虚拟资源分配优化量子学习算法仿真研究

Simulation of Quantum Learning Algorithm on Virtual Resources Allocation Optimization

针对单一优化目标的基于用户需求或服务质量的虚拟资源分配问题,采用协同决策方法,将用户满意、效能最优和服务质量多目标协同集成,以虚拟资源计算服务租用收益和用户满意度效用最大化为优化目标,构建虚拟资源分配集成优化模型。提出改进的量子粒子群算法,设计种群的个体学习权重因子,增加个体寻优的学习激励策略,设置粒子搜索的学习阈值,解决算法陷入局部最优解的问题。通过种群搜索学习求解,得出满足用户需求、效能和服务质量的虚拟资源作业分配的最优服务收益选择方案。仿真结果表明,改进算法具有较好的全局搜索效率和性能。

For single optimization goal of virtual resource allocation based on user requirements or quality of service,the collaborative decision-making method was adopted to integrate user satisfaction,performance optimization and service quality multi-objectives.The virtual resource computing service lease revenue and user satisfaction utility maximization were optimized,and the virtual resource allocation integration optimization model was constructed.An Improved Quantum Particle Swarm Optimization(IQPSO)algorithm was proposed.The individual learning weight factors of the population were designed,the learning incentive strategy of individual optimization was proposed,the learning threshold of particle search was set,and the problem that the algorithm falls into the local optimal solution was solved.Through population search learning,the optimal service revenue selection scheme for job assignment of virtual resources to meet users’needs,efficiency and service quality was obtained.The simulation results show that the improved algorithm has better global search efficiency and performance.