AUTHOR=Ni Guofeng , Zhang Xiaoyuan , Ni Xiang , Cheng Xiaomei , Meng Xiangdong TITLE=A WOA-CNN-BiLSTM-based multi-feature classification prediction model for smart grid financial markets JOURNAL=Frontiers in Energy Research VOLUME=Volume 11 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1198855 DOI=10.3389/fenrg.2023.1198855 ISSN=2296-598X ABSTRACT=Smart grid financial market forecasting is an important topic in deep learning. The traditional LSTM network is widely used in time series forecasting because of its ability to model and predict time series data. However, in long-term series forecasting, the problem of missing historical data may lead to a decline in the forecasting effect, which is a difficult problem for traditional LSTM networks to overcome. We propose a new deep-learning model in this paper to solve this problem. This WOA-CNN-BiLSTM model combines the advantages of bidirectional long short-term memory network BiLSTM and convolutional neural network CNN. We use bidirectional long-term. The short-term memory network BiLSTM replaces the traditional LSTM network to take advantage of its ability to capture long-term dependencies in time series and bidirectional modelling. At the same time, we use a convolutional neural network (CNN) to extract features of time series data to better represent and capture patterns and regularities in the data. This method combining BiLSTM and CNN can learn the characteristics of time series data more comprehensively and accurately, thus improving prediction accuracy. Then, to further improve the performance of the CNN-BiLSTM model, we optimized the model using the whale algorithm WOA. This algorithm is an emerging optimization algorithm with excellent global search ability and convergence speed and can effectively avoid local optimal solutions. Optimizing the CNN-BiLSTM model through the WOA algorithm can reduce its calculation and training speed and improve the prediction accuracy of the smart grid financial market.Experimental results show that our proposed CNN-BiLSTM model has better prediction accuracy than other models and can effectively deal with the problem of missing historical data in long-term series forecasting. This provides essential help for developing the smart grid financial market and risk management services and can promote the development and growth of the smart grid industry. Our research results are of great significance in deep learning and provide an effective method and idea for solving the financial market forecasting problem of the smart grid.