Skip to content
2000
Volume 18, Issue 4
  • ISSN: 2352-0965
  • E-ISSN: 2352-0973

Abstract

Background

Accurate short-term load forecasting is an important guarantee for the safety, stability, economic and efficient operation of power systems.

Objective

In order to effectively improve the forecasting accuracy, this paper proposes a hybrid forecasting model of convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) neural network considering load time-varying trend mapping model (M).

Methods

Firstly, the time-varying features of the load curve are analyzed, and a mapping model is established to characterize the load time-varying trend. The features of the load time-varying trend are extracted, and they are quantified into a mathematical model. Secondly, the feature set is reconstructed through data migration. Then, the reconstructed feature set is input into the CNN-BiLSTM hybrid model. In the hybrid model, CNN is used to extract the features from data again to form a new feature vector, and then the feature vector is input into BiLSTM for forecasting.

Results

The power load data set from the New England in United States is used to simulate and verify the correctness and validity of the proposed method.

Conclusion

With the comparison of the forecasting results between different load forecasting models, the results show that the forecasting accuracy of the proposed method is higher and it is verified that the load time-varying trend mapping method proposed can improve the forecasting accuracy of different models in varying degrees.

© 2025 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/eeng/10.2174/0123520965263452231113074046
2025-05-01
2025-09-05

