TY - GEN
T1 - Foresighted joint resource reciprocation and scheduling strategies for real-time video streaming over peer-to-peer networks
AU - Lee, Sunghoon Ivan
AU - Park, Hyunggon
AU - Van Der Schaar, Mihaela
PY - 2009
Y1 - 2009
N2 - We consider peer-to-peer (P2P) networks, where multiple heterogeneous and self-interested peers are sharing multimedia data. In this paper, we propose a novel scheduling algorithm for real-time video streaming over dynamic P2P networks. The proposed scheduling algorithm is foresighted, since it enables each peer to maximize its long-term video quality by efficiently utilizing its limited resources (e.g., uploading bandwidth) over time, while explicitly considering the time-varying resource reciprocation behaviors of its associated peers. To successfully design the scheduling algorithm, we consider a distinct buffer structure that allows the peers to model the resource reciprocation behavior as a reciprocation game. Then, each peer can determine its foresighted decisions based on a Markov Decision Process (MDP). The simulation results show that the proposed algorithm significantly improves the average video quality, compared to other existing scheduling strategies. Moreover, simulation results also show that the proposed algorithm can flexibly and effectively operate in heterogeneous P2P networks.
AB - We consider peer-to-peer (P2P) networks, where multiple heterogeneous and self-interested peers are sharing multimedia data. In this paper, we propose a novel scheduling algorithm for real-time video streaming over dynamic P2P networks. The proposed scheduling algorithm is foresighted, since it enables each peer to maximize its long-term video quality by efficiently utilizing its limited resources (e.g., uploading bandwidth) over time, while explicitly considering the time-varying resource reciprocation behaviors of its associated peers. To successfully design the scheduling algorithm, we consider a distinct buffer structure that allows the peers to model the resource reciprocation behavior as a reciprocation game. Then, each peer can determine its foresighted decisions based on a Markov Decision Process (MDP). The simulation results show that the proposed algorithm significantly improves the average video quality, compared to other existing scheduling strategies. Moreover, simulation results also show that the proposed algorithm can flexibly and effectively operate in heterogeneous P2P networks.
KW - Foresighted scheduling strategy
KW - Peer-to-peer (P2P) networks
KW - Real-time video streaming
KW - Resource reciprocation game
UR - http://www.scopus.com/inward/record.url?scp=70350367530&partnerID=8YFLogxK
U2 - 10.1109/PACKET.2009.5152153
DO - 10.1109/PACKET.2009.5152153
M3 - Conference contribution
AN - SCOPUS:70350367530
SN - 9781424446520
T3 - 2009 17th International Packet Video Workshop, PV 2009
BT - 2009 17th International Packet Video Workshop, PV 2009
T2 - 2009 17th International Packet Video Workshop, PV 2009
Y2 - 11 May 2009 through 12 May 2009
ER -