Power distribution network fault self-recovery method and system based on machine learning

• Main Authors: QIU JUNQI, ZHANG LIHANG, LIN XIONGFENG, LU XIAOHAI, ZHANG TUO, LI SHENGYUN
• Format: Patent
• Language: Chinese; English
• Published: 31.10.2023
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a power distribution network fault self-recovery method and system based on machine learning, and belongs to the technical field of power distribution network fault self-recovery. According to the invention, the information of a plurality of lines and devices in the power distribution network before and after the fault occurs is collected, the information of the trunk line is extracted, and then the information of the trunk line is standardized, so that different devices have the same standardized information. The method comprises the following steps: firstly, carrying out machine learning-based fault identification model training by using a large amount of standardized equipment information and fault point information on a line, and finally, carrying out power restoration again by using a fault point position identified by a fault identification model and corresponding interconnection switch information when the power restoration of the main line fails by adopting a traditional self-he