Enhancing Load Forecasting Accuracy of Neural Hierarchical Interpolation for Time Series through Hyperparameter Optimization

Thanh Ngoc Tran; Tuan Anh Nguyen

doi:10.46604/peti.2026.16317

Authors

Thanh Ngoc Tran Faculty of Electrical Engineering Technology, Industrial University of Ho Chi Minh City, Ho Chi Minh City, Vietnam
Tuan Anh Nguyen Faculty of Electrical Engineering Technology, Industrial University of Ho Chi Minh City, Ho Chi Minh City, Vietnam

DOI:

https://doi.org/10.46604/peti.2026.16317

Keywords:

NHITS, electricity load forecasting, random search, tree-structured Parzen estimator, genetic algorithm

Abstract

This study aims to improve the forecasting accuracy of the neural hierarchical interpolation for time series (NHITS) model through a hyperparameter optimization framework. Three optimization strategies, namely random search (RS), tree-structured Parzen estimator (TPE), and genetic algorithm (GA), are compared under the same search space and evaluation budget. Three key hyperparameters, including mlp_units, learning_rate, and max_steps, are optimized because they directly affect model capacity, convergence behavior, and training effort. Experiments are conducted on two Australian half-hourly electricity demand datasets, New South Wales (NSW) and Queensland (QLD), each containing 122,735 records. Forecasting performance is evaluated using MSE, RMSE, MAE, and MAPE. The results show that all optimization methods improve the default NHITS configuration, while TPE achieves the best performance. MAPE decreases from 2.21% to 1.23% for NSW and from 3.34% to 1.79% for QLD.

References

Y. Eren and İ. Küçükdemiral, “A Comprehensive Review on Deep Learning Approaches for Short-Term Load Forecasting,” Renewable and Sustainable Energy Reviews, vol. 189, part B, article no. 114031, 2024.

N. T. N. Anh, N. N. Anh, T. N. Thang, V. K. Solanki, R. G. Crespo, and N. Q. Dat, “Online SARIMA Applied for Short-Term Electricity Load Forecasting,” Applied Intelligence, vol. 54, no. 1, pp. 1003-1019, 2024.

H. M. Al-Hamadi, “Long-Term Electric Power Load Forecasting Using Fuzzy Linear Regression Technique,” Proceedings of the 2011 IEEE Power Engineering and Automation Conference, pp. 96-99, 2011.

T. T. Ngoc, L. Van Dai, and C. M. Thuyen, “Support Vector Regression Based on Grid Search Method of Hyperparameters for Load Forecasting,” Acta Polytechnica Hungarica, vol. 18, no. 2, pp. 143-158, 2021.

P. F. Pai and W. C. Hong, “Forecasting Regional Electricity Load Based on Recurrent Support Vector Machines with Genetic Algorithms,” Electric Power Systems Research, vol. 74, no. 3, pp. 417-425, 2005.

S. Deng, X. Dong, L. Tao, J. Wang, Y. He, and D. Yue, “Multi-Type Load Forecasting Model Based on Random Forest and Density Clustering with the Influence of Noise and Load Patterns,” Energy, vol. 307, article no. 132635, 2024.

S. Wang and J. Ma, “A Novel Ensemble Model for Load Forecasting: Integrating Random Forest, XGBoost, and Seasonal Naive Methods,” Proceedings of the 2023 2nd Asian Conference on Frontiers of Power and Energy (ACFPE), pp. 114-118, 2023.

L. Zhang and D. Jánošík, “Enhanced Short-Term Load Forecasting with Hybrid Machine Learning Models: CatBoost and XGBoost Approaches,” Expert Systems with Applications, vol. 241, article no. 122686, 2024.

A. O. Aseeri, “Effective RNN-Based Forecasting Methodology Design for Improving Short-Term Power Load Forecasts: Application to Large-Scale Power-Grid Time Series,” Journal of Computational Science, vol. 68, article no. 101984, 2023.

J. Wen, Y. Peng, W. Zhang, X. Huang, and Z. Wang, “Short-Term Power Load Forecasting Based on TCN-LSTM Model,” Proceedings of the 2024 IEEE 6th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), pp. 734-738, 2024.

