vananh_0nljne
New Member
Luận văn: A Push-pull based Application Multicast Layer for P2P live video streaming = M.A. Thesis Computer science: 60 48 01
Nhà xuất bản: ĐHCN
Ngày: 2011
Chủ đề: Khoa học máy tính
Internet
Video
Miêu tả: 45 p. + CD-ROM
M.A. Thesis. Computer science -- University of Engineering and technology. Vietnam National University, Hanoi, 2011
With the rapid growth of multimedia applications and the Internet, streaming video over the Internet is becoming more and more attractive to users especially live video streaming. Many application-layer multicast pro-tocols have been proposed recently for this demand and each method has different advantages. However, these current methods do not solve effectively peer to peer (P2P) live video streaming's problems. These problems are the randomly churn of nodes and long buffering time since the variance between the arrival times of data of different sub-streams is large. They also do not address the problem of free-riding nodes. This thesis presents our low-delay push-pull based application layer mul-ticast for live video streaming on P2P networks. The main goal of ourwork is to optimize content delivery on P2P networks to guarantee the time constraints of live video streaming. We achieve this goal by constructing multiple balanced sub-trees for pushing data and optimizing pulling connections between nodes in different sub-trees to reduce the time gap between arrival times of pushing data and pulling data. As a result, our mechanism can reduce buffering time at each node. Our mechanism also includes atit-for-tat method to promote node contribution. In order to evaluate our method's performance, we also build a simulation program in SMPL scheduler. We also compare our method's performance with other methods. The simulation result demonstrated the effectiveness of our method
1Introduction11.1Overview and Motivation . . . . . . . . . . . . . . . . . . . . . . . . .11.2Our contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . .31.3Thesis organization . . . . . . . . . . . . . . . . . . . . . . . . . . . .42Background52.1An Overview of multicast. . . . . . . . . . . . . . . . . . . . . . . .52.1.1IP Multicast . . . . . . . . . . . . . . . . . . . . . . . . . . . .62.1.2Application layer multicast . . . . . . . . . . . . . . . . . . . .72.2Application layer multicast methods for P2P live video streaming . .92.2.1Tree-based approach . . . . . . . . . . . . . . . . . . . . . . .92.2.1.1Single-tree . . . . . . . . . . . . . . . . . . . . . . . .92.2.1.2Multiple-tree . . . . . . . . . . . . . . . . . . . . . . 112.2.2Mesh-based approach . . . . . . . . . . . . . . . . . . . . . . . 123Our method for P2P live video streaming163.1Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 173.2Overlay construction . . . . . . . . . . . . . . . . . . . . . . . . . . . 183.3Data distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 203.4Fair policy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 223.5Node failure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 244Experiments and results264.1Experimental set-up. . . . . . . . . . . . . . . . . . . . . . . . . . . 264.1.1Topology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 274.1.2Simulation setting . . . . . . . . . . . . . . . . . . . . . . . . . 284.2Experimental result . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294.2.1Evaluation of services quality if no churn . . . . . . . . . . . . 29 4.2.2Evaluation of service’s quality if churn is present . . . . . . . . 314.2.3Evaluation of services quality in heterogeneous bandwidth case 335Conclusion36A Simulation program38A.1 Functions: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.1.1Input data: . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.1.2 Output data: . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.2 Classes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.1 Constant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.2 Smpl . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.3 DoSchedule: . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.4 Network: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.5 Node:. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.6 Message: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40B Generating input by using GT-ITM41 2.1Using unicast, broadcast and multicast for video streaming . . . . . .62.2An example of IP multicast. . . . . . . . . . . . . . . . . . . . . . .72.3An example of ALM . . . . . . . . . . . . . . . . . . . . . . . . . . .82.4Single multicast tree with 10 nodes . . . . . . . . . . . . . . . . . . . 102.5An example of multi-tree based streaming. . . . . . . . . . . . . . . 122.6An example of mesh-based video streaming method . . . . . . . . . . 132.7Prime mechanism [MR10]. . . . . . . . . . . . . . . . . . . . . . . . 143.1Pushing connections and pulling connection of a node . . . . . . . . . 183.2Example of changing position of high-bandwidth node . . . . . . . . . 203.3Example of diffusion phase with k = 3 . . . . . . . . . . . . . . . . . 213.4Example of swarming phase, node pulls missing data . . . . . . . . . 223.5Example of replacement of node failure . . . . . . . . . . . . . . . . . 254.1An example of real networks topology [NTks]. . . . . . . . . . . . . 284.2CDF of average variance between the arrival times of different partsin PRIME and in our method . . . . . . . . . . . . . . . . . . . . . . 