Multiscale-integrated deep learning approaches for short-term load forecasting

• Published in: International journal of machine learning and cybernetics Vol. 15; no. 12; pp. 6061 - 6076
• Main Authors: Yang, Yang, Gao, Yuchao, Wang, Zijin, Li, Xi’an, Zhou, Hu, Wu, Jinran
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2024; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Alternative energy sources; Artificial Intelligence; Artificial neural networks; Complex Systems; Computational Intelligence; Control; Decomposition; Deep learning; Energy consumption; Engineering; Forecasting; Fourier transforms; Machine learning; Mechatronics; Neural networks; Original Article; Pattern Recognition; Regression analysis; Renewable resources; Robotics; Statistical methods; Systems Biology; Time series; Trends; Deep learning; Outliers; Load forecasting; Robust regression; Time series decomposition
• ISSN: 1868-8071; 1868-808X
• DOI: 10.1007/s13042-024-02302-4

Accurate short-term load forecasting (STLF) is crucial for the power system. Traditional methods generally used signal decomposition techniques for feature extraction. However, these methods are limited in extrapolation performance, and the parameter of decomposition modes needs to be preset. To end this, this paper develops a novel STLF algorithm based on multi-scale perspective decomposition. The proposed algorithm adopts the multi-scale deep neural network (MscaleDNN) to decompose load series into low- and high-frequency components. Considering outliers of load series, this paper introduces the adaptive rescaled lncosh (ARlncosh) loss to fit the distribution of load data and improve the robustness. Furthermore, the attention mechanism (ATTN) extracts the correlations between different moments. In two power load data sets from Portugal and Australia, the proposed model generates competitive forecasting results.