电力建设2025，Vol.46Issue(11)：35-46,12.DOI:10.12204/j.issn.1000-7229.2025.11.004
基于雾计算负荷预测的低压无源台区故障自愈重构恢复策略
Post-fault Self-healing Reconfiguration Strategy for Low-Voltage Passive Station Areas Based on Fog Computing Load Prediction
摘要
Abstract
[Objective]To improve the intelligence level of fault recovery in low-voltage substations,a low-voltage passive substation post-fault self-healing strategy based on fog computing load prediction was proposed for the problem of low-voltage substation fault recovery.[Methods]First,to avoid equipment overload caused by network reconstruction,the load level of the network must be determined in advance.Combining the typical structure of low-voltage passive substations and the characteristics of fog computing communication architecture,a fog computing ultra-short-term load prediction method based on the dynamic aggregation of an incremental learning model was designed.This method embedded two ultrashort-term load prediction technologies with complementary characteristics.It used a real-time load for model incremental learning in a dynamic weighted manner and rapidly predicted low-voltage loads in a fault event-triggered manner.In addition,based on the proposed fog computing load prediction,a low-voltage passive substation switch reconstruction self-healing recovery model without line parameters was proposed and modeled as a mixed-integer quadratic programming problem.[Results]The simulation results showed that the average absolute scale-free error of the proposed fog computing load prediction was mainly affected by the load mutation that could be controlled between 5 and 40,and the relative error was between 1%and 8%.[Conclusions]The proposed post-fault self-healing strategy effectively completed the transfer of single-phase loads and maintained the inter-phase load balance as much as possible,while maintaining the radial network operation and avoiding equipment overload.关键词
低压台区/故障自愈/雾计算/超短期负荷预测/混合整数二次规划Key words
low-voltage power station/fault recovery/fog computing/ultra-short-term load forecasting/mixed-integer quadratic programming分类
动力与电气工程引用本文复制引用
刘音,桂媛,刘若溪,宋一凡,高杨,杨雯沁,王越..基于雾计算负荷预测的低压无源台区故障自愈重构恢复策略[J].电力建设,2025,46(11):35-46,12.基金项目
国网北京市电力公司科技项目(低压配电网状态精准感知与故障快速自愈技术研究及应用)(52022324000F)This work is supported by the Science and Technology Project of State Grid Beijing Electric Power Company(No.52022324000F). （低压配电网状态精准感知与故障快速自愈技术研究及应用）