304.3CDF of average parts delay and average segment delay from sourceto node in PRIME and in our method. . . . . . . . . . . . . . . . . 304.4CDF of missing parts ratio of node in our method when there is leaveand join nodes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 314.5CDF of average variance between the arrival times of different partsin our method when there is leave and join nodes . . . . . . . . . . . 324.6CDF of average parts delay and average segment delay from sourceto node in our method when there are leave and join nodes . . . . . . 324.7CDF of missing parts ratio of our method when participating nodeshave different bandwidth . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.8CDF of average parts delay from source to node when participatingnodes have different bandwidth . . . . . . . . . . . . . . . . . . . . . 344.9CDF of average segment delay from source to node when participatingnodes have different bandwidth . . . . . . . . . . . . . . . . . . . . . 35 Chapter 1Introduction1.1Overview and MotivationWith the rapid growth of multimedia applications and the Internet, stream-ing video over the Internet is becoming more and more attractive to users. Thisis especially the case for live video streaming. Live video streaming applicationsoften require transmitting streaming data to a large number of users. IP Multicast[DC90] is probably the most efficient solution for this requirement. However, thedeployment of IP multicast remains restricted due to many practical and politicalissues [HASG07]. Researchers thus have shifted focus to exploiting application-layermulticast (ALM) for data delivery. ALM utilizes the ability of end hosts that act notonly as receivers but also as senders. They can forward their received data to otherhosts. However, this solution is challenged by the dynamic join/leave of end hosts,the existence of free-riders, the heterogeneous of node bandwidth and the real-timeconstraint, especially in live streaming applications.Many application-layer multicast protocols have been proposed recently. Cur-rent application-layer multicast protocols can be divided into two classes: tree-basedapproach and mesh-based approach. The tree-based approach, organize participat-ing peers into multicast tree for data delivery ([CDK+03], [PWC03], [PKT+05],[WXL10], [RD01], [CDKR02], [BBMB+10], [LLR09], [THD04]). However, for tree-based designs with only one single tree, two major problems can be seen. Firstly, itis unfair between interior nodes and leaf nodes when leaf nodes do not contributeto the system. Secondly, the leave/failure of any interior node may cause packetoutage in all its descendant nodes. To deal with these problems, in SplitStream [CDK+03], nodes are structured intomultiple diverse trees such that an interior node in this tree will be a leaf node ofall other trees. Video streams are split into several smaller sub-streams using Mul-tiple Description Coding [AW01] or layered video [LPA98] and each sub-streamsdata is delivered by one tree. However, SplitStream requires all nodes to have equalbandwidth. Otherwise, its performance will be degraded. Some recent tree-basedresearch ([BBMB+10], [LLR09]) overcomes the disadvantage of Splitstream by op-timizing the construction of multi trees even when nodes have different bandwidth.However, multi-tree based approach still has a disadvantage of long buffering timedue to the variation in arrival times of different sub-streams data. Another problemthat all multi-tree-based designs have to face is the cost of maintaining and recov-ering multicast trees when there is a node churn (there is node join and leave in thesystem).Recently, mesh-based P2P streaming approach ([MR10], [MRW07], [VYF06],[ZXBY05], [ZLZY05], [LPA98], [CdSLMM11], [HCC10], [CJW11], [LKHT10]) hasattracted a lot of attention since it can minimize the impact of node churn and lowbandwidth of a neighbour node by pulling necessary data from a number of appro-priate neighbour nodes. Each node independently selects some nodes as neighboursand pulls data from them based on an assumption that neighbour nodes may havenecessary video data. However, there is a trade-off between minimum delay by send-ing pull request and overhead of whole system ([VYF06], [ZLZY05]). Furthermore,there are may exist content bottleneck due to the lack of data at the pulled nodes.PRIME [MR10] improves bandwidth bottleneck and content bottleneck by com-bining a method of pushing data via multiple sub-trees and a method of pulling datafrom nodes in different sub-trees. However, PRIME did not show clearly how is builtthe overlay network in the case that the bandwidth degree constraint does not sat-isfied and decentralized. [CdSLMM11], [CJW11] proposed some different strategiesto select connections but all these strategies are built based on the fact that thebootstrap node must store the whole information about all nodes in the network,which leads to low scalability. [LKHT10] shows how to build a decentralized overlaynetwork but with the cost of increased computation complexity. In addition, thesestrategies does not address problems such as long buffering time, node churn orfree-riders.Realizing this drawback in current application layer multicast methods for videostreaming, we aim to propose a push-pull based method for lower delay and better
Do Drive thay đổi chính sách, nên một số link cũ yêu cầu duyệt download.
