基于GIS和改进微分进化算法的农网变电站选址定容

Substation locating and sizing in rural power system based on GIS and modified differential evolution algorithm

基于地理信息管理系统将改进微分进化算法引入到变电站优化选址定容求解问题中。利用三个标准的优化算法测试函数对引入惯性加权系数的微分进化改进算法进行了测试,并与标准微分进化算法进行比较。结果证明对不同函数有目的性地调整惯性加权系数F的取值范围可以提高改进算法的搜索效率。在选址模型中考虑了地理因素对投资费用的影响,并综合考虑了农网特点和其所处的复杂地理环境和对变电站选址的影响,使结果更具科学性和可行性。

A modified differential evolution （MDE） algorithm is introduced to solve the problems of substation location optimization based on GIS. Numerical study is carried out using three benchmark functions to the introduced inertia scaling factor MDE algorithm, and the result is compared with that of dynamic differential evolution. Analysis results show that the efficiency of modified differential evolution is significantly improved for adjusting the inertia scaling factor F scope purposefully to different function. The model of the problem involving the geographic information, the rural power network characteristic and its located complex geographical environment make the given solution more effective and feasible.