Figure - available from: Soft Computing
This content is subject to copyright. Terms and conditions apply.
Source publication
Network topology is essential for the safe operation of a low-voltage (LV) distribution network. This network connectivity is difficult to obtain accurately due to the complex structure and low level of automation. In this paper, we first propose a four-level topology (which includes transformer, outlet cabinet, branch box, meter box) automatic ide...
Citations
... Among them, reference [20] proposes a single-phase user phase identification method based on saliency analysis of customer power, which searches for the correlation between customers and feeders during periods when customer power fluctuates significantly. Reference [21,22] use regression analysis based on the energy and power balance principles to determine the connection relationship between nodes. Some scholars combine voltage and power data. ...
Having correct distribution network topology information is essential for system state estimation, line loss analysis, electricity theft detection and fault location. At present, with continuous deployment of smart sensors, a large amount of monitoring data is collected, which enables refined management for distribution network. A data‐driven low voltage (LV) distribution network topology identification method is proposed, which realises transformer‐customer pairing and customer phase identification for distribution network with relatively balanced power supplies. Firstly, an integrated similarity coefficient of voltage curve is proposed, which can reflect the neighbourhood relationship within stations while increase the distinction between stations; the K‐Nearest Neighbour (KNN) algorithm is used to propagate the service transformer labels to complete transformer‐customer association. Then, the influence of power fluctuation on voltage curve is analysed and a dynamic sliding window model is adopted to search for voltage segments with significantly difference among three phase feeders to formulate a voltage time series to identify customer phase. Finally, the results are corrected and verified based on the principle of network power balance. The proposed algorithm is tested in two different real substations in China and Europe and shows high accuracy and robustness especially in distribution network with relatively balanced power supplies.
The information of a low-voltage (LV) distribution network is important for power supply departments to monitor grid information, analyze faults and optimize grid operation status. However, the current mainstream methods are not able to comprehensively update the topology information of LV distribution networks in real time. Therefore, this paper proposes an unsupervised learning and graph theory-based method to identify four-level topology information and generate a topology diagram for low-voltage distribution network. Firstly, four-level topology information are identified based on the tSNE-DBSCAN-LLE algorithm. Then, the identied information is used to simply generate a topology diagram. Finally, the simulation data and the actual data from three LV distribution networks are analyzed to show the effectiveness and advantageousness of the proposed method.
