Deep Learning Based Power Load Prediction in Smart Grid Networks
DOI:
https://doi.org/10.4108/eetsis.9591Keywords:
Deep learning, power load prediction, smart grid networks, performance evaluationAbstract
This paper presents a novel deep learning scheme for power load prediction in smart grid networks, combining temporal modeling with adaptive feature integration to tackle the complex dynamics of electricity consumption. The proposed scheme features a hybrid architecture that merges recurrent neural networks with attention mechanisms, enabling simultaneous capture of long-term load patterns and dynamic weighting of external influences like weather conditions and temporal features. Moreover, the model incorporates specialized preprocessing to decompose load data into periodic and volatile components while employing robust normalization techniques to handle non-stationary behavior. Then, a dual-objective loss function is used to enhance both prediction accuracy and resilience to outliers, supported by adaptive optimization with regularization. Simulation results are provided to demonstrate the proposed scheme’s superior performance, achieving 96.1% prediction accuracy with 5 hidden layers. The attention mechanism proves particularly effective, reducing weather-related prediction errors by 22% while maintaining faster convergence rates than conventional methods. This comprehensive solution offers grid operators a reliable tool for demand-side management, renewable integration, and operational planning in modern power systems.
References
[1] J. Wang, M. Liu, and H. Wu, “The demand-side management and control of smart grids based on weighted network congestion games,” IEEE Trans Autom. Sci. Eng., vol. 22, pp. 43–52, 2025.
[2] S. Rahman, S. Pal, Z. Jadidi, and C. K. Karmakar, “Robust cyber threat intelligence sharing using federated learning for smart grids,” IEEE Trans. Comput. Soc. Syst., vol. 12, no. 2, pp. 635–644, 2025
[3] A. Ayad and F. Bouffard, “Enabling system flexibility in smart grid architecture,” IEEE Trans. Engineering Management, vol. 72, pp. 1892–1908, 2025.
[4] Y. Li, Y. Huo, T. Zhang, Z. Zhou, Q. Gao, T. Yan, Y. Yang, and T. Jing, “Distributed physical layer authentication with dynamic soft voting for smart distribution grids,” IEEE Trans. Inf. Forensics Secur., vol. 20, pp. 1807–1821, 2025.
[5] L. Coppolino, R. Nardone, A. Petruolo, and L. Romano, “Increasing the cyber security of smart grids by prosumer monitoring,” IEEE Trans. Ind. Informatics, vol. 21, no. 3, pp. 2669–2678, 2025.
[6] X. Shang-Guan, S. Shi, Y. He, and C. Zhang, “Optimal digital load frequency control of smart grid considering sampling and time delay based on warm-up gray wolf algorithm,” IEEE Trans. Ind. Informatics, vol. 21, no. 2, pp. 1773–1782, 2025.
[7] J. Qiao, J. Wu, F. Fan, X. Liang, G. Wang, Y. Du, Y. Xu, M. Zhang, Z. Hu, and M. Liu, “Highly sensitive magntoelectric sensor for characteristic current detection in smart grid,” IEEE Trans. Instrum. Meas., vol. 74, pp. 1–11, 2025.
[8] M. Chen, H. Deng, Y. Chen, G. Peng, and Z. Liang,“Stochastic energy scheduling for urban railway smart grids considering distributed evs charging and PV output uncertainty,” IEEE Trans. Intell. Transp. Syst., vol. 26, no. 6, pp. 7898–7908, 2025.
[9] Y. Bo, S. Shao, and M. Tao, “Deep learning-based super-position coded modulation for hierarchical semantic communications over broadcast channels,” IEEE Trans. Commun., vol. 73, no. 2, pp. 1186–1200, 2025.
[10] H. Xie, Z. Qin, G. Y. Li, and B. Juang, “Deep learning enabled semantic communication systems,” IEEE Trans. Signal Process., vol. 69, pp. 2663–2675, 2021.
[11] G. Brauwers and F. Frasincar, “A general survey on attention mechanisms in deep learning,” IEEE Trans. Knowl. Data Eng., vol. 35, no. 4, pp. 3279–3298, 2023.
[12] Y. Li, S. Mavromatis, F. Zhang, Z. Du, J. Sequeira, Z. Wang, X. Zhao, and R. Liu, “Single-image super-resolution for remote sensing images using a deep generative adversarial network with local and global attention mechanisms,” IEEE Trans. Geosci. Remote. Sens., vol. 60, pp. 1–24, 2022.
[13] G. Bono, J. S. Dibangoye, O. Simonin, L. Matignon, and F. Pereyron, “Solving multi-agent routing problems using deep attention mechanisms,” IEEE Trans. Intell. Transp. Syst., vol. 22, no. 12, pp. 7804–7813, 2021.
[14] W. Yu, Y. Ma, H. He, S. Song, J. Zhang, and K. B. Letaief, “Deep learning for near-field XL-MIMO transceiver design: Principles and techniques,” IEEE Commun. Mag., vol. 63, no. 1, pp. 52–58, 2025.
[15] D. Arya, D. K. Gupta, S. Rudinac, and M. Worring, “Adaptive neural message passing for inductive learning on hypergraphs,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 1, pp. 19–31, 2025.
[16] X. Pan, M. Zhang, Y. Yan, S. Zhang, and M. Yang, “Matryoshka: Exploiting the over-parametrization of deep learning models for covert data transmission,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 47, no. 2, pp. 663–678, 2025.
[17] A. Kaur, “Intrusion detection approach for industrial internet of things traffic using deep recurrent reinforcement learning assisted federated learning,” IEEE Trans. Artif. Intell., vol. 6, no. 1, pp. 37–50, 2025.
[18] J. Zhang, M. Wu, Z. Sun, and C. Zhou, “Learning from crowds using graph neural networks with attention mechanism,” IEEE Trans. Big Data, vol. 11, no. 1, pp. 86–98, 2025.
[19] J. Du, J. Xu, A. Sun, J. Kang, Y. Hu, F. R. Yu, and V. C. M. Leung, “Profit maximization for multi-time-scale hierarchical drl-based joint optimization in mec-enabled air-ground integrated networks,” IEEE Trans. Commun., vol. 73, no. 3, pp. 1591–1606, 2025.
[20] M. Zhao, Z. Yang, Z. He, F. Xue, and X. Zhang, “Multi- round stackelberg game-based pricing and offloading in containerized MEC networks,” IEEE Trans. Green Commun. Netw., vol. 9, no. 1, pp. 191–206, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Yifan Tian, Xiaoyi Chen, Yuanyuan Dai, Jiajia Shao, Jiankai Ma, Xiaoyu Yan, Zan Huang, Qi Wang, Lijun Wu, Zhijing Zhang, Shiyun Huang
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 CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
