Dynamic Spatial-Temporal Load Forecasting for Multi-Regional Power Systems via Graph Attention Networks
DOI:
https://doi.org/10.4108/ew.11818Keywords:
Decoupling, Generative Adversarial Networks, Graph Attention Networks, Multi-Region Load ForecastingAbstract
Accurate multi-region load forecasting (MRLF) can effectively ensure the stable operation of the power system and is essential for the economic dispatch of the power system. However, with the gradual deepening of the dynamic spatial dependence among multi-region loads and the unmeasured nature of loads, the challenge is posed to MRLF. To address this challenge, a graph attention learning-based load forecasting model for multi-region considering dynamic spatial correlations aggregation is presented in this paper. Firstly, the regional load series is decomposed into a trend component and a fluctuation component through the discrete wavelet transform. Secondly, a generative adversarial network with the concept of zero-sum game is proposed for adversarial training of spatio-temporal prediction models. Furthermore, reasonable future multi-regional load forecasting values are obtained through a aggregation module that aggregate the trend component and the fluctuation component. Finally, the multi-regional load data of the New York Independent System Operator (NYISO) is used as a case. Compared with the evaluation metrics of mainstream models, the model presented in this paper is effective and superior in MRLF.
Downloads
References
[1] V. Dordonnat, A. Pichavant, A. Pierrot, “GEFCom2014 probabilistic electric load forecasting using time series and semi-parametric regression models,” International Journal of Forecasting, vol. 32, no. 3, pp. 1005-1011, Jul. 2016.
[2] J. W. Taylor and P. E. McSharry, “Short-Term Load Forecasting Methods: An Evaluation Based on European Data,” IEEE Transactions on Power Systems, vol. 22, no. 4, pp. 2213-2219, Nov. 2007.
[3] Rehan Jamil, “Hydroelectricity consumption forecast for Pakistan using ARIMA modeling and supply-demand analysis for the year 2030,” Renewable Energy, vol. 154, pp. 1-10, Jul. 2020.
[4] Saadat Bahrami, Rahmat-Allah Hooshmand, Moein Parastegari, “Short term electric load forecasting by wavelet transform and grey model improved by PSO (particle swarm optimization) algorithm,” Energy, vol. 72, pp. 434-442, Aug. 2014.
[5] Juan F. Rendon-Sanchez, Lilian M. de Menezes, “Structural combination of seasonal exponential smoothing forecasts applied to load forecasting,” European Journal of Operational Research, vol. 275, no. 3, pp. 916-924, Jun. 2019.
[6] Zhining Cao, Jianzhou Wang, Yurui Xia, “Combined electricity load-forecasting system based on weighted fuzzy time series and deep neural networks,” Engineering Applications of Artificial Intelligence, vol. 132, pp. 108375, Jun. 2024.
[7] Hui Hou et al., “Review of load forecasting based on artificial intelligence methodologies, models, and challenges,” Electric Power Systems Research, vol. 210, pp. 108067, Sep. 2022.
[8] J. Wang et al., “An annual load forecasting model based on support vector regression with differential evolution algorithm,” Applied Energy, vol. 94, pp. 65-70, Jun. 2012.
[9] Y. Özüpak and S. Mansurov, "Optimizing electricity demand forecasting with a novel RNN-LSTM hybrid model," Energy Sources, Part B: Economics, Planning, and Policy, vol. 20, no. 1, Art no. 2531448, 2025.
[10] J. Sun, K. Ma and H. Zhao, "Short-term power load hybrid forecasting using GRU and SCN," Energy and Buildings, vol. 347, no. Part B, pp. 116372, 2025.
[11] H. Han, J. Peng, J. Ma, H. Liu and S. Liu, "Research on Load Forecasting Prediction Model Based on Modified Sand Cat Swarm Optimization and SelfAttention TCN," Symmetry, vol. 17, pp. 1270, 2025.
