Skip to main content
SpringerLink
Log in

Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network

  • Special Issue
  • Published:
Evolutionary Intelligence Aims and scope Submit manuscript

Abstract

With the rapid development of smart grid, to solve the power enterprises’ requirement in short-term load forecasting, this paper proposes a short-term electrical load forecasting method based on stacked auto-encoding and GRU (Gated recurrent unit) neural network. Firstly, the method input historical data which contains power load, weather information, and holiday information, and use auto-encoding to compress the historical data; and then, the multi-layer GRU is used to construct the model to predict the power load. The experiment results show, compared with traditional models, the proposed method can effectively predict the daily variation of power load and have lower prediction error and higher precision.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Jetcheva JG, Majidpour M, Chen WP (2014) Neural network model ensembles for building-level electricity load forecasts. Energy Build 84:214–223

    Article  Google Scholar 

  2. Mulyadi Y, Abdullah AG, Rohmah KA (2017) Optimize short term load forcasting anomalous based feed forward backpropagation. IOP Conf Ser Mater Sci Eng 180(1):12–76

    Google Scholar 

  3. Akkar HA, Ali WH (2018) Estimation load forecasting based on the intelligent systems. Al-Nahrain J Eng Sci 21(2):285–291

    Article  Google Scholar 

  4. Hong T, Wilson J, Xie J (2014) Long term probabilistic load forecasting and normalization with hourly information. IEEE Trans Smart Grid 5(1):456–462

    Article  Google Scholar 

  5. Chen F, Xu J, Wang C (2015) Research on building cooling and heating load prediction model on user’s side in energy internet system. Proc CSEE 35(14):3678–3684

    Google Scholar 

  6. Hinton GE, Osindero S, Teh YW (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554

    Article  MathSciNet  MATH  Google Scholar 

  7. Brown RH, Vitullo SR, Corliss GF et al (2015) Detrending daily natural gas consumption series to improve short-term forecasts. In: Power and energy society general meeting, IEEE. IEEE, pp 1–5

  8. Brown RH, Vitullo SR, Corliss GF, Adya M, Kaefer PE, Povinelli RJ (2015) Detrending daily natural gas consumption series to improve short-term forecasts. In: Power and energy society general meeting, 2015 IEEE (pp 1–5). IEEE

  9. Hong T, Fan S (2016) Probabilistic electric load forecasting: A tutorial review. Int J Forecast 32(3):914–938

    Article  Google Scholar 

  10. Peng C, Liu G, Sun H (2012) Wind speed forecasting based on wavelet decomposition and differential evolution-support vector machine for wind farms. Electric Power Autom Equip 32(1):9–13

    Google Scholar 

  11. Sun H, Xie B, Tian Y, Li Z (2017) Forecasting of short-term power load of SecRPSO-SVM based on data-driven. J Syst Simul 29(8):1829–1836

    Google Scholar 

  12. Zhang Y, Hu B, Li S, Luo Y (2017) The short-term power load forecasting model of combing ILMD and ESN based on similar days searching. J Zhengzhou Univ (Nat Sci Edition) 49(2):121–127

    Google Scholar 

  13. Xiao L, Wang J, Hou R, Wu J (2015) A combined model based on data pre-analysis and weight coefficients optimization for electrical load forecasting. Energy 82:524–549

    Article  Google Scholar 

  14. Quan H, Srinivasan D, Khosravi A (2014) Short-term load and wind power forecasting using neural network-based prediction intervals. IEEE Trans Neural Netw Learn Syst 25(2):303–315

    Article  Google Scholar 

  15. Shi J, Tan T, Guo J, Liu Y, Zhang J (2018) Multi-task learning based on deep architecture for various types of load forecasting in regional energy system integration. Power Syst Technol 42(3):698–707

    Google Scholar 

  16. Xu Y, Fang L, Zhao D, Wang K (2017) Electricity consumption prediction based on LSTM neural networks. Power Systems Big Data 20(8):25–29

    Google Scholar 

  17. Zhang P, Ma X, Zhang W, Lin S, Chen H, Yirun AL, Xiao G (2015) Multimodal fusion for sensor data using stacked autoencoders. In: 2015 IEEE tenth international conference on intelligent sensors, sensor networks and information processing (ISSNIP), pp 1–2. IEEE

  18. Shi X, Zhu Y, Ning X, Wang LW, Sun G, Chen GQ (2016) Transformer fault diagnosis based on deep auto-encoder network. Electric Power Autom Equip 36(5):122–126

    Google Scholar 

  19. Li Y, Huang J, Wang H, Zhong N (2017) Study of emotion recognition based on fusion multi-modal bio-signal with SAE and LSTM recurrent neural network. J Commun 38(12):109–120

    Google Scholar 

  20. Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5–6):602–610

    Article  Google Scholar 

  21. Gers FA, Schmidhuber J, Cummins F (1999) Learning to forget: continual prediction with LSTM. In: 9th international conference on artificial neural networks: ICANN ’99, pp 850–855, ICANN

  22. Greff K, Srivastava RK, Koutník J, Steunebrink BR, Schmidhuber J (2017) LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst 28(10):2222–2232

    Article  MathSciNet  Google Scholar 

  23. Niu Z, Yu Z, Li B, Tang W (2018) Short-term wind power forecasting model based on deep gated recurrent unit neural network. Electric Power Autom Equip 38(5):36–42

    Google Scholar 

Download references

Acknowledgements

This work was supported in part by the Scientific and Technological Planning Project of Jilin Province (20180101057JC). A Project Supported by Scientific and Technological Planning Project of Jilin Province (2018C0361).

Author information

Authors and Affiliations

  1. Baicheng Power Supply Company, State Grid Jilin Electric Power Company Limited, Changchun, China

    Kang Ke & Zhang Chengkang

  2. School of Electrical Engineering, Changchun Institute of Technology, Changchun, China

    Sun Hongbin

  3. Department of Electrical Engineering, Texas A&M University, College Station, USA

    Carl Brown

Authors
  1. Kang Ke
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sun Hongbin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhang Chengkang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Carl Brown
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sun Hongbin.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ke, K., Hongbin, S., Chengkang, Z. et al. Short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network. Evol. Intel. 12, 385–394 (2019). https://doi.org/10.1007/s12065-018-00196-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12065-018-00196-0

Keywords

Search

Navigation