Voltage stability margin evaluation method and device based on improved Relief-F algorithm, and medium

• Main Authors: WANG NAN, ZHANG YUYUE, ZENG FANFEI, LIU ZHIPENG, ZHAO LONG, GAO XIAOHAI, WEI XIN, TIAN XIN, SHI BINGKE, MENG XIANGFEI, QIU XUANYU, WANG YAO, LI ZHE, YANG SI, WANG CHEN, ZHANG LINA, FU YIMU, YANG BIN, CHENG PEIFEN, WEI JIA, ZHANG DONGLIANG, YUAN ZHENHUA
• Format: Patent
• Language: Chinese; English
• Published: 01.11.2022
• 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; ELECTRICITY; GENERATION; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a voltage stability margin evaluation method and device based on an improved Relief-F algorithm, and a medium, and aims to solve the technical problem of system voltage instability caused by easy misjudgment when an existing method is used for evaluating a system voltage stability margin state. The method comprises the following steps: extracting a voltage stability margin evaluation rule according to a path structure of a pre-trained decision tree model; wherein a training sample set used for constructing the decision tree model is divided through a Relief-F algorithm in which a penalty factor is introduced, and the penalty factor is used for identifying heterogeneous labels to make up the inherent defects of the Relief-F algorithm and enhance the scene adaptability; and matching measured data acquired by a vector measurement unit with the voltage stability margin evaluation rule extracted by the decision tree model to obtain the current voltage stability state of the system. Accordin