异构多核处理器任务调度算法研究

Research on Task Scheduling Algorithm in Heterogeneous Multi-processor

任务调度问题是研究异构多核处理器中最为重要的问题之一,一个好的调度算法可以充分发挥系统性能,提高系统效率。针对遗传算法的缺陷,文章提出了一种改进的遗传算法来解决异构多核处理器任务调度问题,在算法的初始化种群产生时将Sufferage算法和随机生成方法相结合,在采用随机方法生成个体时使用Hamming距离来控制个体之间的差异,从而在提高初始种群质量的同时又保证了种群的多样性。结果表明改进后的遗传算法提高了初始种群质量,提高算法的寻优起点,具有较好的调度性。

Task scheduling problem is a important issuthe in study of heterogeneous multi-processor, a good scheduling algor-ithm can give full play to the performance of the system and improve system efficiency. For defects of genetic algorithm, an im-proved genetic algorithm is proposed to solve the problem of he task scheduling in terogeneous multi-core processor. In the pro-cess of population initialization, a new method which combines the Sufferage algorithm and random generation method.It uses hamming distance to control the difference among the individuals in using a random method to produce individual. Therefore, the new method can not only improve the quality of initial population, but also ensure the diversity of population. The results show that the improved genetic algorithm improves the quality of the initial population, improve the starting optimization point of the algorithm and has better convergence.