基于人工鱼群遗传算法的异构多核系统任务调度研究  

Research of tasks scheduling in heterogeneous multi-core system based on artificial fish-swarm and genetic algorithm

作　　者：姚丽莎[1] 王占凤[2] 程家兴[1] 

机构地区：[1]安徽新华学院信息工程学院,安徽合肥230088 [2]巢湖学院计算机与信息工程学院,安徽合肥238000

出　　处：《计算机工程与科学》2014年第10期1866-1871,共6页Computer Engineering & Science

基　　金：安徽省教育厅自然科学研究项目(KJ2011Z157)

摘　　要：异构多核系统的任务调度问题已经被证明是一个NP完全问题。人工鱼群算法在算法初期具有较快的收敛速度,后期收敛较慢,而遗传算法的种群初始化具有较强的鲁棒性,初始化种群的质量直接影响着遗传算法的性能。本文提出了一种将人工鱼群算法与遗传算法相结合的任务调度算法,首先分析了异构多核系统的任务调度问题的本质,使用改进的人工鱼群算法来构建遗传算法的初始化种群,并使用改进的遗传算法进行迭代进化,从而提高了算法的收敛速度。Tasks scheduling for heterogeneous-multi-core processor system have been proved to be a NP complete problem. Artificial fish-swarm algorithm begins to converge quickly, then has slow conver- gence. It is robust for genetic algorithm to initialize population; the initialization of the first population affects the performance of genetic algorithm. Based on artificial fish-swarm and genetic algorithm, a task scheduling algorithm is proposed. Firstly, the tasks scheduling of heterogeneous multi-core system is analyzed. Secondly, the improved artificial fish-swarm Algorithm is used to construct the initial population of genetic algorithm. Finally, the improved genetic algorithm is applied to perform iterative optim zation and it improves the convergence of algorithm.

关 键 词：人工鱼群算法 遗传算法 任务调度 

分 类 号：TP316.4[自动化与计算机技术—计算机软件与理论]