基于神经网络的电网潮流图自动拓扑布线方法  

Automatic Topology Wiring Method of Power Flow Diagram Based on Neural Network

作　　者：徐遐龄 田国辉 刘涛 于文娟 肖大军 梁陕鹏 XU Xialing;TIAN Guohui;LIU Tao;YU Wenjuan;XIAO Dajun;LIANG Shanpeng(Central China Electric Power Dispatching Control Sub-center,Central China Branch of State Grid Corporation of China,Wuhan 430077,China;NARI Group Corporation(State Grid Electric Power Research Institute),Nanjing 211106,China;Beijing Kedong Electric Power Control System Co.,Ltd.,Beijing 100192,China)

机构地区：[1]国家电网公司华中分部华中电力调控分中心,湖北省武汉市430077 [2]南瑞集团有限公司(国网电力科学研究院有限公司),江苏省南京市211106 [3]北京科东电力控制系统有限责任公司,北京市100192

出　　处：《电力系统自动化》2022年第6期102-108,共7页Automation of Electric Power Systems

基　　金：国网华中电力调控分中心科研基金(HZ200623-62)对本文工作的支持。

摘　　要：为了解决电网复杂拓扑条件下潮流图自动拓扑布线问题,提出了一种基于神经网络的电网潮流图自动拓扑布线方法。通过建立线路每步步长方向选择与生成线路质量的关联关系构建神经网络的输入层和输出层,进一步进行线路拓扑的自主学习来获取步长方向选择函数的最优解,然后利用训练好的步长方向选择函数进行拓扑路径检索,以解决潮流图自动布线过程中如何寻找最优拓扑连接的问题。基于某220 kV电网进行了算法仿真,结果验证了所提方法的有效性和可行性。与传统自动成图方式相比,所提方法不需要根据不同画面特征人为对拓扑连线的坐标计算算法进行适配,训练过程也无需依赖现有潮流图样本,可明显提升潮流图自动成图的灵活性和准确性。In order to solve the problem of automatic topology wiring of power flow diagram under complex topology of power grid, an automatic topology wiring method of power flow diagram based on neural network is proposed. By establishing the correlation between the step direction selection of each step of the line and the quality of the generated line, the input layer and output layer of the neural network are constructed, and the autonomous learning of the line topology is further carried out to obtain the optimal solution of the step direction selection function. Finally, the trained step direction selection function is used for topology path retrieval, To solve the problem of how to find the optimal topology connection in the process of automatic wiring of power flow diagram. The algorithm is simulated based on a 220 kV power grid, and the results show the effectiveness and feasibility of the proposed method. Compared with the traditional automatic mapping method, the proposed method does not need to manually adapt the coordinate calculation algorithm of topological connection according to different picture characteristics, and the training process does not need to rely on the existing power flow diagram samples, which can significantly improve the flexibility and accuracy of automatic mapping of power flow diagram.

关 键 词：潮流图 自动布线 自动成图 神经网络 拓扑训练 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TM73[自动化与计算机技术—控制科学与工程]