AUTHOR=Zhong Bin TITLE=Deep learning integration optimization of electric energy load forecasting and market price based on the ANN–LSTM–transformer method JOURNAL=Frontiers in Energy Research VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1292204 DOI=10.3389/fenrg.2023.1292204 ISSN=2296-598X ABSTRACT=As the complexity of power energy systems continues to increase and market prices fluctuate, power load forecasting and market price analysis have become particularly critical in the energy and financial fields. The application of deep learning technology in the field of time series forecasting has aroused widespread interest, and more and more scholars are introducing deep learning technology into the research of power energy forecasting. This article aims to improve the accuracy and reliability of power load and market price predictions by integrating and optimizing deep learning models. We propose a deep learning framework based on the ANN-LSTM-Transformer model to solve the problem of electricity load and market price prediction. First, we use the versatility of artificial neural networks (ANN) and the sequence modeling capabilities of long short-term memory networks (LSTM) to fuse multi-source data to obtain initial prediction results. Next, we introduce Transformer technology and use its selfattention mechanism to capture long-distance dependencies in the data to further optimize model performance.In experiments, we validate using multiple public datasets and compare our method with other traditional methods and a single model, and the results show that our method achieves better performance in power load and market price prediction. This more accurate and reliable forecasting framework could provide value to decision makers in the energy sector.