Skip to content
2000
Volume 19, Issue 1
  • ISSN: 2212-7976
  • E-ISSN: 1874-477X

Abstract

Background

In the large-scale steel industry, significant power load variability, especially during processes like steel smelting, poses challenges to power system safety. Although there is an abundance of research and patents related to load forecasting, studies and patents specifically addressing large industrial load forecasting are sparse. Hence, accurate ultra-short-term load forecasting becomes particularly crucial.

Objective

This study proposes an innovative method for ultra-short-term load forecasting to improve prediction accuracy during peak periods and mitigate risks in high-load conditions.

Methods

We introduce an LSTM-XGBoost model enhanced by a random forest network and an improved grey wolf optimization algorithm (IGWO) for feature selection and parameter optimization, respectively.

Results

Compared to other advanced models, our method demonstrates superior performance across key indicators such as MAPE (1.93%), RMSE (220.81), and R2 coefficient (0.99), and the prediction error is lower during both peak and off-peak periods. For instance, the proposed model achieved a MAPE improvement of over 25% compared to traditional models. Validation with data from multiple time periods confirms the model's accuracy and robustness.

Conclusion

The proposed forecasting method effectively tackles load fluctuations in the steel industry, supporting safe and economical power system operations. Future research will aim to further improve peak identification accuracy and enable continuous adaptive learning.

© 2026 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/meng/10.2174/0122127976360100241221192728
2025-01-20
2025-12-09

