多任务处理协同进化粒子群算法

Co-evolutionary Particle Swarm Optimization for Multitasking

粒子群算法及其改进算法专注于单任务的求解.随着电子商务的发展,在线服务器在某一时刻需要同时处理来自多个用户的服务请求,即多任务处理.区别于以往的并行计算机,文中充分挖掘粒子群算法的"隐并行性",并引入协同进化机制,在同一搜索空间根据任务个数设置不同的子种群,各子种群以一定的概率相互传递有效信息,最后提出基于多任务处理协同进化粒子群算法(CPSOM),并将CPSOM应用于多任务连续型函数优化问题、多任务离散型属性选择问题以及多任务约束工程优化问题.仿真实验表明,在CPSOM多任务环境中,不同任务之间确实存在有效信息的传递,不同任务之间的相互协作不仅可以提高解的质量,而且可以加快各优化问题的收敛速度.

The traditional particle swarm optimization（ PSO） and its improved version aim to tackle the single task. With the development of electronic business,online severs need to deal with a batch of requests simultaneously,i.e. multitasking. Different from the parallel computer,the implicit parallelism of PSO is fully exploited, and co-evolution theory is introduced for multitasking. In the multitasking environment,different tasks correspond to different subpopulations, and the useful information is transferred from one subpopulation to another with a certain probability. Thus,co-evolutionary PSO for multitasking（ CPSOM） is proposed in this paper. To verify the effectiveness of the proposed algorithm,CPSOM is used to solve a batch of function test problems,feature selection problems and constrained engineering optimization problems. Experimental results show that the useful information can be autonomously transferred from one task to another in the CPSOM environment. Moreover,cooperation of different tasks enhance the solution quality and speed up the convergence.