A Medium and Long-term Forecasting Method for Electric Load Curves Integrating Dynamic Variable Selection and Sparse Attention Mechanism
DOI:
https://doi.org/10.4108/ew.12161Keywords:
electric load curve forecasting, medium and long-term prediction, dynamic variable selection, sparse attention mechanism, power system planningAbstract
Accurate forecasting of electric load curves is critical for stable power system operation, efficient dispatch, and scientific planning, with medium- and long-term forecasting providing key support for grid expansion, energy allocation, and electricity market decisions. Existing methods struggle with insufficient use of load-related multi-variable data and inefficient extraction of long-term temporal features from load measurements, limiting forecasting accuracy and efficiency. To address these issues, this paper proposes a medium- and long-term electric load curve forecasting model integrating dynamic variable selection and a sparse attention mechanism, with a focus on load measurement correlation. The model takes static variables and temporal variables related to load changes as inputs. Static variables include industry type and location, and temporal variables cover historical load and meteorological data. It uses a gated feedforward network to adaptively weight variables based on their correlation with actual load measurements and filters redundant information. Meanwhile, it adopts a dual-layer encoding structure with sparse attention to prioritize key features from long load measurement sequences, reducing computational complexity while enhancing capture of long-term dependencies between historical load measurements and future loads. Experiments on three datasets show the model outperforms baselines including Informer, Autoformer and TFT. The proposed model reduces average relative error by 14.3%–55.1% and improves computational efficiency, providing reliable technical support for power system medium- and long-term planning by closely linking load measurements to forecasting performance.
Downloads
References
[1] Nti I K, Teimeh M, Nyarko-Boateng O, et al. Electricity load forecasting: a systematic review[J]. Journal of Electrical Systems and Information Technology, 2020, 7(1): 13.
[2] Khuntia S R, Rueda J L, van Der Meijden M A M M. Forecasting the load of electrical power systems in mid‐and long‐term horizons: a review[J]. IET Generation, Transmission & Distribution, 2016, 10(16): 3971-3977.
[3] Aditya T, Jaipuria S, Kumar Dadabada P. A Review of Methods for Long‐Term Electric Load Forecasting[J]. Journal of Forecasting, 2025, 44(4): 1403-1423.
[4] Wang H, Zhang N, Du E, et al. A comprehensive review for wind, solar, and electrical load forecasting methods[J]. Global Energy Interconnection, 2022, 5(1): 9-30.
[5] Liu D, Wang H. Time series analysis model for forecasting unsteady electric load in buildings[J]. Energy and Built Environment, 2024, 5(6): 900-910.
[6] Gasparin A, Lukovic S, Alippi C. Deep learning for time series forecasting: The electric load case[J]. CAAI Transactions on Intelligence Technology, 2022, 7(1): 1-25.
[7] Madhukumar M, Sebastian A, Liang X, et al. Regression model-based short-term load forecasting for university campus load[J]. IEEE Access, 2022, 10: 8891-8905.
[8] Mladenov V, Chobanov V, Georgiev A. Impact of renewable energy sources on power system flexibility requirements[J]. Energies, 2021, 14(10): 2813.
[9] Lin J, Ma J, Zhu J, et al. Short-term load forecasting based on LSTM networks considering attention mechanism[J]. International Journal of Electrical Power & Energy Systems, 2022, 137: 107818.
[10] Mounir N, Ouadi H, Jrhilifa I. Short-term electric load forecasting using an EMD-BI-LSTM approach for smart grid energy management system[J]. Energy and Buildings, 2023, 288: 113022.
[11] Cordeiro-Costas M, Villanueva D, Eguía-Oller P, et al. Load forecasting with machine learning and deep learning methods[J]. Applied Sciences, 2023, 13(13): 7933.
[12] Aslam S, Herodotou H, Mohsin S M, et al. A survey on deep learning methods for power load and renewable energy forecasting in smart microgrids[J]. Renewable and Sustainable Energy Reviews, 2021, 144: 110992.
[13] Wan A, Chang Q, Khalil A L B, et al. Short-term power load forecasting for combined heat and power using CNN-LSTM enhanced by attention mechanism[J]. Energy, 2023, 282: 128274.
[14] Xu H, Hu F, Liang X, et al. A framework for electricity load forecasting based on attention mechanism time series depthwise separable convolutional neural network[J]. Energy, 2024, 299: 131258.
[15] Niu D, Yu M, Sun L, et al. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism[J]. Applied Energy, 2022, 313: 118801.
[16] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. Advances in neural information processing systems, 2017, 30.
[17] Fan C, Zhang Y, Pan Y, et al. Multi-horizon time series forecasting with temporal attention learning[C]//Proceedings of the 25th ACM SIGKDD International conference on knowledge discovery & data mining. 2019: 2527-2535.
[18] Xurui H, Fengyuan Y, Bo Y. Short-term Electric-thermal Load Forecasting Method of Campus Integrated Energy System Based on Transformer Network and multi-task Learning [J][J]. China Southern Power Grid Technology, 2023, 17(01): 152-160.
[19] Baozhong T I, Gengyin L I, Zhaoyuan W U. A short-term load forecasting method based on recurrent and dilated mechanism of ConvGRU-transformer[J]. Journal of North China Electric Power University, 2022, 49(03): 34-43.
[20] Shen L, Wang Y. TCCT: Tightly-coupled convolutional transformer on time series forecasting[J]. Neurocomputing, 2022, 480: 131-145.
[21] Zhao G, Lin J, Zhang Z, et al. Explicit sparse transformer: Concentrated attention through explicit selection[J]. arXiv preprint arXiv:1912.11637, 2019.
[22] Zhou H, Zhang S, Peng J, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI conference on artificial intelligence. 2021, 35(12): 11106-11115.
[23] Wu H, Xu J, Wang J, et al. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in neural information processing systems, 2021, 34: 22419-22430.
[24] Lim B, Arık S Ö, Loeff N, et al. Temporal fusion transformers for interpretable multi-horizon time series forecasting[J]. International journal of forecasting, 2021, 37(4): 1748-1764.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bingqian Chen, Jinlin Liao, Shiyuan Ni, Sudan Lai
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