  • From This Site

    /content/journals/eeng/10.2174/0123520965263452231113074046
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. LuY. TengY. WangH. Load prediction in power system with grey theory and its diagnosis of stabilization.Electr. Power Compon. Syst.2019476-761962810.1080/15325008.2019.1587648
     [Google Scholar]
  2. ChenK. ChenK. WangQ. HeZ. HuJ. HeJ. Short-term load forecasting with deep residual networks.IEEE Trans. Smart Grid20191043943395210.1109/TSG.2018.2844307
     [Google Scholar]
  3. TangX. ChenH. XiangW. YangJ. ZouM. Short-term load forecasting using channel and temporal attention based temporal convolutional network.Electr. Power Syst. Res.202220510776110.1016/j.epsr.2021.107761
     [Google Scholar]
  4. MohanD.P. SubathraM.S.P. A comprehensive review of various machine learning techniques used in load forecasting.Recent Adv. Electr. Electron. Eng.202316319721010.2174/2352096515666220930144336
     [Google Scholar]
  5. MaC. SunY. PengD. ZhaoH Multivariate load forecasting for integrated energy system based on XGBoost-MTLElectric Power Engineering Technology422023515816610.12158/j.2096‑3203.2023.05.018
     [Google Scholar]
  6. KimY. SonH. KimS. Short term electricity load forecasting for institutional buildings.Energy Rep.201951270128010.1016/j.egyr.2019.08.086
     [Google Scholar]
  7. AmjadyN. Short-term hourly load forecasting using time-series modeling with peak load estimation capability.IEEE Trans. Power Syst.200116349850510.1109/59.932287
     [Google Scholar]
  8. ZhaoT. WangJ. ZhangY. Day-ahead hierarchical probabilistic load forecasting with linear quantile regression and empirical copulas.IEEE Access20197809698097910.1109/ACCESS.2019.2922744
     [Google Scholar]
  9. PombeiroH. SantosR. CarreiraP. SilvaC. SousaJ.M.C. Comparative assessment of low-complexity models to predict electricity consumption in an institutional building: Linear regression vs. fuzzy modeling vs. neural networks.Energy Build.201714614115110.1016/j.enbuild.2017.04.032
     [Google Scholar]
  10. DongX. DengS. WangD. A short-term power load forecasting method based on k-means and SVM.J. Ambient Intell. Humaniz. Comput.202213115253526710.1007/s12652‑021‑03444‑x
     [Google Scholar]
  11. GoehryB. GoudeY. MassartP. PoggiJ.M. Aggregation of multi-scale experts for bottom-up load forecasting.IEEE Trans. Smart Grid20201131895190410.1109/TSG.2019.2945088
     [Google Scholar]
  12. LinJ. MaJ. ZhuJ. CuiY. Short-term load forecasting based on LSTM networks considering attention mechanism.Int. J. Electr. Power Energy Syst.202213710781810.1016/j.ijepes.2021.107818
     [Google Scholar]
  13. 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]
  14. YangW. LiuY. ShuQ. A short-term load forecasting model based on CEEMD.Power System Technology20224693615362210.13335/j.1000‑3673.pst.2021.2583
     [Google Scholar]
  15. SajjadM. KhanZ.A. UllahA. HussainT. UllahW. LeeM.Y. BaikS.W. A novel CNN-GRU-based hybrid approach for short-term residential load forecasting.IEEE Access2020814375914376810.1109/ACCESS.2020.3009537
     [Google Scholar]
  16. ZhangJ. WeiY.M. LiD. TanZ. ZhouJ. Short term electricity load forecasting using a hybrid model.Energy201815877478110.1016/j.energy.2018.06.012
     [Google Scholar]
  17. AbediniaO. AmjadyN. ZareipourH. A new feature selection technique for load and price forecast of electrical power systems.IEEE Trans. Power Syst.2017321627410.1109/TPWRS.2016.2556620
     [Google Scholar]
  18. ZhengR. GuJ. JinZ. PengH. CaiL. Research on short-term load forecasting variable selection based on fusion of data driven method and forecast error driven method.Zhongguo Dianji Gongcheng Xuebao202040248749910.13334/j.0258‑8013.pcsee.181740
     [Google Scholar]
  19. LiuY. ZhaoQ. Ultra-short-term power load forecasting based on cluster empirical mode decomposition of CNN-LSTM.Power System Technology202145114444445110.13335/j.1000‑3673.pst.2021.0016
     [Google Scholar]
  20. MaY. ZhangQ. DingJ. WangQ. MaJ. Short term load forecasting based on iForest-LSTM2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2019pp. 2278-2282 Xi’an, China10.1109/ICIEA.2019.8833755
     [Google Scholar]
  21. LianH. WangS. GaoN. QuF. WangH. XieC. YangB. A short-term LOAD forecasting method based on EEMD-LN-GRU2021 3rd Asia Energy and Electrical Engineering Symposium (AEEES), 2021pp. 666-673 Chengdu, China10.1109/AEEES51875.2021.9403230
     [Google Scholar]
  22. YiS. LiuH. ChenT. ZhangJ. FanY. A deep LSTM‐CNN based on self‐attention mechanism with input data reduction for short‐term load forecasting.IET Gener. Transm. Distrib.20231771538155210.1049/gtd2.12763
     [Google Scholar]
  23. RafiS.H. Nahid-Al-Masood DeebaS.R. HossainE. A short-term load forecasting method using integrated CNN and LSTM network.IEEE Access20219324363244810.1109/ACCESS.2021.3060654
     [Google Scholar]
  24. BoharaB. FernandezR. I. GollapudiV. Short-term aggregated residential load forecasting using BiLSTM and CNN-BiLSTM.Int. Conf. Innov. Intell. Informatics, Comput., Technol., 3ICT, 2022pp. 37-43 Sakheer, Bahrain10.1109/3ICT56508.2022.9990696
     [Google Scholar]
  25. ShuklaA. GuptaA.K. Electric load forecasting through CNN: a deep learning approach considering weather dataIEEE Power India Int. Conf., PIICON, 2022pp. 1-6 New Delhi, India10.1109/PIICON56320.2022.10045288
     [Google Scholar]
  26. ShangC. GaoJ. LiuH. LiuF. Short-term load forecasting based on PSO-KFCM daily load curve clustering and CNN-LSTM model.IEEE Access20219503445035710.1109/ACCESS.2021.3067043
     [Google Scholar]
  27. WangY. GanD. SunM. ZhangN. LuZ. KangC. Probabilistic individual load forecasting using pinball loss guided LSTM.Appl. Energy2019235102010.1016/j.apenergy.2018.10.078
     [Google Scholar]
  28. ZhuL. XunZ. WangY. CuiQ. ChenW. LouJ. Short-term power load forecasting based on CNN-BiLSTM.Power System Technology202145114532453910.13335/j.1000‑3673.pst.2021.0470
     [Google Scholar]
  29. ISO New England Inc Energy, load, and demand reports.2014Available from: https://www.iso-ne.com/isoexpress/web/reports/load-and-demand/-/tree/zone-info
  30. JebliI. BelouadhaF.Z. KabbajM.I. TiliouaA. Prediction of solar energy guided by pearson correlation using machine learning.Energy202122412010910.1016/j.energy.2021.120109
     [Google Scholar]
  31. ChoiJ.H. Investigation of the correlation of building energy use intensity estimated by six building performance simulation tools.Energy Build.2017147142610.1016/j.enbuild.2017.04.078
     [Google Scholar]
/content/journals/eeng/10.2174/0123520965263452231113074046
Loading
Short-term Load Forecasting Based on CNN-bilstm Considering Load Time-varying Trend Mapping
Recent Advances in Electrical & Electronic Engineering 18, 415 (2025); https://doi.org/10.2174/0123520965263452231113074046
/content/journals/eeng/10.2174/0123520965263452231113074046
/content/journals/eeng/10.2174/0123520965263452231113074046
Loading

Data & Media loading...


  • Article Type:     Research Article
Keyword(s): bi-directional long short-term memory network; convolutional neural network; feature vector; load time-varying trend mapping; neural network and vector; Short-term load forecasting

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