A. Kathirgamanathan, A. Patel, A. S. Khwaja, B. Venkatesh, and A. Anpalagan, “Performance Comparison of Single and Ensemble CNN, LSTM and Traditional ANN Models for Short-Term Electricity Load Forecasting,” The Journal of Engineering, vol. 2022, no. 5, pp. 550-565, 2022.

H. Eskandari, M. Imani, and M. Parsa Moghaddam, “Best-Tree Wavelet Packet Transform Bidirectional GRU for Short-Term Load Forecasting,” The Journal of Supercomputing, vol. 79, no. 12, pp. 13545-13577, 2023.

J. Ran, Y. Gong, Y. Hu, and J. L. Cai, “EV Load Forecasting Using a Refined CNN-LSTM-AM,” Electric Power Systems Research, vol. 238, article no. 111091, 2025.

Q. Hua et al., “A Short-Term Power Load Forecasting Method Using CNN-GRU with an Attention Mechanism,” Energies, vol. 18, no. 1, article no. 106, 2025.

D. Tan, Z. Tang, F. Zhou, and Y. Xie, “A Novel Hybrid Model Based on EMD-Improved TCN-Improved TST for Short-Term Railway Traction Load Forecasting,” IEEE Transactions on Transportation Electrification, vol. 11, no. 2, pp. 6418-6427, 2024.

X. Guo, Q. Zhao, D. Zheng, Y. Ning, and Y. Gao, “A Short-Term Load Forecasting Model of Multi-Scale CNN-LSTM Hybrid Neural Network Considering the Real-Time Electricity Price,” Energy Reports, vol. 6, pp. 1046-1053, 2020.

J. Zhang, Z. Zhu, and Y. Yang, “Electricity Load Forecasting Based on CNN-LSTM,” Proceedings of the 2023 IEEE International Conference on Electrical, Automation and Computer Engineering (ICEACE), pp. 1385-1390, 2023.

Z. Tian, W. Liu, W. Jiang, and C. Wu, “CNNs-Transformer Based Day-Ahead Probabilistic Load Forecasting for Weekends with Limited Data Availability,” Energy, vol. 293, article no. 130666, 2024.

J. W. Chan and C. K. Yeo, “A Transformer Based Approach to Electricity Load Forecasting,” The Electricity Journal, vol. 37, no. 2, article no. 107370, 2024.

S. F. Stefenon, L. O. Seman, C. K. Yamaguchi, L. D. S. Coelho, V. C. Mariani, J. P. Matos-Carvalho, et al., “Neural Hierarchical Interpolation Time Series (NHITS) for Reservoir Level Multi-Horizon Forecasting in Hydroelectric Power Plants,” IEEE Access, vol. 13, pp. 54853-54865, 2025.

W. Zhou, H. Qi, D. Boland, and P. H. W. Leong, “FPGA Implementation of N-BEATS for Time Series Forecasting Using Block Minifloat Arithmetic,” Proceedings of the 2022 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS), pp. 546-550, 2022.

M. Dai, M. Y. Seow, R. Shirota Filho, A. Sclip, K. Chawla, R. S. M. Goh, et al., “N-BEATS-GAN: A Risk-Aware Financial Time Series Forecasting with Generative Adversarial Networks,” Applied Soft Computing, vol. 186, part D, article no. 114235, 2026.

H. Hou, C. Liu, Q. Wang, X. Wu, J. Tang, Y. Shi, et al., “Review of Load Forecasting Based on Artificial Intelligence Methodologies, Models, and Challenges,” Electric Power Systems Research, vol. 210, article no. 108067, 2022.

O. Rubasinghe, X. Zhang, T. K. Chau, T. Fernando, and H. H. C. Iu, “A Novel Sequence to Sequence based CNN-LSTM Model for Long Term Load Forecasting,” Proceedings of the 2022 IEEE Sustainable Power and Energy Conference (iSPEC), pp. 1-5, 2022.

H. Hu and B. Zheng, “Short-Term Electricity Load Forecasting Based on CEEMDAN-FE-BiGRU-Attention Model,” International Journal of Low-Carbon Technologies, vol. 19, pp. 988-995, 2024.

Ş. Özdemir, Y. Demir, and Ö. Yildirim, “The Effect of Input Length on Prediction Accuracy in Short-Term Multi-Step Electricity Load Forecasting: A CNN-LSTM Approach,” IEEE Access, vol. 13, pp. 28419-28432, 2025.