摘要：This paper proposes a Distributed Multi-ant Algorithm for capacity vehicle route problem (CVRP) where cooperation is helpful for accelerating prior solution by executing a decomposition-based separation methodology for the unsteady capacity constraints. It decreases the complex coupling network with others to solve small instances with less correlation in parallel processing. The main goal of this work is to play well on large scale CVRP with interaction between subsystems and certain state vectors. The results show that Distributed Multi-ant Algorithm plays better performance on average solution and the importance of potential action is analyzed.
