基于人工鱼群遗传算法的异构多核系统任务调度研究

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。

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

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 convergence. 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 optimization and it improves the convergence of algorithm.