Load Forecasting Method Based on Deep Learning-LSTM
Power load forecasting is crucial for the safe and stable operation of the power system,but due to its randomness,volatility,periodicity,and large amount of data,traditional simple forecasting methods can no longer guarantee its prediction accuracy.In this paper,firstly,the correlation factors of power load characteristics are analyzed to determine the input amount of power load prediction,and then the deep learning Long Short-Term Memory Network (LSTM) algorithm is used to predict the power load,and the LSTM algorithm is used to predict the power load error according to the error generated by the prediction results.The results of the two are superimposed to obtain the power load prediction results with dynamic error compensation.Finally,the measured power load data in a certain area is used as an example for verification,and the results show that the proposed method has higher prediction accuracy.
万方数据
维普
