TimesNet Model for Multi-industry Electricity Demand Forecasting

Accurately predicting electricity demand is of crucial importance for optimizing power resource allocation, improving grid operation safety and providing significant economic benefits. In recent years, deep learning models have been widely employed in time series analysis tasks, such as recurrent neural networks (RNNs), gradient boosting decision trees (GBDT), and transformer networks. However, these methods only focus on a single time dimension. For a specific periodic process, the temporal variations at each time point within the process are not only related to neighboring moments but also highly correlated with neighboring periods, exhibiting both intraperiod and interperiod temporal changes. In this study, we propose the TimesNet temporal forecasting model and conduct experiments using electricity consumption data from the A city, combined with a series of covariates such as temperature and holidays, to train the model and predict electricity consumption. We compare the performance of TimesNet with other methods, and the results demonstrate that the TimesNet model outperforms the other models. Overall, the hybrid model we propose provides a valuable framework for accurately predicting electricity demand and holds practical significance for managing and operating power grids in urban areas.