  • From This Site

    /content/journals/meng/10.2174/0122127976360100241221192728
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. HeGuixiong A short-term regional power gap forecasting method, system, Equipment and media.Patent CN118569429A2024
  2. HsuC.C. ChenC.Y. Applications of improved grey prediction model for power demand forecasting.Energy Convers. Manage.200344142241224910.1016/S0196‑8904(02)00248‑0
     [Google Scholar]
  3. PappasS.S. EkonomouL. KaramousantasD.C. ChatzarakisG.E. KatsikasS.K. LiatsisP. Electricity demand loads modeling using autoregressive moving average (ARMA) models.Energy20083391353136010.1016/j.energy.2008.05.008
     [Google Scholar]
  4. ČerneG. DovžanD. ŠkrjancI. Short-term load forecasting by separating daily profiles and using a single fuzzy model across the entire domain.IEEE Trans. Ind. Electron.20186597406741510.1109/TIE.2018.2795555
     [Google Scholar]
  5. GurneyK. An introduction to neural networks.CRC press201810.1201/9781315273570
     [Google Scholar]
  6. ToliyatH.A. SadehJ. GhaziR. Design of augmented fuzzy logic power system stabilizers to enhance power systems stability.IEEE Trans. Energ. Convers.19961119710310.1109/60.486582
     [Google Scholar]
  7. ShanS. Support vector machine (machine learning models and algorithms for big data classification).Integr Ser Inf Syst201636
     [Google Scholar]
  8. RigattiS.J. Random forest.J. Insur. Med.2017471313910.17849/insm‑47‑01‑31‑39.1 28836909
     [Google Scholar]
  9. LahouarA. Ben Hadj SlamaJ. Day-ahead load forecast using random forest and expert input selection.Energy Convers. Manage.20151031040105110.1016/j.enconman.2015.07.041
     [Google Scholar]
  10. HuitingZ. JiabinY. ChenL. Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation.Energies2017108116810.3390/en10081168
     [Google Scholar]
  11. QiuX. ZhangL. RenY. SuganthanP.N. AmaratungaG. Ensemble deep learning for regression and time series forecasting. IEEE symposium on computational intelligence in ensemble learning (CIEL).IEEE2014
     [Google Scholar]
  12. TanM. YuanS. LiS. SuY. LiH. HeF.H. Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning.IEEE Trans. Power Syst.20203542937294810.1109/TPWRS.2019.2963109
     [Google Scholar]
  13. JiangH WuA WangB XuP YaoG Industrial ultra-short-term load forecasting with data completion.IEEE Access202081589284010.1109/ACCESS.2020.3017655
     [Google Scholar]
  14. LiK. HuangW. HuG. LiJ. Ultra-short term power load forecasting based on CEEMDAN-SE and LSTM neural network.Energy Build.202327911266610.1016/j.enbuild.2022.112666
     [Google Scholar]
  15. ZengW. LiJ. SunC. Ultra short-term power load forecasting based on similar day clustering and ensemble empirical mode decomposition.Energies2023164198910.3390/en16041989
     [Google Scholar]
  16. ZhangM. HanY. ZalhafA.S. Accurate ultra-short-term load forecasting based on load characteristic decomposition and convolutional neural network with bidirectional long short-term memory model.Sustain Energy Grids Netw20233510112910.1016/j.segan.2023.101129
     [Google Scholar]
  17. YangF. FuX. YangQ. ChuZ. Decomposition strategy and attention-based long short-term memory network for multi-step ultra-short-term agricultural power load forecasting.Expert Syst. Appl.202423812222610.1016/j.eswa.2023.122226
     [Google Scholar]
  18. TangJ. WangG. CaiZ. Ultra short term load forecasting for different types of industrial parks with intelligent buildings.J. Phys. Conf. Ser.20222378110.1088/1742‑6596/2378/1/012082
     [Google Scholar]
  19. BakareM.S. AbdulkarimA. ShuaibuA.N. MuhamadM.M. A hybrid long-term industrial electrical load forecasting model using optimized ANFIS with gene expression programming.Energy Rep.2024115831584410.1016/j.egyr.2024.05.045
     [Google Scholar]
  20. YadavA. BarethR. KocharM. PazokiM. SehiemyR.A.E. Gaussian process regression‐based load forecasting model.IET Gener. Transm. Distrib.202418589991010.1049/gtd2.12926
     [Google Scholar]
  21. WeiN. YinC. YinL. Short-term load forecasting based on WM algorithm and transfer learning model.Appl. Energy202435312208710.1016/j.apenergy.2023.122087
     [Google Scholar]
  22. ChenB. YangW. YanB. ZhangK. An advanced airport terminal cooling load forecasting model integrating SSA and CNN-Transformer.Energy Build.202430911400010.1016/j.enbuild.2024.114000
     [Google Scholar]
  23. HuangX. HanY. YanJ. ZhouX. Hybrid forecasting model of building cooling load based on EMD-LSTM-Markov algorithm.Energy Build.202432111467010.1016/j.enbuild.2024.114670
     [Google Scholar]
  24. ZhangJ. LiuH. BaiW. LiX. A hybrid approach of wavelet transform, ARIMA and LSTM model for the share price index futures forecasting.N. Am. J. Econ. Finance20246910202210.1016/j.najef.2023.102022
     [Google Scholar]
  25. YadavH. ThakkarA. NOA-LSTM: An efficient LSTM cell architecture for time series forecasting.Expert Syst. Appl.202423812233310.1016/j.eswa.2023.122333
     [Google Scholar]
  26. SaâdaouiF. RabbouchH. Financial forecasting improvement with LSTM-ARFIMA hybrid models and non-Gaussian distributions.Technol. Forecast. Soc. Change202420612353910.1016/j.techfore.2024.123539
     [Google Scholar]
  27. C Yolcu O, Yolcu U. A new ensemble intuitionistic fuzzy-deep forecasting model: Consolidation of the IFRFs-bENR with LSTM.Inf. Sci.202467912100710.1016/j.ins.2024.121007
