A multiagent brokering protocol for supporting Grid resource discovery

摘要

Resource discovery provides a mean to identify the set of resources that are capable of satisfying the job requirements. Scalability and adaptability are two key challenges of resource discovery in a Grid environment. To deal with both issues, the agent concept has been adopted to cope with unexpected events such as the failure of provider agents. Multiple broker agents are used to deal with huge amounts of data from multiple sources. In our multiagent protocol, three types of agents (user agent, provider agent, and broker agent) are used. Each broker agent connects user agents to provider agents using the connection algorithm which mainly consists of 4 stages: selection, evaluation, filtering, and recommendation. In the recommendation stage, two kinds of recommendation approaches (circular approach and multicast approach) are used for making recommendations to the user agents that failed to be matched to provider agents. Empirical results show that our approach using multiagent brokering protocol with the adaptable feature of coordinating load balance (the results of balanced case) has significantly good performance in terms of scalability and adaptability.