[12] Y. Wang, T. Han, L. Rui, J. Ma and Q. Jin, "Ego-centric multiple-correlation and temporal graph neural networks based residential load forecasting," Engineering Applications of Artificial Intelligence, vol. 160, no. Part B, pp. 111933, 2025.
[13] D.A.G. Vieira et al., “Large scale spatial electric load forecasting framework based on spatial convolution,” International Journal of Electrical Power & Energy Systems, vol. 117, pp.105582, May. 2020.
[14] W. Lin, D. Wu and B. Boulet, “Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks,” IEEE Transactions on Smart Grid, vol. 12, no. 6, pp. 5373-5384, Nov. 2021.
[15] J. Liu et al., “Load forecasting based on dynamic adaptive and adversarial graph convolutional networks,” Energy and Buildings, vol. 312, pp. 114206, Jun. 2024.
[16] Y. Zhou and M. Wang, "Empower Pre-Trained Large Language Models for Building-Level Load Forecasting," in IEEE Transactions on Power Systems, vol. 40, no. 5, pp. 4220-4232, Sept. 2025
[17] Y. Liu, Y. Wang, P. Xu, Y. Xue, Y. Chen and D. Zhang, "BuildSTG: A multi-building energy load forecasting method using spatio-temporal graph neural network," Energy and Buildings, vol. 347, no. Part B, pp. 116190, 2025.
[18] G. Fan, H. Wei, H. Huang and W. Hong, "Application of ensemble empirical mode decomposition with support vector regression and wavelet neural network in electric load forecasting," Energy Sources, Part B: Economics, Planning, and Policy, vol. 20, no. 1, 2025.
[19] B. Sun, X. Chen, T. Shen and L. Ma, "Enhancing long-term load forecasting with convolutional informer-based hybrid model," Engineering Applications of Artificial Intelligence, vol. 161, no. Part A, pp. 112051, 2025.
[20] H. Dong, J. Zhu, S. Li, Y. Miao, C. Y. Chung and Z. Chen, "Probabilistic Residential Load Forecasting with Sequence-to-Sequence Adversarial Domain Adaptation Networks," in Journal of Modern Power Systems and Clean Energy, vol. 12, no. 5, pp. 1559-1571, September 2024.
[21] X. Ouyang et al., “CityTrans: Domain-Adversarial Training With Knowledge Transfer for Spatio-Temporal Prediction Across Cities,” IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 1, pp. 62-76, Jan. 2024.
[22] H. Zhang, M. Zhou, Y. Chen and W. Kong, "Short-term power load forecasting for industrial buildings based on decomposition reconstruction and TCN-Informer-BiGRU," Energy and Buildings, vol. 347, no. Part B, pp. 116317, 2025.
[23] Z. Tian, Z. Dong and S. Lv, "WDLformer: A novel mid-term load forecasting network considering weather score and distribution shift based on multi-encoders frequency fusion approach," Information Fusion, vol. 126, no. Part B, pp. 103674, 2026.
[24] Y. Fang, Y. Qin, H. Luo, F. Zhao and K. Zheng, "STWave++: A Multi-Scale Efficient Spectral Graph Attention Network With Long-Term Trends for Disentangled Traffic Flow Forecasting," in IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 6, pp. 2671-2685, June 2024.
[25] D. Hangawatta, A. Gargoom and A. Kouzani, "A novel method for electrical vehicle charging load extraction from low sampling rate data," Sustainable Energy, Grids and Networks, vol. 43, pp. 101903, 2025.
[26] R. Gong, A. Jiang, H. Hu, D. Liu, X. Wu and S. Zhang, "Short-term multi-featured power load forecasting model based on GBKA-VMD-Mambaformer with noise separation error correction under scarce load data," Electric Power Systems Research, vol. 247, pp. 111846, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Junxiong Ge, Zhaojun Wang, Zhen Jiao, Lijun Liu, Xiao Li, Haimin Hong
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.
