A Short-Term Load Forecasting Method for Typical High Energy-Consuming Industrial Parks Based on Multimodal Decomposition and Hybrid Neural Networks
Source abstract
Abstract
High energy-consuming industrial parks are characterized by high base-load-to-peak-valley ratios, overlapping production cycles, and megawatt-scale step changes, which significantly complicate short-term load forecasting. To tackle these challenges, this study proposes a novel forecasting framework that combines hierarchical multimodal decomposition with a hybrid deep learning architecture. First, Maximal Information Coefficient (MIC) analysis is applied to identify key input features and eliminate redundancy. The load series is then decomposed in two stages: seasonal-trend decomposition uses the Loess (STL) isolates trend and seasonal components, while variational mode decomposition (VMD) further disaggregates the residual into multi-scale modes. This hierarchical approach enhances signal clarity and preserves temporal structure. A parallel neural architecture is subsequently developed, integrating an Informer network to model long-term trends and a bidirectional gated recurrent unit (BiGRU) to capture short-term fluctuations. Case studies based on real-world load data from a typical industrial park in northeastern China demonstrate that the proposed model achieves significantly improved forecasting accuracy and robustness compared to benchmark methods. These results provide strong technical support for fine-grained load prediction and intelligent dispatch in high energy-consuming industrial scenarios.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Grey System Theory Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electric Power, Inner Mongolia University of Technology, Hohhot 010080, China
Funding
Inner Mongolia Autonomous Region Science and Technology Breakthrough Project · National Key Research and Development Plan Energy Storage and Smart Grid Technology Project · Inner Mongolia Natural Science Foundation under Grant
References (21)
Show source-provided references
1. Understanding the synergy of energy storage and renewables in decarbonization via random forest-based explainable AI10.1016/j.apenergy.2025.125891 ↗
2. Review of Market Implementation and Scheduling Models Considering the Flexibility Extraction of Differentiated Industrial Energy-Intensive Loads
3. Reinforcement Learning-Based Time of Use Pricing Design Toward Distributed Energy Integration in Low Carbon Power System10.1109/TNSE.2024.3521929 ↗
4. Optimization method for load aggregation scheduling in industrial parks considering multiple interests and adjustable load classification10.1016/j.energy.2025.135887 ↗
5. Collaborative optimization model of industrial high-energy consumption park under green and low-carbon transformation10.1049/ell2.13187 ↗
6. Review on Artificial Intelligence Based Load Forecasting Research for the New-type Power System
7. Review on Application of Artificial Intelligence in Power System and Integrated Energy System
8. Short-term wind speed forecasting based on CEEMD-SE-PSR-BP method
9. Guo, W., Liu, J., Ma, J., and Lan, Z. (2025). Short-Term Power Load Forecasting Using Adaptive Mode Decomposition and Improved Least Squares Support Vector Machine. Energies, 18.10.3390/en18102491 ↗
10. Ultra Short-term Load Forecasting of User Level Integrated Energy System Based on Variational Mode Decomposition and Multi-model Fusion
11. Load Forecasting of Integrated Energy System Based on Combination of Decomposition Algorithms and Meta-learning
12. An Optimized Power Load Forecasting Algorithm Based on VMD-SMA-LSTM10.1002/ese3.70100 ↗
13. A hybrid electric load forecasting model based on decomposition considering fisher information10.1016/j.apenergy.2024.123149 ↗
14. Short-term integrated forecasting method for wind power, solar power, and system load based on variable attention mechanism and multi-task learning10.1016/j.energy.2024.132188 ↗
15. An advanced framework for net electricity consumption prediction: Incorporating novel machine learning models and optimization algorithms10.1016/j.energy.2024.131259 ↗
16. Combined electricity load-forecasting system based on weighted fuzzy time series and deep neural networks10.1016/j.engappai.2024.108375 ↗
17. Evaluating the externality value of distributed photovoltaics: Industry-specific investment decisions under diverse pricing schemes10.1016/j.renene.2025.122986 ↗
18. You, W., Guo, D., Wu, Y., and Li, W. (2023). Multiple Load Forecasting of Integrated Energy System Based on Sequential-Parallel Hybrid Ensemble Learning. Energies, 16.10.3390/en16073268 ↗
19. Parallel TimesNet-BiLSTM model for ultra-short-term photovoltaic power forecasting using STL decomposition and auto-tuning10.1016/j.energy.2025.135286 ↗
20. A combined system based on data preprocessing and optimization algorithm for electricity load forecasting10.1016/j.cie.2024.110114 ↗
21. Artificial lemming algorithm: A novel bionic meta-heuristic technique for solving real-world engineering optimization problems10.1007/s10462-024-11023-7 ↗