Power, Control, and Data Processing Systems

Data-Driven Power Load Forecasting Using Time-Delay Cerebellar and Rough Gaussian Neural Networks

Document Type : Original Research

Authors

Mohammadhossein Tamimi
Ehsan Shahi

Faculty of Electrical Engineering of K. N. Toosi University of Technology

https://doi.org/10.30511/pcdp.2026.2093054.1091
Abstract
Accurate load forecasting is recognized as a critical requirement for the secure and economical operation of modern power systems. In this study, two advanced data-driven neural architectures are presented and compared for forecasting the load behavior of Iran’s power grid. In the first approach, a Time-Delay Cerebellar Model Articulation Controller (TD-CMAC) is employed to capture temporal dependencies in hourly load series, and its performance is systematically benchmarked against a conventional Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Extreme Gradient Boosting (XGBoost). In the second approach, a rough Gaussian Neural Network (RGNN), trained by the Levenberg–Marquardt algorithm, is developed, in which rough set concepts are combined with Gaussian activation functions to enhance robustness under uncertainty. This RGNN is evaluated on power load time-series data, so that its generalization capability across regression tasks can be assessed. Both neural frameworks are trained on real load data from the Iranian power network. Their performance is quantified using cost functions, regression plots, and accuracy metrics, demonstrating that while the proposed RGNN provides exceptional robustness against fluctuations, both architectures offer complementary advantages depending on the forecasting horizon. The empirical findings indicate that the TD-CMAC achieves competitive and often superior accuracy compared with the MLP, and XGBoost for short-term load forecasting, whereas the Levenberg–Marquardt-trained RGNN provides effective and robust modeling for prediction in the presence of uncertainty. Overall, it is demonstrated that the combination of time-delay cerebellar structures with rough Gaussian neural modeling constitutes a powerful data-driven toolkit for power load forecasting in complex power systems.

