自适应混合粒子群算法在梯级水电站群优化调度中的应用  

Application of self-adaptive hybrid particle swarm optimization algorithm to optimal operation of cascade reservoirs

作　　者：王森[1] 武新宇[1] 程春田[1] 郭有安[2] 李红刚[2] 

机构地区：[1]大连理工大学水电与水信息研究所,大连116024 [2]华能澜沧江水电有限公司,昆明650000

出　　处：《水力发电学报》2012年第1期38-44,共7页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金(50979010);国家自然科学基金(51109024);国家杰出青年科学基金(51025934)

摘　　要：针对梯级水电站群长期优化调度发电量最大模型,提出了一种自适应混合粒子群进化算法(AHPSO)。该算法引入混沌思想生成初始解,并定义了粒子能量、粒子能量阈值、粒子相似度和粒子相似度阈值来描述算法的自适应变化以及群体进化程度,同时结合遗传变异思想进行粒子操作,最后提出了一种基于邻域的随机贪心策略以解决算法后期进化速度慢的缺点。以澜沧江下游梯级水电站群为计算实例的结果表明,AHPSO比基本粒子群算法有更好的收敛性和优化结果,计算时间比逐步优化算法少,且优化结果相近,是一种可供选择的计算方法。A self-adaptive hybrid particle swarm optimization algorithm（AHPSO） is proposed to solve the long-term optimal operation model of cascade reservoirs.With total power output as objective function,this model generates initial solutions with chaos and defines variables of particle energy,particle similarity and their thresholds to describe the algorithm＇s self-adaptive changes and the swarm-evolving degree.In the model,a random greedy searching strategy of neighborhood is adopted to overcome the shortcoming of slow evolving at the later stage.Application in a case study of the cascade reservoirs on the Lancangjiang river shows that the self-adaptive AHPSO is better in convergence and optimized solution than the traditional particle swarm method and that it is comparable to the progressive optimization algorithm but its computational cost is lower.

关 键 词：工程水文学 梯级水电站群 优化调度 粒子群算法 自适应 粒子能量 

分 类 号：TV697[水利工程—水利水电工程]