Day-ahead power load forecasting based on Patch-LSTM-MLP

Day-ahead load forecasting belongs to short-term forecasting, which is the basis of new energy utilization as well as power system operation. The large-scale consumption of new energy and the uncertainty of the demand side bring new challenges to day-ahead load forecasting. Traditional recurrent neural networks have limitations in feature extraction capability and learning efficiency. In order to fully learn the features in the load data, we propose a model Patch-LSTM-MLP combining LSTM, patch technique and multilayer perceptron for day-ahead load forecasting. Patch-LSTM-MLP consists of two multilayer perceptron blocks and an LSTM model based on the novel patch technique. Specifically, the proposed model employs LSTM to capture the global temporal patterns of load sequences, and introduces local multilayer perceptron and variable multilayer perceptron to enhance the model's ability to capture local temporal patterns and correlations among variables. In this paper, two public load datasets are selected to validate the effectiveness of the proposed model, which provides new ideas for the application of recurrent networks in day-ahead load forecasting.