基于混合萤火虫遗传算法的云计算中的任务调度优化

Task Scheduling Optimization in Cloud Computing Based on Hybrid Firefly Genetic Algorithm

云计算被广泛应用于商业计算,将计算资源从大量资源池中优化分配给用户,因此在按需连接中分配资源的能力面临严重的挑战。任务调度是作业车间调度问题的一个变种,属于计算复杂性中的NP完全(NP-Complete)问题。对此提出了一种新的混合萤火虫遗传组合的元启发式调度算法任务,融合了萤火虫等数学优化算法和遗传算法等进化算法的优点,形成了一个强大的元启发式搜索算法。混合萤火虫遗传算法能够以所有任务的执行时间最小为目标,快速收敛到近似最佳方案来调度任务。该算法在云计算仿真软件CloudSim中进行了测试,实验结果表明,所提出的算法性能优于传统的FIFO算法和遗传算法。

Cloud computing is widely used in commercial computing needs,and computing resources are optimally allocated to users from a large resource pool.Therefore,the ability to allocate resources in on-demand connections faces serious challenges.Task scheduling is a variant of job shop scheduling problem,which belongs to the NP-complete problem in computational complexity.This paper proposes a new meta-heuristic scheduling algorithm task of hybrid firefly genetic combination,which combines the advantages of mathematical optimization algorithms such as firefly and evolutionary algorithms to form a powerful meta-heuristic search algorithm.The hybrid firefly genetic algorithm can target the minimum execution time of all tasks and quickly converge to an approximate optimal solution to schedule tasks.The algorithm is tested in the cloud computing simulation software CloudSim.The experimental results show that the performance of the proposed algorithm is better than the traditional FIFO algorithm and genetic algorithm.