摘要
配电网重构是一种有效的网络拓扑结构优化方法,通过重构可有效降低配电网功率损耗,提高供电质量。大多数文献通过建立静态重构模型来分析配电网功率损耗,不能满足配电系统参数随时间动态变化的过程。因此本文提出了一种基于实时电价的配电网动态重构方法,首先以历史电价及历史负荷为输入数据,采用BP神经网络算法预测未来一周的实时电价;然后使用自适应差分进化算法对实时电价各时段进行静态重构,合并相邻且相同的静态重构结果得到一次时段划分,在此基础上利用遗传算法并以综合费用最小为目标函数进行二次时段划分,从而得到最终动态重构划分方案;最后采用IEEE33节点配电系统数据对研究内容进行仿真分析,验证方法的可行性。
Reconfiguration of distribution network is an effective method of network topology optimization.It can effectively reduce the power loss of distribution network and improve the quality of power supply.Most literatures analyze the power loss of the distribution network by establishing a static reconstruction model,which cannot meet the process of dynamic changes of the parameters of the distribution system over time.Therefore,this paper proposes a dynamic reconstruction method for distribution networks based on real-time electricity prices.First,the historical electricity price and historical load are used as input data,and the BP neural network algorithm is used to predict the real-time electricity price in the next week.Then use the adaptive differential evolution algorithm to perform static reconstruction for each period of real-time electricity prices,Merge adjacent and identical static reconstruction results to get the first time period division.Based on this,the genetic algorithm is used and the minimum comprehensive cost is used as the objective function to perform the secondary period division,so as to obtain the final dynamic reconstruction division scheme;Finally,the data of IEEE33 node power distribution system is used to carry out simulation analysis to verify the feasibility of the method.
作者
谭文勇
TAN Wen-yong(School of Electrical Engineering,Guizhou University,Guiyang,Guizhou 550025)
出处
《新型工业化》
2020年第2期6-11,共6页
The Journal of New Industrialization
基金
贵州省科技创新人才团队项目(黔科合平台人才[2018]5615)。
关键词
配电网重构
BP神经网
差分进化算法
动态重构时段划分
Reconfiguration of distribution network
BP neural network
Differential evolution algorithm
Dynamic reconstruction period division
