基于小生境多目标粒子群算法的输电网检修计划优化  

Optimization of Transmission Network Maintenance Scheduling Based on Niche Multi-objective Particle Swarm Algorithm

作　　者：刘文颖 谢昶 文晶 王佳明 王维洲[2] 

机构地区：[1]新能源电力系统国家重点实验室(华北电力大学),北京市昌平区102206 [2]甘肃电力科学研究院,甘肃省兰州市730050

出　　处：《中国电机工程学报》2013年第4期141-148,19,共8页Proceedings of the CSEE

基　　金：国家电网公司重点科技项目(2011103004)~~

摘　　要：以检修成本和期望缺供电量最小为目标,建立输电网检修计划多目标优化模型,并提出一种基于小生境的改进多目标粒子群算法对其进行求解。通过得到一组Pareto最优解,全面统筹检修计划优化问题的经济性和可靠性目标。该算法采用小生境共享机制来更新粒子的位置,保持了解的多样性和分布的均匀性;引入混沌变异对部分非支配粒子进行小范围的扰动,提高了算法全局搜索能力,避免陷入局部最优。为使算法能够更好地应用于输电网检修计划优化问题,采用罚函数对约束条件进行处理,并根据模糊隶属度从Pareto最优解集中选取最优折衷解,为检修计划制定人员提供了科学的决策依据。通过IEEE RTS-79节点系统的仿真,验证了该算法在求解输电网检修优化问题时能有效避免早熟收敛,快速地收敛至Pareto最优解集。Taking the minimum maintenance cost and expected energy not supplied（EENS） as objective functions,this paper built a multi-objective optimization model for maintenance scheduling of transmission network and proposed an improved multi-objective particle swarm optimization algorithm based on niche technology for the built model.Through getting a set of Pareto optimal solutions,the model can coordinate the economic and reliability objectives of maintenance scheduling optimization problem.The algorithm used a niche sharing mechanism to update particle’s position so as to keep the diversity of solution and the uniformity of distribution.Besides,by means of leading in chaotic mutation to part of non-dominated particles,the global searching ability of the proposed algorithm was enhanced,and local optimum was also avoided.In order to make the algorithm apply to maintenance scheduling optimization problem better,this paper processed the constraints by using a penalty function,and selected the best compromise solution from the Pareto optimal solution set according to fuzzy membership degree,and provided the scientific decision basis for maintenance plan makers.Simulation of IEEE-RTS 79 bus system testify that this algorithm can avoid the premature phenomenon and local convergence effectively in solving transmission network maintenance optimization problem,and convergence to the Pareto optimal solution set rapidly.

关 键 词：输电网检修计划 多目标粒子群算法 小生境共享 混沌变异 最优折衷解 

分 类 号：TM[电气工程]