     [Google Scholar]
  28. ShiH. WeiA. XuX. ZhuY. HuH. TangS. A CNN-LSTM based deep learning model with high accuracy and robustness for carbon price forecasting: A case of Shenzhen’s carbon market in China.J. Environ. Manage.202435212013110.1016/j.jenvman.2024.120131 38266520
     [Google Scholar]
  29. HasanatS.M. YounisR. AlahmariS. Enhancing load forecasting accuracy in smart grids: A novel parallel multichannel network approach using 1D CNN and Bi‐LSTM models.Int. J. Energy Res.20241240384710.1155/2024/2403847
     [Google Scholar]
  30. HuZ. GaoY. JiS. MaeM. ImaizumiT. Improved multistep ahead photovoltaic power prediction model based on LSTM and self-attention with weather forecast data.Appl. Energy202435912270910.1016/j.apenergy.2024.122709
     [Google Scholar]
  31. LiW. LiuC. XuY. An interpretable hybrid deep learning model for flood forecasting based on Transformer and LSTM.J. Hydrol. Reg. Stud.20245410187310.1016/j.ejrh.2024.101873
     [Google Scholar]
  32. ZhangL. JánošíkD. Enhanced short-term load forecasting with hybrid machine learning models: CatBoost and XGBoost approaches.Expert Syst. Appl.202424112268610.1016/j.eswa.2023.122686
     [Google Scholar]
  33. XuY. ZhengS. ZhuQ. WongK. WangX. LinQ. A complementary fused method using GRU and XGBoost models for long-term solar energy hourly forecasting.Expert Syst. Appl.202425412428610.1016/j.eswa.2024.124286
     [Google Scholar]
  34. FrifraA. MaananM. MaananM. RhinaneH. Harnessing LSTM and XGBoost algorithms for storm prediction.Sci. Rep.20241411138110.1038/s41598‑024‑62182‑0
     [Google Scholar]
  35. YangQ. LinY. KuangS. WangD. A novel short-term load forecasting approach for data-poor areas based on K-MIFS-XGBoost and transfer-learning.Electr. Power Syst. Res.202422911015110.1016/j.epsr.2024.110151
     [Google Scholar]
  36. BashirS.B. FaragM.M. HamidA.K. AdamA.A. Abo-KhalilA.G. BansalR. A novel hybrid CNN-XGBoost model for photovoltaic system power forecasting.6th International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)20241610.1109/REEPE60449.2024.10479878
     [Google Scholar]
  37. LiP. FuY. PanL. LiJ. TangJ. QinY. Multi-model short-term load forecasting based on VMD-XGBoost-BiGRU.3rd International Conference on Energy, Power and Electrical Technology (ICEPET)20241282128510.1109/ICEPET61938.2024.10625872
     [Google Scholar]
  38. AhmadA. JavaidN. GuizaniM. AlrajehN. KhanZ.A. An accurate and fast converging short-term load forecasting model for industrial applications in a smart grid.IEEE Trans. Industr. Inform.20171352587259610.1109/TII.2016.2638322
     [Google Scholar]
  39. LiY. LinX. LiuJ. An improved gray wolf optimization algorithm to solve engineering problems.Sustainability2021136320810.3390/su13063208
     [Google Scholar]
  40. FallahS.N. DeoR.C. ShojafarM. ContiM. ShamshirbandS. Computational intelligence approaches for energy load forecasting in smart energy management grids: State of the art, future challenges, and research directions.Energies201811359610.3390/en11030596
     [Google Scholar]
  41. HegdeK. DilliR. Wireless sensor networks: Network life time enhancement using an improved grey wolf optimization algorithm.Engineered Science2022196186197 35857542
     [Google Scholar]
  42. QiuY. YangX. ChenS. An improved gray wolf optimization algorithm solving to functional optimization and engineering design problems.Sci. Rep.20241411419010.1038/s41598‑024‑64526‑2
     [Google Scholar]
  43. RabieA.H. EltamalyA.M. A new NEST-IGWO strategy for determining optimal IGWO control parameters.Neural Comput. Appl.20233520151431516510.1007/s00521‑023‑08535‑8
     [Google Scholar]
  44. WangZ. WangY. ZengR. SrinivasanR.S. AhrentzenS. Random Forest based hourly building energy prediction.Energy Build.2018171112510.1016/j.enbuild.2018.04.008
     [Google Scholar]
  45. ZhangH. ZimmermanJ. NettletonD. NordmanD.J. Random forest prediction intervals.Am. Stat.202074439240610.1080/00031305.2019.1585288
     [Google Scholar]
  46. CahuantziR. ChenX. GüttelS. A comparison of LSTM and GRU networks for learning symbolic sequences.Science and Information Conference.Cham: Springer Nature Switzerland2023771785
     [Google Scholar]
  47. FanC. NieS. XiaoL. YiL. WuY. LiG. A multi-stage ensemble model for power load forecasting based on decomposition, error factors, and multi-objective optimization algorithm.Int. J. Electr. Power Energy Syst.202415510962010.1016/j.ijepes.2023.109620
     [Google Scholar]
  48. AbbasiR.A. JavaidN. GhumanM.N. KhanZ.A. Ur RehmanS. Amanullah. Short term load forecasting using XGBoost. Web, Artificial Intelligence and Network Applications.Proceedings of the Workshops of the 33rd International Conference on Advanced Information Networking and Applications (WAINA-2019)Springer International Publishing20191120113110.1007/978‑3‑030‑15035‑8_10
     [Google Scholar]
  49. LiG. LiW. TianX. CheY. Short-term electricity load forecasting based on the XGBoost algorithm.Smart Grid20177427428510.12677/SG.2017.74031
     [Google Scholar]
  50. MirjaliliS. MirjaliliS.M. LewisA. Grey wolf optimizer.Adv. Eng. Softw.201469466110.1016/j.advengsoft.2013.12.007
     [Google Scholar]
