WaveTimes: Short-term Load Forecast Based on Wavelet Decomposition and Improved TimesNet

Short-term load forecasting (STLF) is an essential component of smart grids, enabling power departments to anticipate grid operations in advance, thereby controlling electricity usage in a timely manner, allocating power resources reasonably, and ensuring the quality and relia-bility of grid services. In the field of electric load forecasting, existing prediction models perform poorly on load data with frequent fluctua-tions and have issues with prediction lag. To address these issues, this paper proposes an improved TimesNet model based on wavelet de-composition, called WaveTimes. Firstly, the model uses wavelet decomposition to decompose load data, obtaining sequences with smaller mutation amplitudes and weaker autocorrelation. Secondly, a feature extraction module is introduced, which uses Fourier transformation and computer vision models for periodic analysis, effectively capturing periodic changes in load data across different frequency domains. Finally, a residual connection and prediction module are used to complete the forecasting task. This paper evaluates the proposed method on public datasets and load data from a certain province in China, showing significant improvements compared to the baseline. The model can more effectively support relevant departments in load control and demand response, contributing to the construction of smart grids.