Enforce Cooperative Resource Sharing in Untrusted Peer-to-Peer Computing Environment

Peer-to-Peer (P2P) computing is widely recognized as a promising paradigm for building next generation distributed applications, ranging from large scale scientific applications to mobile ad hoc information sharing, by federating dispersed pools of geographically distributed resources under loosely coordinated control. However, the autonomous, heterogeneous, and decentralized nature of participating peers across multiple administrative domain introduces the challenge for resource sharing in such an environment: how to make the peers profitable in the decentralized resource sharing under the untrusted P2P environment. To address the problem, in this paper we present a self-policing and distributed approach by combining two models: PET, a PEsonalize Trust model, and M-CUBE, a multiple-currency based economic model, to lay a foundation for resource sharing in an untrusted P2P computing environment. PET is a flexible trust model that can adapt to different requirements, and provides the solid support for the currency management in M-CUBE. With the help of the trust management and the merits of the economics, M-CUBE provides a novel self-policing and quality-aware framework for the sharing of multiple resources, including homogenous and heterogeneous resources. We evaluate the efficacy and performance of this approach in the context of a real application, a peerto-peer Web server sharing. Our results show that our approach is flexible enough to adapt to different situations and effective to make the system profitable, especially for the system with large scale.