An intelligent agent-basedmethod for task allocation in competitive cloud environments

摘要

In market-based cloud environments, both resource consumers and providers are self-interested;rnadditionally, they can come and leave the environment freely. Therefore, the environment is competitivernand uncertain. Because of the competition, participants may cheat in making deals, andrnthis represents that the environment is insecure to resource providers who intend to earn profitsrnthrough renting their resources to the tasks of resource consumers. Against this, in this paper,rnintelligent agents are designed to strategically quote for the tasks that they are interested in, onrnbehalf of resource providers. Agents could quote according to the messages it obtained and therninformation learntandpredicted from the messages, to minimize the influence of insecure factors,rnsuch as cheating, competition, and dynamism. The experimental evaluation shows that the proposedrnmethod outperforms both a well-known multiresource negotiation-based task allocationrnmethod and a max-sum belief propagation–based method.