Load prediction method and system suitable for power dispatching equipment in small energy utilization place

• Main Authors: JI RUNDONG, GUO RENWEI, JI JIE, SU JIAOYUE, TANG JIANKANG, WANG FUCHENG, ZHOU MENGXIONG
• Format: Patent
• Language: Chinese; English
• Published: 03.03.2023
• 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; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a load prediction method suitable for power dispatching equipment in a small energy utilization place, and the method comprises the steps: collecting the short-term historical load data of the dispatching equipment in the small energy utilization place, forming a data set, and dividing the data set into a training data set and a test data set; constructing an electrical load grey neural network prediction model, optimizing the electrical load grey neural network prediction model by adopting an improved genetic algorithm, and performing continuous training by adopting the training data set until an optimal prediction model is achieved; calculating a load prediction result corresponding to the test data set according to the optimal prediction model; and according to the obtained load prediction result, performing intelligent regulation and control on the electric equipment in the small energy utilization place. According to the combined prediction model, compared with a single prediction