Enhanced Short-Term Load Forecasting Based on Adaptive Residual Fusion of Autoformer and Transformer
Open Access
Abstract
Accurate short-term electricity load forecasting (STELF) is essential for grid scheduling and low-carbon smart grids. However, load exhibits multi-timescale periodicity and non-stationary fluctuations, making STELF highly challenging for existing models. To address this challenge, an Autoformer–Transformer residual fusion network (ATRFN) is proposed in this paper. A dynamic weighting mechanism is applied to combine the outputs of Autoformer and Transformer through residual connections. In this way, lightweight result-level fusion is enabled without modifications to either architecture. In experimental validations on real-world load datasets, the proposed ATRFN model achieves notable performance gains over single STELF models. For univariate STELF, the ATRFN model reduces forecasting errors by 11.94% in mean squared error (MSE), 10.51% in mean absolute error (MAE), and 7.99% in mean absolute percentage error (MAPE) compared with the best single model. In multivariate experiments, it further decreases errors by at least 5.22% in MSE, 2.77% in MAE, and 2.85% in MAPE, demonstrating consistent improvements in predictive accuracy.Keywords
Funding Information
- Science and Technology Project of China Southern Power Grid Co., Ltd. (210000KC24060044)
This publication has 39 references indexed in Scilit:
- Research on the application of an improved Autoformer model integrating CNN-attention-BiGRU in short-term power load forecastingEvolving Systems, 2025
- Short-time photovoltaic power forecasting based on Informer model integrating Attention MechanismApplied Soft Computing, 2025
- Intra and inter-series pattern representations fusion network for multiple time series forecastingApplied Soft Computing, 2025
- Leveraging LSTM-SMI and ARIMA architecture for robust wind power plant forecastingApplied Soft Computing, 2025
- A double-layer forecasting model for PV power forecasting based on GRU-Informer-SVR and Blending ensemble learning frameworkApplied Soft Computing, 2025
- A power load forecasting method in port based on VMD-ICSS-hybrid neural networkApplied Energy, 2024
- Multi-step electric vehicles charging loads forecasting: An autoformer variant with feature extraction, frequency enhancement, and error correction blocksApplied Energy, 2024
- A Multi-strategy Improved Sparrow Search Algorithm and its ApplicationNeural Processing Letters, 2023
- An adaptive deep-learning load forecasting framework by integrating transformer and domain knowledgeAdvances in Applied Energy, 2023
- Hybrid short-term load forecasting using CGAN with CNN and semi-supervised regressionApplied Energy, 2023