Identification of distribution network topology parameters based on multidimensional operation data

• Main Authors: Jiaqiao Li, Di Wu, Weichao Jin, Zhenyue Chu, Shengyuan Liu, Jien Ma, Zhenzhi Lin, Li Yang
• Format: Article
• Language: English
• Published: Elsevier 2021-04-01
• Series: Energy Reports
• Subjects: Station–user relationship; Phase identification; t-Distributed Stochastic Neighbor Embedding; Principal Component Analysis; Local Outlier Factor; Spectral clustering
• Online Access: http://www.sciencedirect.com/science/article/pii/S2352484721000664

The connection relationship of distribution network topology is of great significance for the maintenance and fault diagnosis of distribution network, and scheduled power outage optimization. At present, the verification of topological documents mainly relies on on-site inspection, which consumes a lot of manpower and material resources and is inefficient. Therefore, an efficient method for topology verification of low-voltage substation areas is required. Given this background, a model for error correction and user access phase identification of low-voltage stations based on multi-dimensional voltage data collected by smart meters is presented in this paper, which can provide a certain reference for topology identification and line troubleshooting of low-voltage substations. First, the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm and the Principal Component Analysis (PCA) performs dimensionality reduction on the original load data to solve the problem of redundancy caused by the high dimension of the original voltage data set. Second, the Local Outlier Factor (LOF) algorithm is used to identify abnormal samples in the voltage data set. Then, the spectral clustering method is used to cluster the dimensionality-reduced load data to realize the phase identification of single-phase users in the low-voltage station area. Finally, the real data of a certain area in Haining, Zhejiang Province of China are used as simulation cases for demonstrating. The results of the case studies show that the model proposed in this paper is feasible and effective.