lab. Maximizing User Gain in Multi-flow Multicast Streaming on Overlay Networks Y.Nakamura, H.Yamaguchi and T.Higashino Graduate School of Information Science and Technology, Osaka University

Higashino Lab. FMUIT'069 May Research Goal Realizing Multi-party video conferencing systems Many-to-many multicast application which consists of hundreds of users User hosts exchange multiple video streams in real- time Efficient use of bandwidth is required Internet

Higashino Lab. FMUIT'069 May Application Layer Multicast (ALM) ALM is multicast on overlay networks End users act as multicast routers Does not require special hardware such as IP multicast enable routers Application-specific routing protocols can be designed More efficient than Unicast because a sender does not need to send data to all receivers Unicast A B C S D A B C S D ALM

Higashino Lab. FMUIT'069 May Related works Overcast , CAN , RMX aiming at an efficient delivery of video stream in a large-scale group HBM aiming at overlay network construction for the mobile terminal Narada , ALMI , Yoid aiming at delivery of single video stream in small-scale group also target the conference application Few research to deliver the two or more streams simultaneously and continuously for the video conferencing

Higashino Lab. FMUIT'069 May Issues to be considered Each video uses some amount of bandwidth on overlay networks → In delivering multiple video streams, they compete for bandwidth on overlay links Users may have priority requirements to video streams e.g. users may prefer the speaker’s video than audience’s video Internet

Higashino Lab. FMUIT'069 May Emma/QoS New ALM protocol for multi-party communication systems Users construct overlay network Each user sends its own video continuously and receives some of other user hosts’ video streams on overlay networks Each user filters and adjusts the quality of streams and make the space for a new requested stream Internet Overlay Network Red

Higashino Lab. FMUIT'069 May Overlay Network New user joins the session by constructing the overlay link Measuring the delay with another user, and constructing the overlay link with the number of appropriate users When the link is constructed, the link capacity (number of streams that can be delivered) is negotiated and decided The participating users enhance the delivery routing tree The routing tree of the source user is constructed with the shortest path tree by flooding Overlay network construction Underlying Network D A B E C

Higashino Lab. FMUIT'069 May Leaving failure management Many users frequently leave on the overlay network Descendant node cannot receive the stream We need guarantee the continuance delivery of the stream Need to make the stream had delivered through the left node can immediately delivered from another node again Each node knows the nodes can deliver the stream by periodical message If neighbor node leaves, t he node is immediately reconnected to one of them

Higashino Lab. FMUIT'069 May Loss/Gain-based rate adaptation Problem Because of the restriction and a decrease of the link capacity, all requests of stream cannot be accepted Solutions Simple way When the stream cannot be delivered, all requests of the stream are not accepted Narada When it is impossible to deliver the stream in the received rate in each user, user reduces the rate of the stream so that it can be delivered Emma/QoS Each user decides that it increases / reduces the rate of the stream according to the value of the gain obtained by receiving the requested stream and cutting the rate of the delivering stream Requests are accepted as many as possible

Higashino Lab. FMUIT'069 May User gain function Every user defines for each stream User gain is added when a unit of bandwidth is added to current receiving stream We use utility function This function shows the priority of the user for each unit of bandwidth e.g. In the typical streaming, utility tends to increase suddenly by the rate of a at least necessary quality, and to increase gradually in a rate increase after that User gain is calculated by the difference of the following two values Value on utility function of k-1 units Value on utility function of added k-th unit k denotes certain amount of bandwidth on the overlay links Utility function k-1k } User gain Linear approximation

Higashino Lab. FMUIT'069 May Protocol operations Every node periodically sends messages about user gain (negative gain) for each stream Negative gain : Value of user gain lost in descendant nodes when a unit is deprived from delivering stream Request message is transmitted calculating the optimal allocation of each unit from user gain and a negative gain that increases by the request acceptance when requesting it As a result, each user can know and decide which stream should be reduced B # of units of links is 3 : Streams

Higashino Lab. FMUIT'069 May Performance evaluations We have implemented a simulator of Emma/QoS simulated in a typical video conferencing scenario compared with Narada (one of the most popular ALMs) We examined the following items Link stress : the number of copies of a single packet delivered on a physical link Path stretch : the ratio of the sum of unicast hops of the overlay links between two nodes to that on the shortest path on the underlying physical network User satisfaction ratio : the ratio of the sum of user gain obtained by each node to that of user gains requested by the node Variation of user gain

Higashino Lab. FMUIT'069 May # of users 0 Emma/QoS Narada Emma/QoS Narada Unicast # of physical links Link stress and path stretch Compare with the performance of Narada Narada assumes the delay between hosts to be optimizing metric and constructs mesh-like overlay network On this overlay network Narada constructs shortest path tree Emma/QoS has better values than unicast Maximum link stress is about 10th of the unicast The performance of Narada is not so quite different from that of Emma/QoS Link StressPath Stretch

Higashino Lab. FMUIT'069 May Distribution of users’ satisfaction The ratio of the total gain of accepted requests to that of all requests Requests not accepted at all is much smaller than Narada and FCFS (First Come First Serve method) The admission control mechanism of Emma/QoS is useful to video-conference systems

Higashino Lab. FMUIT'069 May Emma/QoS Narada # of users gain (avg.) 15 # of users time Variation of user gain Emma/QoS achieves higher user gain than Narada when users join/leave during the session when users’ preferences to stream s are changed during the session

Higashino Lab. FMUIT'069 May Conclusion We have proposed new ALM protocol called Emma/QoS To avoid resource competition, we use utility-based admission control in decentralized way From the experimental results Higher satisfaction of users than a simple method Even though some users leave from or join to a session, users’ satisfaction is kept high