In order to improve the accuracy of load forecasting in distribution network demand side,a multi-level load forecas-ting method based on grey clustering model and active demand management technology is proposed.A grey clustering model is used to perform feature clustering on demand side load data,the normalized average residual value is calculated to obtain se-quence grey correlation degree,and the feature clustering is completed.The restricted Boltzmann machine(RBM)is used as the basic structure for training to obtain the optimal prediction parameters.The prediction process is designed by using long and short-term memory(LSTM)network to complete multi-level load forecasting on the distribution network demand side.The ex-ample analysis results show that the mean absolute percentage error(MAPE)of the 7-day load prediction results obtained un-der the application of the load prediction method is 201.8 MW,and the root mean square error(RMSE)is 2.1020％.
关键词
灰色聚类模型/主动需求管理技术/多级负荷预测/特征聚类/无监督训练
Key words
grey clustering model/active demand management technology/multi-level load forecasting/feature clustering/un-supervised training
维普
万方数据