云环境下基于动态蚁群遗传算法的调度方法研究

Research of Scheduling Method Based on Dynamic Ant Colony Genetic Algo-rithm in Cloud Environment

当前,随着云计算技术的发展,动态资源调度问题越来越受到大家的关注。针对蚁群算法在虚拟云环境下求解最佳调度路径的最小化,并不能满足资源调度最佳路径寻址与收敛性的问题。为了解决云计算调度应用的动态性与实时性,该文使用蚁群算法与遗传算法相结合的交叉混合调度策略。该策略算法使用动态编码方式,由蚁群算法根据信息素求出的最佳路径解作为遗传算法中的种子任务来优化遗传操作初始任务种群,与近年来原始算法在调度问题上相比较,文章提出的交叉算法调度策略具有明显的路径优化效果。仿真实验结果表明,动态蚁群遗传算法在云环境下任务资源调度最佳路径寻址、效率上具有明显的收敛效果。

At present,with the development of cloud computing technology,the problem of dynamic resource scheduling is causing more and more attention. The minimization of optimal scheduling method gained in the virtual cloud computing in view of the ant colony algorithm cannot meet the best path of resource scheduling for addressing and the problem of con- vergence. In order to solve the dynamic nature and real-time of cloud computing scheduling application the article use cross hybrid scheduling strategy which is the combination of ant colony algorithm and genetic algorithm. The strategy algorithm used dynamic encoding,taking the optimal path obtained by ant colony algorithm based on pheromone as the seed task in genetic algorithm for optimizing the genetic operations initial task population. And when it compares with the original algorithm in scheduling problem,the cross algorithm scheduling strategy proposed in this article has obvi- ous effects on path optimization. Simulation experimental results show that the dynamic ant colony genetic algorithm has obvious convergence efficiency on task resource scheduling optimal path for addressing in a cloud environment.