Using Evolutionary Computation to Optimize Mobile Agent Performance

摘要

The distributed nature of mobile agents raises questions as to how to initially position agents for efficient cooperation in a computer network. In this paper we present a method using evolutionary computation to discover a near optimal way to divide a graph amongst many agents. This work entails design and implementation of the mobile agent, creation of a simulation environment in which to simulate the operation of the agent, and the evolutionary computation system to partition the graph.