Power system state estimation method and system based on hyper-parameter particle swarm optimization

• Main Authors: LI ZHENGSHUO, WANG XUZHUO, YU PENG
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention belongs to the technical field of power systems, and particularly relates to a power system state estimation method and system based on hyper-parameter particle swarm optimization, and the method comprises the steps: obtaining historical power data; according to the obtained data and a preset electric power system state estimation model, state estimation of the electric power system is completed; wherein the preset power system state estimation model adopts a double-layer hyper-parameter simulation optimization model, an upper-layer model of the double-layer hyper-parameter simulation optimization model adopts a mean square error function of a power data state quantity, and a lower-layer model of the double-layer hyper-parameter simulation optimization model adopts an exponential target function state estimation model; and taking the window width of the exponential target function state estimation model as a hyper-parameter, carrying out iterative solution on the double-layer hyper-parameter sim