Password giải nén nếu cần: ket-noi.com | Bấm vào Link, đợi vài giây sau đó bấm Get Website để tải:
Nhà xuất bản: ĐHCN
Ngày: 2011
Chủ đề: Khoa học máy tính
Internet
Video
Miêu tả: 45 p. + CD-ROM
M.A. Thesis. Computer science -- University of Engineering and technology. Vietnam National University, Hanoi, 2011
With the rapid growth of multimedia applications and the Internet, streaming video over the Internet is becoming more and more attractive to users especially live video streaming. Many application-layer multicast pro-tocols have been proposed recently for this demand and each method has different advantages. However, these current methods do not solve effectively peer to peer (P2P) live video streaming's problems. These problems are the randomly churn of nodes and long buffering time since the variance between the arrival times of data of different sub-streams is large. They also do not address the problem of free-riding nodes. This thesis presents our low-delay push-pull based application layer mul-ticast for live video streaming on P2P networks. The main goal of ourwork is to optimize content delivery on P2P networks to guarantee the time constraints of live video streaming. We achieve this goal by constructing multiple balanced sub-trees for pushing data and optimizing pulling connections between nodes in different sub-trees to reduce the time gap between arrival times of pushing data and pulling data. As a result, our mechanism can reduce buffering time at each node. Our mechanism also includes atit-for-tat method to promote node contribution. In order to evaluate our method's performance, we also build a simulation program in SMPL scheduler. We also compare our method's performance with other methods. The simulation result demonstrated the effectiveness of our method
1Introduction11.1Overview and Motivation . . . . . . . . . . . . . . . . . . . . . . . . .11.2Our contribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . .31.3Thesis organization . . . . . . . . . . . . . . . . . . . . . . . . . . . .42Background52.1An Overview of multicast. . . . . . . . . . . . . . . . . . . . . . . .52.1.1IP Multicast . . . . . . . . . . . . . . . . . . . . . . . . . . . .62.1.2Application layer multicast . . . . . . . . . . . . . . . . . . . .72.2Application layer multicast methods for P2P live video streaming . .92.2.1Tree-based approach . . . . . . . . . . . . . . . . . . . . . . .92.2.1.1Single-tree . . . . . . . . . . . . . . . . . . . . . . . .92.2.1.2Multiple-tree . . . . . . . . . . . . . . . . . . . . . . 112.2.2Mesh-based approach . . . . . . . . . . . . . . . . . . . . . . . 123Our method for P2P live video streaming163.1Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 173.2Overlay construction . . . . . . . . . . . . . . . . . . . . . . . . . . . 183.3Data distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 203.4Fair policy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 223.5Node failure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 244Experiments and results264.1Experimental set-up. . . . . . . . . . . . . . . . . . . . . . . . . . . 264.1.1Topology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 274.1.2Simulation setting . . . . . . . . . . . . . . . . . . . . . . . . . 284.2Experimental result . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294.2.1Evaluation of services quality if no churn . . . . . . . . . . . . 29 4.2.2Evaluation of service’s quality if churn is present . . . . . . . . 314.2.3Evaluation of services quality in heterogeneous bandwidth case 335Conclusion36A Simulation program38A.1 Functions: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.1.1Input data: . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.1.2 Output data: . . . . . . . . . . . . . . . . . . . . . . . . . . . 38A.2 Classes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.1 Constant . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.2 Smpl . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.3 DoSchedule: . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.4 Network: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.5 Node:. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39A.2.6 Message: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40B Generating input by using GT-ITM41 2.1Using unicast, broadcast and multicast for video streaming . . . . . .62.2An example of IP multicast. . . . . . . . . . . . . . . . . . . . . . .72.3An example of ALM . . . . . . . . . . . . . . . . . . . . . . . . . . .82.4Single multicast tree with 10 nodes . . . . . . . . . . . . . . . . . . . 102.5An example of multi-tree based streaming. . . . . . . . . . . . . . . 122.6An example of mesh-based video streaming method . . . . . . . . . . 132.7Prime mechanism [MR10]. . . . . . . . . . . . . . . . . . . . . . . . 143.1Pushing connections and pulling connection of a node . . . . . . . . . 183.2Example of changing position of high-bandwidth node . . . . . . . . . 203.3Example of diffusion phase with k = 3 . . . . . . . . . . . . . . . . . 213.4Example of swarming phase, node pulls missing data . . . . . . . . . 223.5Example of replacement of node failure . . . . . . . . . . . . . . . . . 254.1An example of real networks topology [NTks]. . . . . . . . . . . . . 284.2CDF of average variance between the arrival times of different partsin PRIME and in our method . . . . . . . . . . . . . . . . . . . . . . 304.3CDF of average parts delay and average segment delay from sourceto node in PRIME and in our method. . . . . . . . . . . . . . . . . 