Performance evaluation of market-based resource allocation for Grid computing

摘要

Resource allocation is an important aspect of Grid computing. Over the past few years, various systems have been developed which use market mechanisms to allocate resources. However, the performance of such policies has not been sufficiently studied. In this paper, we investigate under which circumstances market-based resource allocation by continuous double auctions and by the proportional share protocol, respectively, outperforms a conventional round-robin approach. We develop a model for clients, servers and the market, and present simulation results. Factors which are studied include the amount of load in the system, the number of resources, different degrees of resource heterogeneity, and communication delays.