自适应多策略粒子群算法在水库群优化调度中的应用  

Adaptive multi-variant strategy particle swarm optimization algorithm and its application to the optimal operation of cascade reservoirs

作　　者：陈立华[1] 梅亚东[2] 杨娜[2] 

机构地区：[1]广西大学土木建筑工程学院,南宁530004 [2]武汉大学水资源与水电工程科学国家重点实验室,武汉430072

出　　处：《水力发电学报》2010年第2期139-144,共6页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金项目(50779049);广西大学科研基金资助项目(X081098)

摘　　要：根据梯级水电站优化调度特点,建立粒子群算法求解多阶段最优化问题数学模型。针对基本粒子群算法(PSO)在早期存在精度较低、易发散等缺点,后期出现"趋同性"和"早熟"等现象,提出了自适应多策略粒子群算法。并将该算法与基本PSO、改进型PSO、杂交PSO和收敛因子PSO分别在雅砻江梯级水库群优化调度中应用,通过对其优化结果的比较,验证了改进算法在加快收敛速度和提高算法精度方面的有效性。In this work a mathematical model is established to solve multi-stage optimization problem for the operation of cascade hydropower stations. The particle swarm optimization （ PSO） algorithm is of low accuracy,easy to diverge at the early stage,and tends to homoplasy and premature at the later stage. Thus an improved PSO or the adaptive multi-variant stratege PSO algorithm （AMPSO） is proposed. The optimization of cascade hydropowers on the Yalong river is solved separately by PSO,AMPSO,hybrid PSO and convergence- factor PSO. Results show an improvement of AMPSO in convergence and accuracy.

关 键 词：水电工程 粒子群算法 水库调度雅砻江 梯级水电站 

分 类 号：TV697.1[水利工程—水利水电工程]