No abstract

No abstract

Transmission control protocol (TCP) with its well-established congestion control mechanism is the prevailing transport layer protocol for non-real time data in current Internet Protocol (IP) networks. It would be desirable to transmit any type of multimedia data using TCP in order to take advantage of the extensive operational experience behind TCP in the Internet. However, some features of TCP including retransmissions and variations in throughput and delay, although not catastrophic for non-real time data, may result in inefficiencies for video streaming applications. In this paper, we propose an architecture which consists of an input buffer at the server side, coupled with the congestion control mechanism of TCP at the transport layer, for efficiently streaming stored video in the best-effort Internet. The proposed buffer management scheme selectively discards low priority frames from its head-end, which otherwise would jeopardize the successful playout of high priority frames. Moreover, the proposed discarding policy is adaptive to changes in the bandwidth available to the video stream. © 2004 Elsevier B.V. All rights reserved

No abstract

In the recent years, the peer-to-peer (P2P) overlay network has been a promising architecture for multimedia streaming services besides its common use for efficient file sharing. By simply increasing the number of peers, the P2P overlay network can meet the high bit rate requirements of multimedia applications. Optimal peer selection for newly joining peers is one of the important problems, especially in wireless networks which have limited resources and capacity, since the peer selection process has a direct impact on the throughput of the underlay network and the co-existing unicast traffic. In this paper we tackle the problem of peer selection for streaming applications over wireless ad hoc networks. We devise a novel peer selection algorithm which maximizes the throughput of the underlay network, and at the same time makes P2P streaming friendly towards the co-existing data traffic. The proposed receiver based Rate allocation and Peer Selection (RPS) algorithm is derived using the network utility maximization (NUM) framework. The algorithm solves the peer selection and rate allocation problem distributedly while optimally adapting the medium access control (MAC) layer parameters and is easily extensible to large P2P networks. Simulation results show that by using the proper price exchange mechanism, the peer receivers can effectively maximize the throughput of the underlay network by intelligently selecting its source peers.Index Terms-P2P streaming, peer selection, wireless ad hoc networks, dual decomposition, cross-layer design.