304.4CDF of missing parts ratio of node in our method when there is leaveand join nodes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 314.5CDF of average variance between the arrival times of different partsin our method when there is leave and join nodes . . . . . . . . . . . 324.6CDF of average parts delay and average segment delay from sourceto node in our method when there are leave and join nodes . . . . . . 324.7CDF of missing parts ratio of our method when participating nodeshave different bandwidth . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.8CDF of average parts delay from source to node when participatingnodes have different bandwidth . . . . . . . . . . . . . . . . . . . . . 344.9CDF of average segment delay from source to node when participatingnodes have different bandwidth . . . . . . . . . . . . . . . . . . . . . 35 Chapter 1Introduction1.1Overview and MotivationWith the rapid growth of multimedia applications and the Internet, stream-ing video over the Internet is becoming more and more attractive to users. Thisis especially the case for live video streaming. Live video streaming applicationsoften require transmitting streaming data to a large number of users. IP Multicast[DC90] is probably the most efficient solution for this requirement. However, thedeployment of IP multicast remains restricted due to many practical and politicalissues [HASG07]. Researchers thus have shifted focus to exploiting application-layermulticast (ALM) for data delivery. ALM utilizes the ability of end hosts that act notonly as receivers but also as senders. They can forward their received data to otherhosts. However, this solution is challenged by the dynamic join/leave of end hosts,the existence of free-riders, the heterogeneous of node bandwidth and the real-timeconstraint, especially in live streaming applications.Many application-layer multicast protocols have been proposed recently. Cur-rent application-layer multicast protocols can be divided into two classes: tree-basedapproach and mesh-based approach. The tree-based approach, organize participat-ing peers into multicast tree for data delivery ([CDK+03], [PWC03], [PKT+05],[WXL10], [RD01], [CDKR02], [BBMB+10], [LLR09], [THD04]). However, for tree-based designs with only one single tree, two major problems can be seen. Firstly, itis unfair between interior nodes and leaf nodes when leaf nodes do not contributeto the system. Secondly, the leave/failure of any interior node may cause packetoutage in all its descendant nodes. To deal with these problems, in SplitStream [CDK+03], nodes are structured intomultiple diverse trees such that an interior node in this tree will be a leaf node ofall other trees. Video streams are split into several smaller sub-streams using Mul-tiple Description Coding [AW01] or layered video [LPA98] and each sub-streamsdata is delivered by one tree. However, SplitStream requires all nodes to have equalbandwidth. Otherwise, its performance will be degraded. Some recent tree-basedresearch ([BBMB+10], [LLR09]) overcomes the disadvantage of Splitstream by op-timizing the construction of multi trees even when nodes have different bandwidth.However, multi-tree based approach still has a disadvantage of long buffering timedue to the variation in arrival times of different sub-streams data. Another problemthat all multi-tree-based designs have to face is the cost of maintaining and recov-ering multicast trees when there is a node churn (there is node join and leave in thesystem).Recently, mesh-based P2P streaming approach ([MR10], [MRW07], [VYF06],[ZXBY05], [ZLZY05], [LPA98], [CdSLMM11], [HCC10], [CJW11], [LKHT10]) hasattracted a lot of attention since it can minimize the impact of node churn and lowbandwidth of a neighbour node by pulling necessary data from a number of appro-priate neighbour nodes. Each node independently selects some nodes as neighboursand pulls data from them based on an assumption that neighbour nodes may havenecessary video data. However, there is a trade-off between minimum delay by send-ing pull request and overhead of whole system ([VYF06], [ZLZY05]). Furthermore,there are may exist content bottleneck due to the lack of data at the pulled nodes.PRIME [MR10] improves bandwidth bottleneck and content bottleneck by com-bining a method of pushing data via multiple sub-trees and a method of pulling datafrom nodes in different sub-trees. However, PRIME did not show clearly how is builtthe overlay network in the case that the bandwidth degree constraint does not sat-isfied and decentralized. [CdSLMM11], [CJW11] proposed some different strategiesto select connections but all these strategies are built based on the fact that thebootstrap node must store the whole information about all nodes in the network,which leads to low scalability. [LKHT10] shows how to build a decentralized overlaynetwork but with the cost of increased computation complexity. In addition, thesestrategies does not address problems such as long buffering time, node churn orfree-riders.Realizing this drawback in current application layer multicast methods for videostreaming, we aim to propose a push-pull based method for lower delay and better
Do Drive thay đổi chính sách, nên một số link cũ yêu cầu duyệt download.
Password giải nén nếu cần: ket-noi.com | Bấm vào Link, đợi vài giây sau đó bấm Get Website để tải:
You must be registered for see links
Last edited by a moderator: