Top > JACIII > A Short-Term Load Forecasting Method Based on a Hybrid Model f ...

single-jc.php

JACIII Vol.29 No.5 pp. 1145-1152
doi: 10.20965/jaciii.2025.p1145
(2025)

Research Paper:

Views over last 60 days: 317

A Short-Term Load Forecasting Method Based on a Hybrid Model for Industrial Boiler Generator Sets

Yan Xu*,**,*** ORCID Icon, Min Wu*,**,*** ORCID Icon, Jie Hu*,**,***,† ORCID Icon, Sheng Du*,**,*** ORCID Icon, Fusheng Peng*,**,*** ORCID Icon, Wen Zhang*,**,*** ORCID Icon, Wenshuo Song*,**,*** ORCID Icon, and Huihang Li*,**,*** ORCID Icon

*School of Automation, China University of Geosciences
No.388 Lumo Road, Hongshan District, Wuhan 430074, China

**Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems
No.388 Lumo Road, Hongshan District, Wuhan 430074, China

***Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education
No.388 Lumo Road, Hongshan District, Wuhan 430074, China

†Corresponding author

Received:
December 17, 2024
Accepted:
May 21, 2025
Published:
September 20, 2025
Creative Commons License
Keywords:
generator sets, load forecasting, CNN-LSTM, hybrid model
Abstract

Accurately predicting load variations is crucial for improving the energy efficiency and operational stability of industrial boiler generator sets. However, the current load scheduling of industrial boiler power plants heavily relies on manual experience, which hinders the optimization of system performance. This paper proposes a novel hybrid forecasting model, IFA-CNN-LSTM, which integrates data preprocessing, feature selection, and deep learning techniques. Firstly, the isolation forest algorithm is employed to detect and eliminate anomalies in the historical dataset. Then, key variables are identified by combining mechanistic analysis with spearman correlation. To address the variability of generator sets under diverse operating conditions, a hybrid neural network model combining convolutional neural networks and long short-term memory networks is constructed to capture both spatial and temporal features. The proposed model has been validated using real-world production data, and experimental results show that it outperforms traditional models in terms of forecasting accuracy.

Forecasting results of unit load based on different ensemble models

Forecasting results of unit load based on different ensemble models

Cite this article as:
Y. Xu, M. Wu, J. Hu, S. Du, F. Peng, W. Zhang, W. Song, and H. Li, “A Short-Term Load Forecasting Method Based on a Hybrid Model for Industrial Boiler Generator Sets,” J. Adv. Comput. Intell. Intell. Inform., Vol.29 No.5, pp. 1145-1152, 2025.
Data files:
References
  1. [1] A. R. Khatib, J. Desai, M. Kazmi, and N. Cai, “Commissioning challenges for upgrading gas turbines to combined cycle,” IEEE Trans. on Industry Applications, Vol.60, No.3, pp. 5202-5210, 2024. https://doi.org/10.1109/TIA.2024.3372514
  2. [2] J. Zhou, L. Z. Zhang, L. Zhu, and W. Zhang, “A data-driven operating improvement method for the thermal power unit with frequent load changes,” Applied Energy, Vol.354, Article No.122195, 2024. https://doi.org/10.1016/j.apenergy.2023.122195
  3. [3] N. Pathak, A. Verma, and T. S. Bhatti, “Automatic generation control of thermal power system under varying steam turbine dynamic model parameters based on generation schedules of the plants,” The J. of Engineering, Vol.2016, No.8, pp. 302-314, 2016. https://doi.org/10.1049/joe.2016.0178
  4. [4] S. Du, M. Wu, L. F. Chen, and W. Pedrycz, “Prediction model of burn-through point with fuzzy time series for iron ore sintering process,” Eng. Applications of Artificial Intelligence, Vol.102, Article No.104259, 2021. https://doi.org/10.1016/j.engappai.2021.104259
  5. [5] J. Hu, H. L, H. Li, M. Wu, W. Cao, and W. Pedrycz, “Relevance vector machine with hybrid kernel-based soft sensor via data augmentation for incomplete output data in sintering process,” Control Engineering Practice, Vol.145, Article No.105850, 2024. https://doi.org/10.1016/j.conengprac.2024.105850
  6. [6] F. Liu, Y. Huang, Y. Wang et al., “Short-term multi-energy consumption forecasting for integrated energy system based on interactive multi-scale convolutional module,” Scientific Reports, Vol.14, Article No.21382, 2024. https://doi.org/10.1038/s41598-024-72103-w
  7. [7] S. Zhou et al., “A load forecasting framework considering hybrid ensemble deep learning with two-stage load decomposition,” IEEE Trans. on Industry Applications, Vol.60, No.3, pp. 4568-4582, 2024. https://doi.org/10.1109/TIA.2024.3354222
  8. [8] S. Du et al., “Operating mode recognition based on fluctuation interval prediction for iron ore sintering process,” IEEE/ASME Trans. on Mechatronics, Vol.25, No.5, pp. 2297-2308, 2020. https://doi.org/10.1109/TMECH.2020.2992706
  9. [9] J. Hu, M. Wu, W. Cao, and W. Pedrycz, “Soft-sensing of burn-through point based on weighted kernel just-in-time learning and fuzzy broad-learning system in sintering process,” IEEE Trans. on Industrial Informatics, Vol.20, No.5, pp. 7316-7324, 2024. https://doi.org/10.1109/TII.2024.3359444
  10. [10] Y. Xu, M. Wu, J. Hu, S. Du, W. Zhang, F. S. Peng, H. H. Li, and W. S. Song, “Unit load prediction method based on weighted just-in-time learning with spatio-temporal characteristics for gas boiler power generation process,” Control Engineering Practice, Vol.160, Article No.106325, 2025. https://doi.org/10.1016/j.conengprac.2025.106325
  11. [11] M. Yan, L. Wang, M. Zhang, and P. Shi, “Improved LS-SVM boiler combustion model based on affinity propagation,” IEEE Access, Vol.12, pp. 35184-35194, 2024. https://doi.org/10.1109/ACCESS.2024.3372660
  12. [12] Y. Guo, Y. Li, X. B. Qiao, Z. Y. Zhang et al., “BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system,” IEEE Trans. on Smart Grid, Vol.13, No.5, pp. 3481-3492, 2022. https://doi.org/10.1109/TSG.2022.3173964
  13. [13] M. Dong and L. Grumbach, “A hybrid distribution feeder long-term load forecasting method based on sequence prediction,” IEEE Trans. on Smart Grid, Vol.11, No.1, pp. 470-482, 2020. https://doi.org/10.1109/TSG.2019.2924183
  14. [14] Y. Ren, P. N. Suganthan, N. Srikanth, and G. Amaratunga, “Random vector functional link network for short-term electricity load demand forecasting,” Information Sciences, Vols.367-368, pp. 1078-1093, 2016. https://doi.org/10.1016/j.ins.2015.11.039
  15. [15] D. C. Yang, J. E. Guo, Y. Z. Li, S. L. Sun, and S. Y. Wang, “Short-term load forecasting with an improved dynamic decomposition-reconstruction-ensemble approach,” Energy, Vol.263, Article No.125609, 2023. https://doi.org/10.1016/j.energy.2022.125609
  16. [16] J. Hu, M. Wu, P. Zhang, and W. Pedrycz, “Prediction performance improvement via anomaly detection and correction of actual production data in iron ore sintering process,” IEEE Trans. on Industrial Informatics, Vol.16, No.12, pp. 7602-7612, 2020. https://doi.org/10.1109/TII.2020.2979465
  17. [17] L. Chen, M. Li, W. Su, M. Wu, K. Hirota, and W. Pedrycz, “Adaptive feature selection-based adaBoost-KNN with direct optimization for dynamic emotion recognition in human–robot interaction,” IEEE Trans. on Emerging Topics in Computational Intelligence, Vol.5, No.2, pp. 205-213, 2021. https://doi.org/10.1109/TETCI.2019.2909930
  18. [18] Q. Xie, G. Tao, C. Xie, and Z. Wen, “Abnormal data detection based on adaptive sliding window and weighted multiscale local outlier factor for machinery health monitoring,” IEEE Trans. on Industrial Electronics, Vol.70, No.11, pp. 11725-11734, 2023. https://doi.org/10.1109/TIE.2022.3231279
  19. [19] H. Fan, X. Lai, S. Du, W. Yu, C. Lu, and M. Wu, “Distributed monitoring with integrated probability PCA and mRMR for drilling processes,” IEEE Trans. on Instrumentation and Measurement, Vol.71, pp. 1-13, 2022. https://doi.org/10.1109/TIM.2022.3186081
  20. [20] L. Li, W. Li, Q. Du, and R. Tao, “Low-rank and sparse decomposition with mixture of gaussian for hyperspectral anomaly detection,” IEEE Trans. on Cybernetics, Vol.51, No.9, pp. 4363-4372, 2020. https://doi.org/10.1109/TCYB.2020.2968750

Creative Commons License  This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Sep. 19, 2025