| 引用本文: | 陈招安,黄 纯,张志丹,江亚群.基于T型灰色关联度和KNN算法的低压配电网台区拓扑识别方法[J].电力系统保护与控制,2021,49(1):163-169.[点击复制] |
| CHEN Zhaoan,,HUANG Chun,et al.Topology identification method of a low voltage distribution network based on T-type grey correlation degree and KNN algorithm[J].Power System Protection and Control,2021,49(1):163-169[点击复制] |
|
| 摘要: |
| 针对目前低压配电网台区拓扑存在记录不准确，人工排查成本高，准确率低的问题。提出了一种基于T型灰色关联度和K-最近邻(K-nearest Neighbor, KNN)算法的低压配电网拓扑自动识别方法。首先计算用户与所属台区电压的T型灰色关联度，对低于设定阈值的可疑用户用KNN算法判断所属台区，完成户变关系识别工作。然后计算新户变关系下用户之间电压的T型灰色关联度，结合拓扑结构图识别馈线中的可疑用户。最后找出与可疑用户最相关的用户，依据电压沿着馈线逐渐降低定位可疑用户在馈线中的位置。算例分析结果表明，该方法能自动识别用户所属台区和馈线，准确率高，实用性好。 |
| 关键词: 低压配电网 拓扑结构 T型灰色关联度 KNN算法 台区 |
| DOI：DOI: 10.19783/j.cnki.pspc.200260 |
| 投稿时间：2020-03-31修订日期：2020-06-06 |
| 基金项目:国家自然科学基金项目资助(51677060)；国网湖南省电力公司科技项目资助(5216A518000T) |
|
| Topology identification method of a low voltage distribution network based on T-type grey correlation degree and KNN algorithm |
| CHEN Zhaoan,,HUANG Chun,,ZHANG Zhidan,,JIANG Yaqun |
| (1. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China;
2. Electric Power Research Institute of State Grid Hunan Electric Power Company, Changsha 410007, China) |
| Abstract: |
| There are errors in the topology record of the low-voltage distribution network, and its manual verification has high cost and low accuracy. An automatic topology identification method of a low-voltage distribution network based on T-type grey correlation degree and the K-Nearest Neighbor (KNN) algorithm is proposed. First, the T-type grey correlation degrees of the voltages between the users and the station area are calculated, and the KNN algorithm is used to judge the suspicious users of a station area by the set threshold value to identify the relationship between the user and the station area. Then, the T-type grey correlation degrees between user voltages are calculated under the new station area, and the suspicious users in the feeder are identified by the topological structure diagram. Finally, the users related to the suspicious users are found, and the location of the suspicious users in the feeder is located according to the characteristic that the voltage decreases gradually along the feeder. The results of case analysis show that the proposed method can automatically identify the user's station area and feeder line with high accuracy and good practicability.
This work is supported by National Natural Science Foundation of China (No. 51677060) and Science and Technology Project of Hunan Electric Power Company (No. 5216A518000T). |
| Key words: low voltage distribution network topology T-type grey correlation degree KNN algorithm station area |
