基于分布估计-单亲遗传算法的配电网规划  

Distribution Network Optimal Planning Based on Algorithm of Partheno-genetic Algorithm and Estimation of Distribution Algorithm

作　　者：章文俊[1] 程浩忠[1] 王卫华[2] 

机构地区：[1]上海交通大学电气工程系,上海200240 [2]华东电力设计院,上海200063

出　　处：《高电压技术》2009年第6期1476-1482,共7页High Voltage Engineering

基　　金：上海市重点科技攻关计划(041612012);高等学校优秀青年教师教学科研奖励计划~~

摘　　要：为了改善单亲遗传算法在某些方面存在的缺陷,提出一种分布估计算法与单亲遗传算法相结合的混合智能算法进行配电网的优化规划。并结合普里姆(Prim)算法产生初始种群,获得比完全随机产生的配电网络更优的初始方案。分布估计算法根据所得分布概率可为单亲遗传算法提供搜索方向,而后者则加速了前者精确分布概率模型的获得,二者的结合起到了优势互补的作用。实例计算的对比结果表明,混合算法更加稳定高效。In order to improve some defects of partheno-genetic algorithm, a hybrid intelligent algorithm of parthenogenetic algorithm （PGA） and estimation of distribution algorithm （EDA） was presented to handle distribution networks optimal planning problem. Prim algorithm was employed to produce preliminary radial networks, which are better than entirely random schemes. The distribution probability of EDA can provide search direction for PGA, and the latter accelerates the obtaining of the accurate model of distribution probability. By the complementary advantages of the hybrid algorithm, the convergence rate is accelerated. The results show that the hybrid algorithm is more steady and effective.

关 键 词：配电网络规划 辐射网 分布估计算法 单亲遗传算法 PRIM算法 树形结构编码 

分 类 号：TM715[电气工程—电力系统及自动化]