Research on Short Term Power Load Forecasting Based on AHP-K-Means-LSTM Model
In order to further improve the prediction performance,this paper proposes a short-term load forecasting method using the AHP-K-Means-LSTM combination model from the dimensions of weight and clustering.Firstly,the Analytic Hierarchy Process(AHP)is used to calculate the weights of factors that affect load forecasting.The improved K-Means clustering algorithm is combined to select the most effective clustering results from the samples.Then,the sample is brought into the Long Short-Term Memory(LSTM)neural network model for training,and the output results are compared and analyzed with the actual load.Taking the 2022 electricity load dataset in Shenyang of Liaoning Province as an example for simulation verification,the results of which show that the proposed method has improved load forecasting accuracy compared to traditional methods in working days and holidays in different seasons.
short term load forecastingbig data analysisAnalytic Hierarchy ProcessK-Means clusteringLSTM neural network
万方数据
维普
