Short-term power load forecasting using informer encoder and bi-directional LSTM

Abstract

An innovative model called InE-BiLSTM is proposed here, which combines the Informer Encoder with a bidirectional LSTM (Bi-LSTM) network. The goal is to enhance the precision and efficacy of short-term electricity load forecasting. By integrating the long-term dependency capturing capability of the informer encoder with the advantages of Bi-LSTM in handling dynamic features in time series data, the InE-BiLSTM model effectively addresses complex patterns and fluctuations in electricity load data. The study begins by analyzing the current state of short-term electricity load forecasting, followed by a detailed introduction to the structure and principles of the InE-BiLSTM model. Results of the experiment demonstrate that, compared to the Informer, traditional Bi-LSTM, and Transformer models, the InE-BiLSTM model consistently outperforms them across various evaluation metrics.