Electrical load forecasting based on variable T-distribution and dual attention mechanism

• Published in: Energy (Oxford) Vol. 283; p. 128569
• Main Authors: Wang, Jianguo, Han, Lincheng, Zhang, Xiuyu, Wang, Yingzhou, Zhang, Shude
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 15.11.2023
• Subjects: Bayesian hyperparameter optimization; Dual attention mechanism; load forecasting; Periodicity detection; Variable t-distribution; Periodicity detection; Bayesian hyperparameter optimization; Dual attention mechanism; load forecasting; Variable t-distribution
• ISSN: 0360-5442
• DOI: 10.1016/j.energy.2023.128569

Accurate load forecasting is essential for power system stability and grid dispatch optimization. However, this task is challenging due to the inherent instability and volatility of the load sequence. To address this problem, this paper proposes a novel load forecasting model that integrates periodicity detection, the variable t-distribution, and the dual attention mechanism. Periodicity detection has been incorporated into the self-attention mechanism for the first time, identifying the most significant period in the raw load sequence. Subsequently, the raw load sequence undergoes processing using empirical wavelet transform, resulting in a series of subsequences. A feature attention mechanism is then employed to extract relevant input features. Furthermore, a novel variable t-distribution distance matrix is introduced into the temporal self-attention mechanism, enhancing the influence of data at identical or nearby positions in other periods based on the length of the most significant period. This modification improves the capacity of the vanilla self-attention mechanism to effectively model the relationship between data at varying distances. The hyperparameters of the variable t-distribution are obtained through Bayesian hyperparameter optimization. Empirical evaluations on two datasets with distinct meteorological and load features show that the proposed model outperforms baseline models across all metrics. © 2017 Elsevier Inc. All rights reserved. •Novel load forecasting model integrating periodicity detection, variable t-distribution, and dual-attention mechanism.•Incorporation of the most significant period into the self-attention mechanism.•Empirical wavelet transform of raw load sequence extracts informative subsequences.•Feature attention mechanism dynamically extracting relevant input features.•Introduction of variable t-distribution distance matrix for improved modeling of data relationships at varying distances.