“…Each peer divides the set of unacquired pieces into high priority set and low priority set by the closeness to the PP, and conducts a piece selection in the following two steps: 1) select one set with a certain probability, and 2) select a piece from the selected set according to the rarest first rule [2]. Although the piece selection rule adopted in BiToS is widely used in the literature [21], it is pointed out that in order to attain a satisfactory performance, the selection of pieces from the high priority set should be conducted so that both of the rareness and the closeness to the PP (within the high priority set) are taken into account [12].…”
Section: Related Workmentioning
confidence: 99%
“…A similar idea has been proposed in [1] so that the set of neighbors is dynamically divided into high priority group and low priority group, and in selecting the target of upload, it first selects a group with a certain probability and then selects requests in the descending order of the criticalness of the deadline. Appropriate selection of uploaders is also considered in the literature [12], [19]. In the method proposed in [19], each peer keeps the number of un-responded requests for each neighbor, and issues a request to a neighbor with the least un-responded requests.…”
Section: Related Workmentioning
confidence: 99%
“…Since any of previous schemes [1], [12], [15], [18], [19] concerned with match making do not use the overlay of SPs, we cannot directly compare them with the proposed scheme. Recall that the key idea of the proposed scheme is that: 1) it explicitly uses the data structure reflecting the difference of the status of piece acquisition, and 2) it explicitly conducts match making between requests and uploaders by using a hierarchical approach.…”
SUMMARYThis paper proposes a method to reduce the playback suspension in a Video-on-Demand system based on the Peer-to-Peer technology (P2P VoD). Our main contribution is twofold. The first is the proposal of a hierarchical P2P architecture with the notion of dynamic swarms. Swarm is a group of peers to have similar playback position and those swarms are connected with an overlay so that requested pieces are forwarded from a swarm to another swarm in a bucket brigade manner, where the forward of pieces is regulated by the super-peer (SP) of each swarm. The second contribution is the proposal of a match making scheme between requests and uploaders. The simulation result indicates that the proposed scheme reduces the total waiting time of a randomized scheme by 24% and the load of the media server by 76%.
“…Each peer divides the set of unacquired pieces into high priority set and low priority set by the closeness to the PP, and conducts a piece selection in the following two steps: 1) select one set with a certain probability, and 2) select a piece from the selected set according to the rarest first rule [2]. Although the piece selection rule adopted in BiToS is widely used in the literature [21], it is pointed out that in order to attain a satisfactory performance, the selection of pieces from the high priority set should be conducted so that both of the rareness and the closeness to the PP (within the high priority set) are taken into account [12].…”
Section: Related Workmentioning
confidence: 99%
“…A similar idea has been proposed in [1] so that the set of neighbors is dynamically divided into high priority group and low priority group, and in selecting the target of upload, it first selects a group with a certain probability and then selects requests in the descending order of the criticalness of the deadline. Appropriate selection of uploaders is also considered in the literature [12], [19]. In the method proposed in [19], each peer keeps the number of un-responded requests for each neighbor, and issues a request to a neighbor with the least un-responded requests.…”
Section: Related Workmentioning
confidence: 99%
“…Since any of previous schemes [1], [12], [15], [18], [19] concerned with match making do not use the overlay of SPs, we cannot directly compare them with the proposed scheme. Recall that the key idea of the proposed scheme is that: 1) it explicitly uses the data structure reflecting the difference of the status of piece acquisition, and 2) it explicitly conducts match making between requests and uploaders by using a hierarchical approach.…”
SUMMARYThis paper proposes a method to reduce the playback suspension in a Video-on-Demand system based on the Peer-to-Peer technology (P2P VoD). Our main contribution is twofold. The first is the proposal of a hierarchical P2P architecture with the notion of dynamic swarms. Swarm is a group of peers to have similar playback position and those swarms are connected with an overlay so that requested pieces are forwarded from a swarm to another swarm in a bucket brigade manner, where the forward of pieces is regulated by the super-peer (SP) of each swarm. The second contribution is the proposal of a match making scheme between requests and uploaders. The simulation result indicates that the proposed scheme reduces the total waiting time of a randomized scheme by 24% and the load of the media server by 76%.
“…A remarkable feature of BiToS is that it does not rely on any media server, while techniques proposed there are also applicable to P2P VoDs with a media server. The piece selection rule in BiToS was further refined by many researchers; e.g., Zhou et al [11] proposed a mixed strategy consisting of several known rules and Sakashita et al [8] proposed a rule based on the rarity and the urgency of pieces. The reader should note that those piece selection rules can be used with our proposed scheme in a combined manner, since the objective of our scheme is to reduce the load of a media server rather than the increase of the efficiency of piece exchanges.…”
SUMMARYIn this paper, we consider Peer-to-Peer Video-on-Demand (P2P VoD) systems based on the BitTorrent file sharing protocol. Since the Rarest First policy adopted in the original BitTorrent protocol frequently fails to collect pieces corresponding to a video file by their playback time, we need to develop a new piece selection rule particularly designed for P2P VoDs. In the proposed scheme, we assume the existence of a media server which can upload any piece upon request, and try to bound the load of such media server with two techniques. The first technique is to estimate pieces which are not held by any peer and prefetch them from the media server. The second technique is to switch the mode of each peer according to the estimated size of the P2P network. The performance of the proposed scheme is evaluated by simulation.
“…For example, to enhance the fluidity of fast-forward (and fast-backward) operations, the size of each piece must be much smaller than conventional P2P VoDs, and the support of the seek operation, which allows users to jump to arbitrary chapters in the video file, violates the assumption behind conventional P2P VoDs such that each peer tries to collect as many pieces close to the current playback position as possible [14], [16]. In each of the above two cases, precise identification of the buffer map of the neighbors would play a crucial role in efficiently supporting VCR function.…”
SUMMARYIn this paper, we propose a new buffer map notification scheme for Peer-to-Peer Video-on-Demand systems (P2P VoDs) which support VCR operations such as fast-forward, fast-backward, and seek. To enhance the fluidity of such VCR operations, we need to refine the size of each piece as small as possible. However, such a refinement significantly degrades the performance of buffer map notification schemes with respect to the overhead, piece availability and the efficiency of resource utilizations. The basic idea behind our proposed scheme is to use a piece-based buffer map with a segment-based buffer map in a complementary manner. The result of simulations indicates that the proposed scheme certainly increases the accuracy of the information on the piece availability in the neighborhood with a sufficiently low cost, which reduces the intermittent waiting time of each peer by more than 40% even under a situation in which 50% of peers conduct the fast-forward operation over a range of 30% of the entire video.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.