Path Selection in Streaming Video Over Multioverlay Application Layer Multicast

Abstract

Abstract-Application-layer multicast (ALM) has grown tremendously in recent years, making the distribution of bulk data such as streaming video economically feasible for small companies and even individuals. The efficiency of an ALM network depends on its data distribution overlay, which is constructed based on metrics such as round-trip time (RTT) measurement between peers. However Internet measurement experiments revealed that RTT is far from an accurate estimator of bandwidth availability and as such, may lead to sub-optimal performance in the constructed ALM overlays. This paper tackles this problem by developing a new in-band bandwidth probing tool which can estimate the amount of achievable bandwidth available in the target network path so that excess data traffic can be diverted from the congested path without causing new congestion in the target path. Moreover, the probing tool does not incur any bandwidth overhead as it piggybacks on the existing data flow. Simulation results show that multioverlay ALM networks constructed based on achievable bandwidth consistently out-performs RTT-based and residual bandwidthbased approaches in terms of data delivery ratio and video playback continuity. Moreover, the proposed bandwidth probing tool can be implemented entirely within the application and thus can be readily incorporated into existing ALM protocols.

A path selection approach with genetic algorithm for P2P video streaming systems

“…In the simulations, there is one video server and one tracker server residing one of the ISPs. The average bandwidth distribution of links in the system is in accordance with the values given in [19]. The values of the parameters used in the simulations are given in are selected according to the optimal values given in [18] and [17].…”

“…The partnership is achieved mutually and buffermap exchange is realized within 2 s' periods between the partners. (1)) 500 chunks T p (used in formula (2)) 500 chunks Generation count [10][11][12][13][14][15][16][17][18][19][20] The peer joining the system plays the video after it buffers for up to 8 s. During the streaming, if a peer decides to choose a new parent and if this selection is not successful, i.e., the received video bitrate is not adequate to play the video properly, and candidate parents cannot be found, some partners are deleted from the list and new partners are selected from the membership list. If this problem continues for 20 s, the peer resets itself and joins the system again.…”

“…In these systems, the parents are selected according to these criteria; hence the improvement in experienced quality increases by changing/adding parents, in other words, by changing of streaming path or retransmitting over alternative paths. An achievable bandwidth estimation method which can be utilized in hybrid push-pull systems has been proposed in [19]. It is shown that the performance of the proposed method is superior than that of systems considering RTT and available bandwidth [4,7,15,29].…”

“…It is shown that the performance of the proposed method is superior than that of systems considering RTT and available bandwidth [4,7,15,29]. Achievable bandwidth differs from the available bandwidth of the path due to the fact that it considers the fairness property of TCP protocol, which provides more accurate bandwidth estimation between peers [19].…”

CloudTCast: A Video Distribution Solution Based on Cloud and Tree-based ALM

“…So far there exist a lot of P2P streaming protocols, which generally fall into two coexisting strategic categories-mesh-pull P2P and tree-push P2P (i.e., tree-based ALM). The tree-based ALM solutions (e.g., [4], [5], [6], [7], [8]) organize participating peers into one or more multicast trees, and disseminate the data along these trees. As mentioned above, the tree-based ALM can obtain excellent forwarding effectiveness.…”