Skip to main content
SpringerLink
Log in

An innovative method-based CEEMDAN–IGWO–GRU hybrid algorithm for short-term load forecasting

  • Original Paper
  • Published:
Electrical Engineering Aims and scope Submit manuscript

Abstract

The accuracy level of short-term load forecasting (STLF) affects the power department's arrangements for unit start-up, shutdown, overhaul, and load dispatching. However, the existing algorithms do not fully consider load volatility and difficulty in setting the algorithm parameters. In this regard, this paper proposes a hybrid model which combines complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), gated recurrent unit (GRU) with improved gray wolf optimizer (IGWO), namely CEEMDAN–IGWO–GRU (CIG) hybrid algorithm. Firstly, the details and trend information of the load signal are separated by the CEEMDAN algorithm to suppress the interference of load fluctuation. Then, the GRU network optimized by IGWO parameters is used to predict each component, separately. Finally, the complete load forecasting results are obtained by reconstructing the forecasting result of each component. The power load data of a certain area under study is used to verify the CIG model, and the experimental results are compared with other existing algorithms. The experimental results show that the load forecasting results of the CIG model get the high-precision evaluation of 0.6997%, 52.4685, and 38.1891 MW in MAPE, RMSE, and MAE, respectively. Therefore, the parameter optimization ability of the IGWO algorithm can effectively improve the prediction accuracy, and the CIG method can availably suppress the impact of load fluctuation on prediction and has a powerful nonlinear fitting ability. In conclusion, CIG has great potential in establishing a power load forecasting model.

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
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Abbreviations

STLF:

Short-term load forecasting

CEEMDAN:

Complete ensemble empirical mode decomposition with adaptive noise

IMF:

Intrinsic mode functions

RES:

The final residue

PE:

Permutation entropy

GRU:

Gated recurrent unit

GWO:

Gray wolf optimizer

IGWO:

Improved gray wolf optimizer

PCCs:

Pearson correlation coefficient

MI:

Mutual information

CIG:

CEEMDAN–IGWO–GRU

MAE:

Mean absolute error

MAPE:

Mean absolute percentage error

RMSE:

Root mean square error

PCCs(*,•):

The pearson correlation coefficient function.

MI(*,•):

The mutual information function.

q(•) :

The marginal probability density function.

p(*,•) :

The joint distribution function.

EMDj(•):

The jth IMF mode obtained by EMD operation.

δ i :

The ith white noise obeying N(0, 1) distribution(i = 1, 2, …, I).

x :

The power load signal

IMF1, IMFk :

The first IMF of the original signal. The kth IMF of the original signal.

r 1, r k, RES:

The first residue. The kth residue. The final residue.

K :

The total number of IMF components.

IMFw, RIRw :

The wth CEEMDAN decomposition (w = 1, 2, …, K + 1). Results of phase space reconstruction for IMFw.

μ :

The embedding dimension.

τ :

The delay time.

L = m − (μ − 1) τ :

The number of reconstruction components of RIRw.

S w(l):

Symbol sequence vectors.

swl1, swl2, …, swlμ :

The column index value corresponding to each element in the original vector after the lth row vector is reordered.

PRc :

The probability of occurrence of cth symbol sequence.

PEw :

The PE of time series IMFw.

h λ,:

The state memory variable at the λ moment.

\(\tilde{h}_{\lambda }\) :

The candidate state memory variable at the λ moment.

x λ n :

The eigenvalue of the nth component is marked.

σ(•):

The sigmoid activation function.

r λ :

The reset gate state.

z λ :

The update gate state.

tanh(•):

The hyperbolic tangent activation function.

W r, W u :

The weight parameter of the reset gate part. The weight parameter of the update gate part.

W o :

The weight parameter for calculating the \(\tilde{h}_{\lambda }\) part.

P ′, P ′′, P :

The random initialization population. The opposite population. The final initial population

lb v :

The lowest search space of the vth parameter to be optimized.

ub v :

The uppest search space of the vth parameter to be optimized.

p e(t):

The position of the eth search agent at the tth iteration (e = α, β, δ).

cd(t):

The random number produced by Cauchy distribution.

a rm(t):

The control factor.

p α v(t), p β v(t), p δ v(t):

The vth dimension positions of the wolf α, β, and δ at the tth iteration, respectively

rand1, rand2 :

The random numbers between [0, 1]

a(t):

The convergence factor.

t :

The current iteration number.

t max :

The maximum number of iterations.

