TY - JOUR
T1 - Pushing server bandwidth consumption to the limit
T2 - Modeling and analysis of peer-assisted VoD
AU - Xu, Ke
AU - Wang, Haiyang
AU - Liu, Jiangchuan
AU - Lin, Song
AU - Xu, Lei
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/12/1
Y1 - 2014/12/1
N2 - Recent years have witnessed video-on-demand (VoD) as an efficient means for providing reliable streaming service for Internet users. It is known that peer-assisted VoD systems, such as NetFlix and PPlive, generally incur a lower deployment cost in terms of server bandwidth consumption. However, some fundamental issues still need to be further clarified, particularly for VoD service providers. In particular, how far can we push peer-assisted VoD forward, and at the scale of VoD systems, the maximum reduction of server bandwidth consumption that can be achieved with peer-assisted approaches. In this paper, we provide extensive model analysis to understand the minimum server bandwidth consumption for peer-assisted VoD systems. We first propose a basic model that can optimally schedule user demands at given snapshots. Our model analysis reveals the optimal performance bound and shows that the existing peer-assisted protocols are still far from being optimal. How to push the server bandwidth consumption to the limit remains a big challenge in VoD system design. To approach the optimal bandwidth consumption in real deployment, we further extend our model to a realistic case to capture the peer dynamic across continuous time-slots. The simulation result indicates that the optimal load scheduling problem is still achievable through a dynamic programming algorithm. Its design principle further motivates a fast priority-based algorithm that achieves near-optimal performance. These proposed algorithms can significantly reduce the bandwidth consumption of dedicated VoD servers.
AB - Recent years have witnessed video-on-demand (VoD) as an efficient means for providing reliable streaming service for Internet users. It is known that peer-assisted VoD systems, such as NetFlix and PPlive, generally incur a lower deployment cost in terms of server bandwidth consumption. However, some fundamental issues still need to be further clarified, particularly for VoD service providers. In particular, how far can we push peer-assisted VoD forward, and at the scale of VoD systems, the maximum reduction of server bandwidth consumption that can be achieved with peer-assisted approaches. In this paper, we provide extensive model analysis to understand the minimum server bandwidth consumption for peer-assisted VoD systems. We first propose a basic model that can optimally schedule user demands at given snapshots. Our model analysis reveals the optimal performance bound and shows that the existing peer-assisted protocols are still far from being optimal. How to push the server bandwidth consumption to the limit remains a big challenge in VoD system design. To approach the optimal bandwidth consumption in real deployment, we further extend our model to a realistic case to capture the peer dynamic across continuous time-slots. The simulation result indicates that the optimal load scheduling problem is still achievable through a dynamic programming algorithm. Its design principle further motivates a fast priority-based algorithm that achieves near-optimal performance. These proposed algorithms can significantly reduce the bandwidth consumption of dedicated VoD servers.
KW - Video-on-demand (VOD)
KW - peer-assisted systems
KW - scheduling
UR - http://www.scopus.com/inward/record.url?scp=84919932463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84919932463&partnerID=8YFLogxK
U2 - 10.1109/TNSM.2014.2360772
DO - 10.1109/TNSM.2014.2360772
M3 - Article
AN - SCOPUS:84919932463
SN - 1932-4537
VL - 11
SP - 472
EP - 485
JO - IEEE Transactions on Network and Service Management
JF - IEEE Transactions on Network and Service Management
IS - 4
M1 - 6912984
ER -