基于聚类算法的城市中压配电网接线模式识别

Connection pattern recognition of urban medium voltage distribution network integrated with clustering algorithm

接线模式识别是配电网规划的基础,对于保障配电网可靠、安全、经济运行具有重要意义。结合10kV城市中压配电网接线模式特点,提出一种基于深度优先搜索分析和聚类算法的接线模式识别方法。首先,采用深度优先搜索算法将一个完整配电网划分为若干馈线树,作为模式识别的基本对象;然后,针对各种10 kV交流电网、交直流混联电网等典型网架结构,分别提取接线模式特征指标并形成特征参数库;最后,利用聚类算法将未知待识别线路的特征与已知特征库进行匹配。算例仿真结果验证了所提特征指标的有效性,聚类方法能够实现中压配电网接线模式的准确识别。

Connection pattern recognition is the foundation of distribution system planning, and it is of great significance to ensure reliable, safe and economical operation of distribution network. Combined with the characteristics of 10 kV urban distribution network connection pattern, a connection pattern recognition method based on depth-first topology analysis and clustering algorithm is proposed. Firstly, a complete distribution network is divided into several feeder trees as the basic object of pattern recognition using depth-first search algorithm. Then, according to various 10 kV AC networks, AC-DC hybrid networks and other typical network structures, the typical connection mode features are extracted to form a feature parameter library. Finally, the clustering algorithm is used to match the features of the unknown lines with the feature database. The simulation results of an example verify the effectiveness of the proposed mode features, and the clustering algorithm can realize the accurate identification of urban distribution network connection pattern.