Cloud task scheduling method of load-based improved simulated annealing algorithm

The invention relates to a load-based cloud task scheduling method of an improved simulated annealing algorithm, and belongs to the technical field of networks. According to the method, the time-cost dual-fitness function is established, and the load delta L is added into the metropolis criterion in the traditional simulated annealing algorithm, so that the acceptance probability of a solution with a better system load is improved, and the system achieves load balance while the time and the cost of a task are reduced. Compared with a traditional simulated annealing algorithm, the method has the advantages that the total task execution time and the task execution cost are reduced, the balance degree of system loads is improved, and compared with a genetic simulated annealing algorithm, parameters are reduced, and implementation is easy. 本发明涉及一种基于负载的改进模拟退火算法的云任务调度方法，属于网络技术领域。本发明通过建立时间-成本双适应度函数并将负载ΔL加入到传统模拟退火算法中的metropolis准则中，提高系统负载较好的解的接受概率，使任务在减少时间以及成本的同时以使系统达到负载均衡。传统模拟退火算法相比，本发明降低了任务总执行时间以及任务执行成本，提高了系统负载的均衡度,