动态速度限制粒子群算法及其应用  

Dynamic speed limits particle swarm optimization and application

作　　者：陈立华[1] 蔡德所[1] 梅亚东[2] 

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

出　　处：《广西大学学报（自然科学版）》2010年第1期152-156,共5页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(50779049);国家科技重大专项基金资助项目(2008ZX07317-001);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,建立了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,从算法参数方面对基本粒子群算法进行改进,提出了动态速度限制粒子群算法并与基本粒子群算法、改进型粒子群算法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,验证了改进策略在提高算法求解精度和收敛性能方面的有效性。According to the characteristics of optimal operation of cascade hydropower stations, a particle swarm algorithm for solving a multi-stage optimization problem is established. Aiming at the defects of basic particle swarm optimization algorithm （ BPSO）, such as low precision and easy to divergence in the early stage, ＂homogenization＂ and ＂premature＂ and other phenomena in the later stage, improvement on the algorithm parameters of the BPSO is made and the dynamic speed limit particle swarm optimization algorithm （DSLPSO） is developed. Then, DSLPSO, BPSO, and improved PSO are applied separately to the optimal operation of cascade hydropower stations in Yalong River and the comparison of their optimization results verifies the effectiveness of the improvement strategies in enhancing the accuracy and convergence of the algorithm.

关 键 词：粒子群算法 动态速度 梯级水电站 

分 类 号：TV697.1[水利工程—水利水电工程]