Y pred :

The predictive value.

Y act :

The actual value.

PLs-n :

The historical load value with a time interval of n from the time s.

T s :

Temperature at time s.

D s :

Dew point at time s.

H s :

Humidity at time s.

W s :

Wind speed at time s.

WHs :

Date type at time s

References

  1. Zou H, Tao J, Elsayed SK, Elattar EE, Almalaq A, Mohamed MA (2021) Stochastic multi-carrier energy management in the smart islands using reinforcement learning and unscented transform. Int J Electr Power Energy Syst 130:106988

    Article  Google Scholar 

  2. Mohamed MA, Abdullah HM, El-Meligy MA, Sharaf M, Soliman AT, Hajjiah A (2021) A novel fuzzy cloud stochastic framework for energy management of renewable microgrids based on maximum deployment of electric vehicles. Int J Electr Power Energy Syst 129:106845

    Article  Google Scholar 

  3. Mohamed MA, Almalaq A, Abdullah HM, Alnowibet KA, Alrasheedi AF, Zaindin MSA (2021) A distributed stochastic energy management framework based-fuzzy-PDMM for smart grids considering wind park and energy storage systems. IEEE Access 9:46674–46685

    Article  Google Scholar 

  4. Lan T, Liu X, Wang S, Jermsittiparsert K, Alrashood ST, Rezaei M, Mohamed MA (2021) An advanced machine learning based energy management of renewable microgrids considering hybrid electric vehicles’ charging demand. Energies 14(3):569

    Article  Google Scholar 

  5. Chen J, Alnowibet K, Annuk A, Mohamed MA (2021) An effective distributed approach based machine learning for energy negotiation in networked microgrids. Energy Strategy Rev 38:100760

    Article  Google Scholar 

  6. Santhoshi BK, Mohanasundaram K, Kumar LA (2021) ANN-based dynamic control and energy management of inverter and battery in a grid-tied hybrid renewable power system fed through switched Z-source converter. Electr Eng. https://doi.org/10.1007/s00202-021-01231-7

    Article  Google Scholar 

  7. Su X, Liu T, Cao H, Jiao H, Yu Y, He C, Shen J (2017) A multiple distributed bp neural networks approach for short-term load forecasting based on hadoop framework. Proc CSEE 37(17):4966–4973

    Google Scholar 

  8. Islam B, Baharudin Z, Nallagownden P (2017) Development of chaotically improved meta-heuristics and modified BP neural network-based model for electrical energy demand prediction in smart grid. Neural Comput Appl 28(1):877–891

    Article  Google Scholar 

  9. Li S, Wang P, Goel L (2015) A novel wavelet-based ensemble method for short-term load forecasting with hybrid neural networks and feature selection. IEEE Trans Power Syst 31(3):1788–1798

    Article  Google Scholar 

  10. Ertugrul ÖF (2016) Forecasting electricity load by a novel recurrent extreme learning machines approach. Int J Electr Power Energy Syst 78:429–435

    Article  Google Scholar 

  11. Lahouar A, Slama JBH (2015) Day-ahead load forecast using random forest and expert input selection. Energy Convers Manage 103:1040–1051

    Article  Google Scholar 

  12. Barman M, Choudhury ND, Sutradhar S (2018) A regional hybrid GOA-SVM model based on similar day approach for short-term load forecasting in Assam, India. Energy 145:710–720

    Article  Google Scholar 

  13. Selakov A, Cvijetinović D, Milović L, Mellon S, Bekut D (2014) Hybrid PSO–SVM method for short-term load forecasting during periods with significant temperature variations in city of Burbank. Appl Soft Comput 16:80–88

    Article  Google Scholar 

  14. Dai S, Niu D, Li Y (2018) Daily peak load forecasting based on complete ensemble empirical mode decomposition with adaptive noise and support vector machine optimized by modified grey wolf optimization algorithm. Energies 11:163

    Article  Google Scholar 

  15. Li W, Shi Q, Sibtain M, Li D, Mbanze DE (2020) A hybrid forecasting model for short-term power load based on sample entropy, two-phase decomposition and whale algorithm optimized support vector regression. IEEE Access 8:166907–166921

