Industrial Electricity Load Forecasting Considering Periodic Features and Inter-Industry Associations
DOI:
https://doi.org/10.13052/dgaej2156-3306.4139Keywords:
Industrial electricity load forecasting, time2vector, periodic features, VECM, inter-industry association dynamic graph neural networkAbstract
Industrial electricity load forecasting is crucial for the stable operation of power systems and energy management. However, the complex temporal patterns and dynamic interdependencies between loads from different industries make it challenging for traditional forecasting methods to model effectively. To address this, this paper proposes a forecasting model based on an inter-industry association dynamic graph neural network that integrates periodic features. The proposed method uses the Time2Vector block to adaptively capture multiple periodic fluctuations in the load sequence, and combines this with the cointegration relationship and error correction mechanism from the Vector Error Correction Model (VECM) to quantify the association strength between industries. Each industry is represented as a node, and the association strengths define the edges and their weights. Thus, this forms a Dynamic Inter-industry Association Graph (DIAG). This graph is then integrated into a Dynamic Spatial-Temporal Aware Graph Neural Network framework. As a result, the Inter-industry Association Dynamic Graph Neural Network (IADGNN) is formed. This model captures the complex dynamic characteristics of electricity loads across different industries. Test cases based on industrial load data from one province in China show that this method significantly outperforms traditional models in terms of forecasting accuracy, providing a novel solution for addressing the complex industrial load forecasting problem.
Downloads
References
Ahmad T, Zhang D. A critical review of comparative global historical energy consumption and future demand: The story told so far. Energy Reports, 2020, 6: 1973–1991.
Xu, C, Liu, J, Chen, L, Zhang, P, and He, W (2025). Advanced Machine Learning Solutions for Power Load Forecasting and Power Grid Planning Optimization. Distributed Generation & Alternative Energy Journal, 40(2), 259–278.
Hepburn C, Qi Y, Stern N, et al. Towards carbon neutrality and China’s 14th Five-Year Plan: Clean energy transition, sustainable urban development, and investment priorities. Environmental Science and Ecotechnology, 2021, 8: 100130.
Gang L I, Hong F, Yunpeng L I U. Large-model drive technology in new power system: status, challenges and prospects. High Voltage Engineering, 2024, 50(7): 2864–2878.
Habbak H, Mahmoud M, Metwally K, et al. Load forecasting techniques and their applications in smart grids. Energies, 2023, 16(3): 1480.
Han F J, Wang X H, Qiao J, et al. Review on artificial intelligence based load forecasting research for the new-type power system. Proc. CSEE, 2023, 43(22): 8569–8591.
Hongtao L, Shuo L, Junwei D U, et al. Review of deep learning applied to time series prediction. Journal of Frontiers of Computer Science & Technology, 2023, 17(6): 1285.
Unlu A, Peña M, Wang Z. Comparison of the combined deep learning methods for load forecasting. 2023 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT). IEEE, 2023: 1–5.
Buratto W G, Muniz R N, Nied A, et al. Seq2Seq-LSTM with attention for electricity load forecasting in Brazil. IEEE Access, 2024, 12: 30020–30029.
Ma G, Hu S, Pang N and Zhou Q. Strategy Improved Pelican Algorithm Optimization ELM for Short-Term Electricity Load Forecasting. Distributed Generation & Alternative Energy Journal, 2025, 40, 85–108.
Yong B, Huang L, Li F, et al. A research of Monte Carlo optimized neural network for electricity load forecast. The Journal of Supercomputing, 2020, 76: 6330–6343.
Alkayal S, Almisbahi H, Baowidan S, Alkayal E. Air Pollution Trends and Predictive Modeling for Three Cities with Different Characteristics Using Sentinel-5 Satellite Data and Deep Learning. Atmosphere. 2025; 16(2):211.
Hu Y, Li J, Hong M, et al. Industrial artificial intelligence based energy management system: Integrated framework for electricity load forecasting and fault prediction. Energy, 2022, 244.
Kartini U T, Ardyansyah D P, Yundra E. Hybrid Model For The Next Hourly Electricity Load Demand Forecasting Based on Clustering and Weather Data. 2020.
Tan M, Yuan S, Li S, et al. Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning. IEEE transactions on power systems, 2019, 35(4): 2937–2948.
Wang Y, Chen J, Chen X, et al. Short-term load forecasting for industrial customers based on TCN-LightGBM. IEEE Transactions on Power Systems, 2020, 36(3): 1984–1997.
Bessani M, Massignan J A D, Santos T M O, et al. Multiple households very short-term load forecasting using bayesian networks. Electric Power Systems Research, 2020, 189: 106733.
Kychkin A V, Chasparis G C. Feature and model selection for day-ahead electricity-load forecasting in residential buildings. Energy and Buildings, 2021, 249: 111200.
Alikhani P, Tjernberg L B, Astner L, et al. Forecasting the electrical demand at the port of Gävle Container termina. 2021 IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe). IEEE, 2021: 1–6.
Yadav K, Singh M. A novel energy management of public charging stations using attention-based deep learning model. Electric Power Systems Research, 2025, 238.
Fan G. Research and implementation on parallel power load prediction[D]. North China Electric Power University (Beijing), 2022.
Guo Y, Li Y, Qiao X, et al. BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system. IEEE Transactions on Smart Grid, 2022, 13(5): 3481–3492.
He Z, Zhao C, Huang Y. Multivariate time series deep spatiotemporal forecasting with graph neural network. Applied Sciences, 2022, 12(11): 5731.
Lv Y, Wang L, Long D, et al. Multi-area short-term load forecasting based on spatiotemporal graph neural network. Engineering Applications of Artificial Intelligence, 2024, 138.
Wang Y, Rui L, Ma J, et al. A short-term residential load forecasting scheme based on the multiple correlation-temporal graph neural networks. Applied Soft Computing, 2023, 146(000):12.
Lan S, Ma Y, Huang W, et al. Dstagnn: Dynamic spatial-temporal aware graph neural network for traffic flow forecasting. International conference on machine learning. PMLR, 2022: 11906–11917.
Kazemi S M, Goel R, Eghbali S, et al. Time2Vec: Learning a Vector Representation of Time. 2019.
Liu Y, Zhao X, Lu D, et al. Impact of policy incentives on the adoption of electric vehicle in China. Transportation research part A: policy and practice, 2023, 176: 103801.
Ren X, Shao Q, Zhong R. Nexus between green finance, non-fossil energy use, and carbon intensity: Empirical evidence from China based on a vector error correction model. Journal of Cleaner Production, 2020, 277: 122844.
Song W, Zhang X. Research on the linkage between lithium carbonate futures market and spot market: Based on the perspective of VECM model. Northern Economics and Trade, 2025, (2): 93–98.
Ma G, Hu S, Pang N, et al. Strategy Improved Pelican Algorithm Optimization ELM for Short-Term Electricity Load Forecasting. Distributed Generation & Alternative Energy Journal, 2025, 40(1), 85–108.
Chen H, Meng L, Xi Y, et al. GRU Based Time Series Forecast of Oil Temperature in Power Transformer. Distributed Generation & Alternative Energy Journal, 2023, 38(2), 393–412.
Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv preprint arXiv:1709.04875, 2017.
