Job-shop scheduling based on multiagent evolutionary algorithm

Abstract

With the intrinsic properties of job-shop scheduling problems (JSPs) in mind, we integrate the multiagent systems and evolutionary algorithms to form a new algorithm, Multiagent Evolutionary Algorithm for JSPs (MAEA-JSPs). In MAEA-JSPs, all agents live in a latticelike environment. Making use of the designed behaviors, MAEA-JSPs realizes the ability of agents to sense and act on the environment in which they live. During the process of interacting with the environment and the other agents, each agent increases energy as much as possible, so that MAEA-JSPs can find the optima. In the experiments, 59 benchmark JSPs are used, and good performance is obtained. © Springer-Verlag Berlin Heidelberg 2005.