云计算任务调度的粒子鸡群优化算法研究

Cloud Computing Task Scheduling based on Particle Chicken-Swarm Optimization Algorithm

粒子群优化算法已经有许多的研究应用在云计算任务调度上,但是粒子群优化算法在应用过程中易出现陷入早熟、求解精度低的缺点。针对上述不足,提出混合标准粒子群与鸡群优化算法的策略,将粒子群算法以任务完成总时间和任务执行成本为目标进一步优化,最后用cloudsim对新算法与标准粒子群算法、鸡群优化算法进行比较。实验结果表明,新算法在任务完成总时间和任务总的执行成本上取得了明显改善,能够更好地提高对用户的服务质量和需求。

Many researches on particle swarm optimization algorithms are applied to cloud computing task scheduling and however the particle swarm optimization algorithms are prone to premature aging and low accuracy in the application process.In view of the above shortcomings,the strategy of hybrid standard particle swarm optimization and flock optimization algorithm is proposed.Firstly with total completion time and task execution cost as the goal,the particle swarm optimization algorithm is further optimized.Then,cloudsim is used to compare the new algorithm with the standard particle swarm algorithm and the flock optimization algorithm.The experimental results indicate that the new algorithm could receive significant improvement in the total task-completion time and the total task-execution cost,and thus fairly promote the quality of service and demand for users.