Combining Reliability and Economic Incentives in Peer-to-Peer Grids

Abstract

Peer-to-peer grids emerge as the convergence of grid computing and peer-to-peer technologies. In p2p grids, unreliability and free-riding are two serious problems that must be effectively solved. Existing studies are concerned with either of the two problems, while we believe they are closely related for building a practical p2p grid system. Our goal is to ensure consumer tasks can be reliably executed while the economic revenue of service peers is maximized. In this work, we combine reliability and economic incentives to achieve such a goal. First, we design a scheme to determine the minimum reliability threshold based on the bidding price of a consumer. Second, we propose a group of scheduling heuristics to obtain the approximately maximum revenue of service providers in p2p grids. Finally, we perform extensive simulations to evaluate the effectiveness of our solution.