基于改进人工蜂群算法的配电网重构  

Distribution Network Reconfiguration Based on Improved Artificial Bee Colony Algorithm

作　　者：邓海潮[1] 毛弋[1] 彭文强[1] 刘小丽[1] 梁杉[1] 范幸[1] 

机构地区：[1]湖南大学电气与信息工程学院,长沙410082

出　　处：《电力系统及其自动化学报》2016年第7期125-129,共5页Proceedings of the CSU-EPSA

摘　　要：为了更好地解决配电网重构问题,采用改进人工蜂群算法,建立了以系统有功损耗为目标的重构模型。在该改进算法中,利用差分进化操作的思想对人工蜂群算法中的邻域搜索方式进行了改进,直接在离散域进行多维搜索代替原来的单维更新策略,提高了算法的探索能力并且加快了收敛速度。此外,为了克服基于比例适应度选择的不足,用基于适应度排序的选择概率替代基于比例适应度的选择概率,使得种群的多样性得到了保护,从而避免了陷入局部最优。该算法应用于配电网重构能够以较快的速度收敛到最优解,文中的算例结果验证了该算法用于网络重构是可行而且有效的。In order to deal with distribution network reconfiguration better,artificial bee colony algorithm was proposedto construct a mathematical model for distribution network reconfiguration in which the network loss minimization isbuilt. In this improved algorithm,the search behaviors are modified by using the differential evolution operators. Original one-dimensional neighborhood search strategy is replaced by multidimensional neighborhood search strategy in thediscrete domain,which improves the exploration ability and accelerates the converge speed of the algorithm. Moreover,to overcome the shortage of selection based on the proportion of fitness,the selection based on fitness ranking probability is adopted instead of depending on the proportion of fitness,which protects the diversity of the population and avoidspremature convergence. The algorithm used in distribution network reconfiguration can converge at a faster rate to theoptimal solution,and results of calculation examples show that the proposed algorithm is feasible and effective.

关 键 词：人工蜂群算法 配电网重构 邻域搜索 适应度排序选择 

分 类 号：TM72[电气工程—电力系统及自动化]