Electric Power ›› 2024, Vol. 57 ›› Issue (6): 193-203.DOI: 10.11930/j.issn.1004-9649.202306073

• Technology and Economics • Previous Articles     Next Articles

An Evaluation Method for Distribution Network Operation Based on Multi-source Data Deep Fusion

Junfeng QIAO1(), Aihua ZHOU1(), Lin PENG1(), Yiqing WANG2(), Xiaofeng SHEN3, Sen PAN1, Pei YANG1, Chenhong HUANG3   

  1. 1. State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology, State Grid Smart Grid Research Institute Co., Ltd., Nanjing 210003, China
    2. Xuzhou Power Supply Company, State Grid Jiangsu Electric Power Co., Ltd., Xuzhou 221005, China
    3. Qingpu Power Supply Company, State Grid Shanghai Municipal Electric Power Company, Shanghai 201799, China
  • Received:2023-06-21 Accepted:2023-09-19 Online:2024-06-23 Published:2024-06-28
  • Supported by:
    This work is supported by Science and Technology Project of SGCC (Research on Deep Data Fusion and Resource Sharing Technology for New Distribution Networks, No.5400-202258431A-2-0-ZN).

Abstract:

As the last link in the power supply process, the distribution network determines the quality of power supply services by its operational level. Scientific evaluation of the distribution network’s operational level is thus an important task for power supply companies. However, the existing evaluation methods are difficult to implement and apply due to the fact that the multi-source data are hard to be fused and the evaluation indicators are poor in reflecting the actual operation status of the distribution network. To address above-said problem, this paper proposes an evaluation method for distribution network operation based on multi-source data deep fusion. Firstly, the regional distribution network is divided into multiple grids, and then the address gradation based matching algorithm is used to fuse multi-source heterogeneous data. Based on the results, the distribution network operation evaluation index system is designed and a distribution network operation comprehensive evaluation model based on multi-layer weight constraints is constructed to obtain the distribution network comprehensive evaluation results. Finally, a distribution network operation evaluation system is developed to support the unified access of multi-source heterogeneous data from various business systems of the distribution network, achieving the visualization and intelligent application of distribution network evaluation functions. The proposed distribution network operation evaluation system is connected to the data center of a provincial power grid company for verification, and the accuracy and applicability of the proposed method have been verified with actual operation data.

Key words: distribution network operation evaluation, grid partitioning, deep data fusion, evaluation index system, evaluation verification