Searching For Agent Coalition Using Particle Swarm Optimization Algorithm

The coordination and cooperation among agent in large-scale complicated system is a key problem. Coalition Generation is a key topic in Multi-Agent System, some research about searching for agent coalition using particle swarm optimization is done. The conclusion enriches the theories of MAS and Particle Swarm Optimization Algorithm, and provides theoretical and methodological guidance for the manufacture of practical application system.The main research contents and innovations in this dissertation are as follow:Coalition Generation mainly focuses on how to generate the optimal task-oriented coalition in a dynamic manner. Compared with GA and ACA, the feature of Particle Swarm Optimization (PSO) Algorithm is parallel, distributed and robust. A Discrete Particle Swarm Optimization (DPSO) Algorithm is adopted to solve the problem which reduces the time and improves the quality of the solution. The results of constructive experiments show that this algorithm is superior to other related methods both on the quality of solution and on the convergence rate.A Task-matching Based Coalition Generation Strategy is presented and realized. This paper introduces the concepts of History Task Set and System Experience Set, and employes the Similarity of Tasks to estimate their relationship. It presents a Task-matching based coalition generation strategy by which the learning ability of agents is highly enhanced and the optimal solution for the task alignment is generated. The contrastive experiments show that this strategy can decrease the retrieving time and computation effectively.