论文部分内容阅读
针对传统仿真系统静态构建技术中存在的资源重用性低、部署难度高等问题,提出了一种在云仿真运行环境下基于遗传算法来求解仿真模型与虚拟机之间最优映射的算法.该算法充分考虑云仿真环境下大规模资源调度的应用背景,保持适当的染色体编码长度,优化了种群的适应度函数,提高了GA算法收敛速度和所得解的可信度.实验结果表明:本文算法相比于传统遗传算法能有效避免局部收敛,达到更好的资源负载均衡效果.
Aiming at the problems of low reusability and high deployment difficulty in the traditional static construction of simulation system, this paper proposes an algorithm based on genetic algorithm to solve the optimal mapping between simulation model and virtual machine in cloud simulation operating environment. Considering the application background of large-scale resource scheduling in cloud simulation environment, keeping the appropriate chromosome coding length, the fitness function of population is optimized, and the convergence speed of GA algorithm and the credibility of the solution are improved.The experimental results show that the algorithm phase Compared with the traditional genetic algorithm can effectively avoid local convergence, to achieve better resource load balancing effect.