AUTHOR=Li Xuhan 

TITLE=CNN-GRU model based on attention mechanism for large-scale energy storage optimization in smart grid

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1228256

DOI=10.3389/fenrg.2023.1228256

ISSN=2296-598X

ABSTRACT=At present, Smart Grid (SG) technology has a wide range of applications that can improve the power system's reliability, economy, and sustainability. Optimizing large-scale energy storage technology for Smart Grids is an important topic in the field of optimizing Smart grids. A reasonable optimization scheme can be proposed by predicting the power system's historical load and price. Based on this, a prediction model combining a convolutional neural network (CNN) and gated recurrent unit (GRU) based on an attention mechanism is proposed in this paper for exploring the optimization scheme of large-scale energy storage in a smart grid. The CNN model can effectively extract the spatial features, and the GRU model can effectively solve the problems of gradient explosion in long-term prediction. Its structure is simplified and faster than the LSTM model, which has a similar prediction accuracy. After CNN-GRU extracts the data, the features are finally weighted by the attention module to further improve the model's prediction performance. Then, we also compared different prediction models. The results show that our model has better prediction performance and computing power, an important contribution to developing large-scale energy storage optimization schemes for smart grids.