Efficient and incentive-compatible resource allocation mechanism for P2P-assisted content delivery systems

摘要

In this paper, we propose an efficient resource allocation mechanism for Peer-to-peer(P2P) assisted content delivery systems. The key component of the mechanism is a novel distributed data bartering protocol that can redistribute the bandwidth resources among peers according to their contributions. It is formally proved that the proposed mechanism is incentive-compatible, i.e., the only optimal strategy of each peer is to behave honestly and to contribute as much as possible. Based on the proposed mechanism, we design a general P2P-assisted content delivery system for delivering both live video streams and static files. We also propose the design of some key modules including peer/data organization, bandwidth allocation, data scheduling, and tax rate adjustment. We implement our system on a packet-level simulator and simulate two scenarios: P2P live streaming and P2P file sharing. Experimental results on real world traces show that the system can provide both differentiated services and satisfactory performance to peers. Furthermore, when bandwidth resource levels are dynamic, the system can still guarantee consistent service quality by adjusting the global tax rate adaptively. We also find that our system can effectively defend against dishonest behaviors even when the percentage of cheating peers is as high as 50%.