    Article  Google Scholar 

  16. Bedi J, Toshniwal D (2019) Deep learning framework to forecast electricity demand. Appl Energy 238:1312–1326

    Article  Google Scholar 

  17. Wang S, Wang X, Wang S, Wang D (2019) Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting. Int J Electr Power Energy Syst 109:470–479

    Article  Google Scholar 

  18. Bedi J, Toshniwal D (2018) Empirical mode decomposition based deep learning for electricity demand forecasting. IEEE Access 6:49144–49156

    Article  Google Scholar 

  19. Li C, Tang G, Xue X, Saeed A, Hu X (2019) Short-term wind speed interval prediction based on ensemble GRU model. IEEE Trans Sustain Energy 11(3):1370–1380

    Article  Google Scholar 

  20. de Freitas JT, Coelho FGF (2021) Fault localization method for power distribution systems based on gated graph neural networks. Electr Eng. https://doi.org/10.1007/s00202-021-01223-7

    Article  Google Scholar 

  21. Zhao R, Wang D, Yan R, Mao K, Shen F, Wang J (2017) Machine health monitoring using local feature-based gated recurrent unit networks. IEEE Trans Industr Electron 65(2):1539–1548

    Article  Google Scholar 

  22. Daiyu DENG, Jian LI, Zhenyuan ZHANG (2019) Short-term electric load forecasting based on EEMD-GRU-MLR. Power Syst Technol 55(20):36–43

    Google Scholar 

  23. Li J, Li Q (2015) Medium term electricity load forecasting based on CEEMDAN-permutation entropy and ESN with leaky integrator neurons. Electr Mach Control 19(8):70–80

    Google Scholar 

  24. Torres ME, Colominas MA, Schlotthauer G, Flandrin P (2011) A complete ensemble empirical mode decomposition with adaptive noise. In: 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE. pp 4144–4147

  25. Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46–61

    Article  Google Scholar 

  26. Gu QH, Li XX, Lu CW, Ruan SL (2019) Hybrid genetic grey wolf algorithm for high dimensional complex function optimization. Control and Decision, 1–8

  27. Gupta S, Deep K (2019) A novel random walk grey wolf optimizer. Swarm Evol Comput 44:101–112

    Article  Google Scholar 

  28. Wang Z, Xie H, Hu Z, Li D, Wang J, Liang W (2019) Node coverage optimization algorithm for wireless sensor networks based on improved grey wolf optimizer. J Algorithms Comput Technol 13:1748302619889498

    Article  Google Scholar 

  29. Price Information [EB/OL]. (2020) [Aug, 23]. https://www.emcsg.com/marketdata/priceinformation#priceDataView

  30. Weather Underground [EB/OL]. (2020) [Aug, 23]. https://www.wunderground.com/

  31. Tang X, Dai Y, Liu Q, Dang X, Xu J (2019) Application of bidirectional recurrent neural network combined with deep belief network in short-term load forecasting. IEEE Access 7:160660–160670

    Article  Google Scholar 

  32. Zhou M, Jin M (2017) Holographic ensemble forecasting method for short-term power load. IEEE Trans Smart Grid 10(1):425–434

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Electrical Engineering and Automation, Fuzhou University, Fuzhou, 350116, China

    Zixing Chen, Tao Jin, Xidong Zheng, Yulong Liu & Zhiyuan Zhuang

  2. Fujian Key Laboratory of New Energy Generation and Power Conversion, Fuzhou, 350116, China

    Zixing Chen, Tao Jin, Xidong Zheng, Yulong Liu & Zhiyuan Zhuang

  3. Electrical Engineering Department, Faculty of Engineering, Minia University, Minia, 61519, Egypt

    Mohamed A. Mohamed

Authors
  1. Zixing Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tao Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xidong Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yulong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhiyuan Zhuang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mohamed A. Mohamed
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Tao Jin or Mohamed A. Mohamed.

Additional information

Publisher's Note

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

Appendices

Appendix 1

Prediction results

See Tables 6 and 7.

Table 6 Prediction results of load on December 16, 2019 (Unit: 103 MW)
Full size table
Table 7 Prediction results of load on December 17, 2019 (Unit: 103 MW)
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, Z., Jin, T., Zheng, X. et al. An innovative method-based CEEMDAN–IGWO–GRU hybrid algorithm for short-term load forecasting. Electr Eng 104, 3137–3156 (2022). https://doi.org/10.1007/s00202-022-01533-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00202-022-01533-4

Keywords

Search

Navigation