Topology Identification of Low-Voltage Distribution Network Based on Deep Convolutional Time-Series Clustering

Abstract

Accurate topology relationships of low-voltage distribution networks are important for distribution network management. However, the topological information in Geographic Information System (GIS) systems for low-voltage distribution networks is prone to errors such as omissions and false alarms, which can have a heavy impact on the effective management of the networks. In this study, a novel method for the identification of topology relationships, including the user-transformer relationship and the user-phase relationship, is proposed, which is based on Deep Convolutional Time-Series Clustering (DCTC) analysis. The proposed DCTC method fuses convolutional autoencoder and clustering layers to perform voltage feature representation and clustering in a low-dimensional feature space simultaneously. By jointly optimizing the clustering process via minimizing the sum of the reconstruction loss and clustering loss, the proposed method effectively identifies the network topology relationships. Analysis of examples shows that the proposed method is correct and effective.

Modeling and Simulation of Distribution Networks with High Renewable Penetration in Open-Source Software: QGIS and OpenDSS

“…These tools facilitate the assessment, accurate representation and analysis of complex distribution networks facing increasing integration of renewable energy sources, allowing for the evaluation of various technical aspects such as voltage regulation, power quality, and system stability. Creating the possibility of conducting studies of the Dominican Republics' electrical grid with similar focus as the ones shown in [36][37][38].…”

Modeling and Simulation of Distribution Networks with High Renewable Penetration in Open-Source Software: QGIS and OpenDSS

“…These tools facilitate the assessment, accurate representation, and analysis of complex distribution networks facing increasing integration of renewable energy sources, allowing for the evaluation of various technical aspects such as voltage regulation, power quality, and system stability. This creates the possibility of conducting studies of the Dominican Republics' electrical grid with similar focus to the ones shown in [38][39][40].…”

Improved topology identification for distribution network with relatively balanced power supplies

“…The voltage of each node is related to the impedance parameters of the line and the customer's power consumption. The closer the node is to the transformer, the higher the Complex algorithms and relatively low accuracy [17,18] Voltage series High accuracy High data quantity requirements for learning, low interpretability [20] Active power Effective in incomplete measurement stations Dependence on large power fluctuations of customers [21,22] Energy/power Multi-level topology identification Complete measurement of network [23,24] Voltage and active power More distinguishing features and high accuracy Less effective for stations with a low degree of threephase unbalance voltage is, and the farther away the voltage is lower. Moreover, the active power of any upstream branch node P t busi in the line satisfies power balance:…”

“…[16] to identify the latent nodes in network. References [17,18] use machine learning approach to extract features by reducing the dimension of the voltage time series, and achieve station distinction and phase identification using feature clustering methods. The harmonic voltage correlation is proposed in Ref.…”