Rural multi-element load multi-time scale prediction method

• Main Authors: LIU JUNHUI, LU YAO, LI HUIXUAN, ZHENG YONGLE, ZU WENJING, CAI SHUYAO, LI PENG, YANG MENG, ZHANG YIHAN, XIE ANBANG, CHAI ZHE, CHEN XING, ZHANG HONGKAI
• Format: Patent
• Language: Chinese; English
• Published: 03.05.2024
• 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 relates to a rural multi-element load multi-time scale prediction method. The method comprises the following steps: step 1, constructing a distributed user cluster medium-short term load prediction model based on an adaptive time-space synchronization graph convolutional neural network; 2, predicting the power of the rural distributed renewable energy sources; step 3, performing rural distributed source load integrated prediction; the method has the advantages that the user cluster short-term load prediction model is constructed, multi-time scale load prediction is realized, and the new energy output prediction accuracy is improved. 本发明涉及乡村多元负荷多时间尺度预测方法，所述的方法包括以下步骤：步骤1：构建基于自适应时空同步图卷积神经网络的分布式用户集群中短期负荷预测模型；步骤2：乡村分布式可再生能源功率预测；步骤3：乡村分布式源荷集成预测；本发明具有构建用户集群短期负荷预测模型、实现多时间尺度负荷预测、提高新能源出力预测准确性的优点。