基于改进蚁群算法的云环境任务调度研究

Study on Cloud Computing Task Schedule Strategy Based on MACO Algorithm

针对蚁群优化算法(ACO)在解决大规模的组合优化问题时容易陷入搜索速度慢和局部最优的缺陷,进行算法的改进;结合遗传算法全局收敛的优点,将遗传算法融入到蚁群优化算法的每一次迭代中,加快其收敛速度,并引入逆转变异策略,避免了蚁群优化算法陷入局部最优;深入研究了改进的蚁群优化算法在云计算环境中的任务调度策略,并通过扩展云计算仿真平台CloudSim实现了模拟仿真;实验结果表明,此算法能够缩短云环境下的任务平均运行时间,提高了资源利用率。

For characteristics of Ant Colony Optimization Algorithm in solving the large-scale combination optimization problem easy to fall into the search speed slowly and partially the most superior,the global fast convergence of genetic algorithm is utilized to combine ant colony optimization algorithm with genetic algorithm in each generation,which enhances the convergence rate and improves the efficiency.And the reversal variation strategy is introduced to avoid the ant colony optimization algorithm falling into partial most superior.The paper deeply researches the improved Ant Colony Optimization Algorithm（ACO） in resources scheduling strategy of the cloud computing,by extending the Cloud Computing platform CloudSim to test the simulation.The results show that this method can reduce the task average running time,and raises the rate availability of resources.