  51. Nadimi-ShahrakiM.H. TaghianS. MirjaliliS. An improved grey wolf optimizer for solving engineering problems.Expert Syst. Appl.202116611391710.1016/j.eswa.2020.113917
     [Google Scholar]
  52. Jackson Peter. Introduction to expert systems1986
     [Google Scholar]
  53. SavichA.W. MoussaM. AreibiS. The impact of arithmetic representation on implementing MLP-BP on FPGAs: A study.IEEE Trans. Neural Netw.200718124025210.1109/TNN.2006.883002 17278475
     [Google Scholar]
  54. ShinH.C. RothH.R. GaoM. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.IEEE Trans. Med. Imaging20163551285129810.1109/TMI.2016.2528162 26886976
     [Google Scholar]
  55. KongW. DongZ.Y. JiaY. HillD.J. XuY. ZhangY. Short-term residential load forecasting based on LSTM recurrent neural network.IEEE Trans. Smart Grid201910184185110.1109/TSG.2017.2753802
     [Google Scholar]
  56. MariniF. WalczakB. Particle swarm optimization (PSO). A tutorial.Chemom. Intell. Lab. Syst.201514915316510.1016/j.chemolab.2015.08.020
     [Google Scholar]
  57. SelimS.Z. AlsultanK. A simulated annealing algorithm for the clustering problem.Pattern Recognit.199124101003100810.1016/0031‑3203(91)90097‑O
     [Google Scholar]
  58. MaB LuP ZhangL Enhanced sparrow search algorithm with mutation strategy for global optimization.IEEE Access202191592186110.1109/ACCESS.2021.3129255
     [Google Scholar]
  59. ZhuF. LiG. TangH. LiY. LvX. WangX. Dung beetle optimization algorithm based on quantum computing and multi-strategy fusion for solving engineering problems.Expert Syst. Appl.202423612121910.1016/j.eswa.2023.121219
     [Google Scholar]
  60. MaoY. ZhengM. WangT. DuanM. A new mooring failure detection approach based on hybrid LSTM-SVM model for semi-submersible platform.Ocean Eng.202327511416110.1016/j.oceaneng.2023.114161
     [Google Scholar]
  61. ZhangX XiaoP YangY Remaining useful life estimation using CNN-XGB with extended time window.IEEE Access201971543869710.1109/ACCESS.2019.2942991
     [Google Scholar]
  62. KimT.Y. ChoS.B. Predicting residential energy consumption using CNN-LSTM neural networks.Energy2019182728110.1016/j.energy.2019.05.230
     [Google Scholar]
  63. WanR. MeiS. WangJ. LiuM. YangF. Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting.Electronics20198887610.3390/electronics8080876
     [Google Scholar]
  64. ChenX. LiH. HuangY. Heart sound classification based on equal scale frequency cepstral coefficients and deep learning.Biomed. Eng.2023683285295
     [Google Scholar]
  65. LuoH. LiX. A hybrid model of CNN-BiLSTM and XGBoost for HVAC systems energy consumption prediction.5th International Conference on Industrial Artificial Intelligence (IAI). IEEE202316
     [Google Scholar]
  66. SajjadM KhanZA UllahA A novel CNN-GRU-based hybrid approach for short-term residential load forecasting.IEEE Access202081437596810.1109/ACCESS.2020.3009537
     [Google Scholar]
  67. KimD.H. LeeE.K. QureshiN.B. Peak-load forecasting for small industries: A machine learning approach.Sustainability20201216653910.3390/su12166539
     [Google Scholar]
  68. RodriguesF. CardeiraC. CaladoJ.M. MelicioR. Short-term load forecasting of electricity demand for the residential sector based on modelling techniques: A systematic review.Energies20231610409810.3390/en16104098
     [Google Scholar]
  69. AbumohsenM. OwdaA.Y. OwdaM. Electrical load forecasting using LSTM, GRU, and RNN algorithms.Energies2023165228310.3390/en16052283
     [Google Scholar]
  70. PinheiroM.G. MadeiraS.C. FranciscoA.P. Short-term electricity load forecasting-A systematic approach from system level to secondary substations.Appl. Energy202333212049310.1016/j.apenergy.2022.120493
     [Google Scholar]
  71. B Behmiri NFezzi C, Ravazzolo F. Incorporating air temperature into mid-term electricity load forecasting models using time-series regressions and neural networks.Energy202327812783110.1016/j.energy.2023.127831
     [Google Scholar]
  72. AkhtarS. ShahzadS. ZaheerA. Short-term load forecasting models: A review of challenges, progress, and the road ahead.Energies20231610406010.3390/en16104060
     [Google Scholar]
  73. TarmaniniC. SarmaN. GezeginC. OzgonenelO. Short term load forecasting based on ARIMA and ANN approaches.Energy Rep.2023955055710.1016/j.egyr.2023.01.060
     [Google Scholar]
  74. SekharC. DahiyaR. Robust framework based on hybrid deep learning approach for short term load forecasting of building electricity demand.Energy202326812666010.1016/j.energy.2023.126660
     [Google Scholar]
  75. ZhangS. ChenR. CaoJ. TanJ.A. CNN and LSTM-based multi-task learning architecture for short and medium-term electricity load forecasting.Electr. Power Syst. Res.202322210950710.1016/j.epsr.2023.109507
     [Google Scholar]
/content/journals/meng/10.2174/0122127976360100241221192728
Loading
Ultra-short-term Forecasting Study of Power Load in Mega Steel Industry Based on Multi-stage Modeling
Recent Patents on Mechanical Engineering 19, 131 (2026); https://doi.org/10.2174/0122127976360100241221192728
/content/journals/meng/10.2174/0122127976360100241221192728
/content/journals/meng/10.2174/0122127976360100241221192728
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): deep learning; IGWO; integrated model; LSTM; steel industry; XGBoost

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test