基于改进粒子群算法的云数据中心能耗优化任务调度策略  

Task Scheduling Strategy for Energy Consumption Optimization of Cloud Data Center Based on Improved Particle Swarm Algorithm

作　　者：刘陈伟 孙鉴 雷冰冰 徐涛[1] 吴隹伟 LIU Chenwei;SUN Jian;LEI Bingbing;XU Tao;WU Zhuiwei(School of Computer Science and Engineering,North Minzu University,Yinchuan 750021,China;Key Laboratory of Images&Graphics Intelligent Processing of State Ethnic Affairs Commission,North Minzu University,Yinchuan 750021,China)

机构地区：[1]北方民族大学计算机科学与工程学院,银川750021 [2]北方民族大学图像图形智能处理国家民委重点实验室,银川750021

出　　处：《计算机科学》2023年第7期246-253,共8页Computer Science

基　　金：国家自然科学基金(62062002,62102201);宁夏自然科学基金(2022AAC03289,2022AAC03245,2021AAC03034);北方民族大学中央高校基本科研业务费专项资金(FWNX09);北方民族大学校级一般项目(2021XYZJK01)。

摘　　要：随着云计算的发展,能耗急剧上升,这进一步限制了云数据中心整体性能的提高,因此能耗问题引起了工业界和学术界的重视。同时,传统粒子群算法被广泛应用于数据中心任务调度问题的求解,但其收敛速度慢、精度低,容易忽略集群能耗问题。为此提出了一种基于反向学习的混沌映射自适应粒子群算法(OAPSO)。首先,采用反向学习的方法产生初始种群,使粒子更加均匀地分布于初始解空间,提高了初始种群的质量;其次,在粒子更新方式中引入非线性递减的动态惯性权重策略,以改变粒子的寻优能力,使局部搜索和全局搜索达到平衡,避免算法陷入局部最优;然后,引入混沌映射策略,在最优解位置进行扰动变异产生新解,提高算法从局部最优中跳出的能力。最后,在Cloudsim平台上对所提算法进行实验验证,结果表明,与PSO,OBL_TP_PSO和SAPSO算法相比,OAPSO算法资源利用率更高,节能效果更好。With the development of cloud computing,energy consumptionhas increased dramatically,which further limits the improvement of the overall performance of the cloud data center,and thus the energy consumption issue has attracted the attention of industry and academia.Meanwhile,traditional particle swarm optimization algorithm(PSO)is widely used to solve data center task scheduling problems,but it has the shortcomings of slow convergence and low accuracy,and it is easy to ignore the cluster energy consumption problem.A chaotic mapping adaptive particle swarm optimization algorithm based on opposition-based lear-ning(OAPSO)is proposed.Firstly,the initial population is generated by the method of opposition-based learning,which makes the particles more evenly distributed in the initial solution space and improves the quality of the initial population.Secondly,a nonlinear decreasing dynamic inertia weight stra-tegy is introduced into the particle updating mode to change the particle optimization ability,so as to balance the local search and global search and avoid the algorithm falling into the local optimal.Thirdly,the chaotic mapping strategy is introduced to generate new solutions by perturbation and mutation at the optimal location,which improves the ability of the algorithm to jump out of the local optimal.Finally,the proposed algorithm is verified by experiments on the Cloudsim platform,and the results show that,compared to PSO,OBL_TP_PSO and SAPSO,OAPSO algorithm has higher resource utilization and better energy-saving effect.

关 键 词：云数据中心 任务调度 粒子群算法 混沌映射 能耗优化 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]