Keywords

Short-term Load Forecasting (STLF)
Power systems
Data-driven time-series modeling
Time-Delay Cerebellar Model Articulation Controller (TD-CMAC)
Rough Gaussian Neural Network (RGNN)
Levenberg&ndash
Marquardt algorithm
Multi-Layer Perceptron (MLP)
Robust neural architectures
Subjects
Q. T. Nguyen, T. N. Le, T. T. Phung, H. M. V. Nguyen, and T. A. Nguyen, "Effect of real-time price on short-term load forecasting," J. Tech. Educ. Sci., vol. 18, no. Special Issue 03, Aug., 2023, doi: https://doi.org/10.54644/jte.78A.2023.1310.
[2]    G. Tang and Z. Zhang, "Generalizability-enhanced deep network based day-ahead sub-hourly resolution load forecasting model," CSEE J. Power Energy Syst, Jul., 2026, doi: https://doi.org/10.17775/CSEEJPES.2025.10090.
[3]    Y. Zhang, S. Dong, M. Liu, Z. Ling, W. Gang, and C. Zhang, "A fast and accurate multi-user load forecasting method based on coupled traditional neural networks and a time-series large model," J. Cleaner Prod., vol. 546, p. 147799, Feb., 2026, doi: https://doi.org/10.1016/j.jclepro.2026.147799.
[4]    A. M. Assaf, H. Haron, H. N. Abdull Hamed, F. A. Ghaleb, S. N. Qasem, and A. M. Albarrak, "A review on neural network based models for short term solar irradiance forecasting," Appl. Sci., vol. 13, no. 14, p. 8332, Jul., 2023, doi: https://doi.org/10.3390/app13148332.
[5]    O. M. Neda, "A Hybrid LSTM-XGBoost Model for Multi-Horizon Short-Term Load Forecasting in Smart Power Distribution Systems," e-Prime Adv. Electr. Eng. Electron. Energy, p. 201211, Sep., 2026, doi: https://doi.org/10.1016/j.eprime.2026.201211.
[6]    Y. Yang, F. Jinfu, W. Zhongjie, Z. Zheng, and X. Yukun, "A dynamic ensemble method for residential short-term load forecasting," Alexandria Eng. J., vol. 63, pp. 75-88, Jan., 2023, doi: https://doi.org/10.1016/j.aej.2022.07.050.
[7]    S. Pelekis et al., "A comparative assessment of deep learning models for day-ahead load forecasting: Investigating key accuracy drivers," Sustainable Energy Grids Networks, vol. 36, p. 101171, Dec., 2023, doi: https://doi.org/10.1016/j.segan.2023.101171.
[8]    Z. Sheng, Z. An, H. Wang, G. Chen, and K. Tian, "Residual LSTM based short-term load forecasting," Appl. Soft Comput., vol. 144, p. 110461, Sep., 2023, doi: https://doi.org/10.1016/j.asoc.2023.110461.
[9]    K. Ullah et al., "Short-term load forecasting: A comprehensive review and simulation study with CNN-LSTM hybrids approach," Ieee Access, vol. 12, pp. 111858-111881, Aug., 2024, doi: https://doi.org/10.1109/ACCESS.2024.3440631.
[10]    N. Behnia, M. Hayatzadeh, and M. F. Doghozlo, "Enhancing sediment load predictions: a comparative analysis of local and global fuzzy cerebellar model articulation controller (FCMAC)," Earth Sci. Inf., vol. 18, no. 1, p. 50, Jan., 2025, doi: https://doi.org/10.1007/s12145-024-01498-x
[11]    J. Huang and R. Qin, "Elman neural network considering dynamic time delay estimation for short-term forecasting of offshore wind power," Appl. Energy, vol. 358, p. 122671, Mar., 2024, doi: https://doi.org/10.1016/j.apenergy.2024.122671.
[12]    S. Kudukkil Manchingal, M. Mubashar, K. Wang, K. Shariatmadar, and F. Cuzzolin, "Random-set neural networks," in Int. Conf. Learn. Representations, Apr., 2025, vol. 2025. 
[13]    S. Ali, S. Riaz, X. Liu, and G. Wang, "A Levenberg–Marquardt based neural network for short-term load forecasting," Comput. Mater. Continua, vol. 75, no. 1, p. 1783, Feb., 2023, doi: https://doi.org/10.32604/cmc.2023.035736.
[14]    J. Chen, L. Liu, K. Guo, S. Liu, and D. He, "Short-term electricity load forecasting based on improved data decomposition and hybrid deep-learning models," Appl. Sci., vol. 14, no. 14, p. 5966, Jul., 2024, doi: https://doi.org/10.3390/app14145966.
[15]    Z. Hong and Q. Lin, "Adaptive user clustering enhanced BiLSTM-attention for short-term load forecasting in smart distribution networks," Sci. Rep., Jul., 2026, doi: https://doi.org/10.1038/s41598-026-60718-0
[16]    H. I. Beloev, S. R. Saitov, A. A. Filimonova, N. D. Chichirova, O. E. Babikov, and I. K. Iliev, "Short-Term Electrical Load Forecasting Based on XGBoost Model," Energies, vol. 18, no. 19, Sep., 2025, doi: https://doi.org/10.3390/en18195144.
[17]    S. Akhtar et al., "Short-term load forecasting models: A review of challenges, progress, and the road ahead," Energies, vol. 16, no. 10, May., 2023, doi: https://doi.org/10.3390/en16104060.
[18]    H. Khajeh and H. Laaksonen, "Applications of probabilistic forecasting in smart grids: A review," Appl. Sci., vol. 12, no. 4, p. 1823, Feb., 2022, doi: https://doi.org/10.3390/app12041823.
[19]    E. Uwimana, Y. Zhou, and N. M. Sall, "A short-term load demand forecasting: Levenberg–Marquardt (LM), Bayesian regularization (BR), and scaled conjugate gradient (SCG) optimization algorithm analysis," J. Supercomput., vol. 81, no. 1, p. 55, Oct., 2024, doi: https://doi.org/10.1007/s11227-024-06513-y
Q. Dong et al., "Short-Term Electricity-Load Forecasting by deep learning: A comprehensive survey," Eng. Appl. Artif. Intell., vol. 154, p. 110980, Aug., 2025, doi: https://doi.org/10.1016/j.engappai.2025.110980
Power, Control, and Data Processing Systems
Volume 4, Issue 1
Winter 2027
Pages 31-43

  • Receive Date 02 July 2026
  • Revise Date 05 August 2026
  • Accept Date 21 August 2026
  • First Publish Date 21 August 2026
  • Publish Date 01 March 2027

Home

AI Policy

Submit Manuscript

Contact Us