Skip to main content

Advertisement

SpringerLink
Log in

New soft computing model for multi-hours forecasting of global solar radiation

  • Regular Article
  • Published:
The European Physical Journal Plus Aims and scope Submit manuscript

Abstract

The growing development of photovoltaic technology has explored the role of effective solar irradiance forecasting in grid security and stability However, due to its non-stationary nature and complexity, make its estimating extremely difficult. The scope of this work is to deal with this issue by introducing a new machine learning forecasting architecture for multi-hours ahead in multiple-site in Algeria. Specifically, we proposed a new decomposition-based ensemble-forecasting model. The developed forecasting strategy based on a new multi-scale decomposition algorithm named Iterative Filtering (IF) used as a pre-processing stage of the historical solar radiation data combined with Gaussian Process Regression (GPR) as an essence predictor to build an IF-GPR model. Hourly global solar radiation data of two years from different cities with diverse solar radiation profiles are used to validate the full potential of the newly proposed IF-GPR model. The performance of the proposed IF-GPR is rigorously assessed utilizing effective metrics and comparing its performance with the reference model. The forecasting results demonstrate the potential of the hybridization IF-GPR methodology for multi-hour forecasting up to four hours ahead. The forecasting errors in terms of normalized root-mean-square error for four hours ahead are as follows: 0.7, 2.45, 5.496, and 9.76 for the Algiers site; 0.373, 1.34, 2.81 and 11.22 for the Ghardaia region, while the attained results for the Adrar site are equal to: 0.525, 1.36, 2.73, and 4.73. Furthermore, the proposed IF method outperforms the recently introduced decomposition algorithm, complete ensemble empirical mode decomposition with adaptive noise, in boosting the forecasting ability of a stand-alone 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

Similar content being viewed by others

Abbreviations

BiLSTM:

Bi-directional long short-term memory

BPNN:

Back propagation neural network

CDELA:

Decomposition-clustering based ensemble learning approach

CDER:

Renewable energy development center

CEEMDAN:

Complete ensemble empirical mode decomposition with adaptive noise

CELA:

Cluster-based ensemble learning approach

DELA:

Decomposition-based ensemble learning approach

DTC-FADF:

Deep Time-series clustering feature attention deep forecasting model

EELA:

Evolutionary-based ensemble learning approach

EEMD:

Ensemble empirical mode decomposition

ELT:

Ensemble learning techniques

EMD:

Empirical mode decomposition

GELA:

General ensemble learning approaches

GHI:

Global solar radiation

GPR:

Combined with Gaussian process regression

IF:

Iterative filtering decomposition method

Kc:

Clear-sky index

LSTM:

Long short-term memory

MABE:

Mean absolute bias error

MEMD:

Multivariate empirical mode decomposition

MMFF:

Multi-model forecasting framework

MOS:

Model output statistics

NMAE:

Normalized mean absolute error

nRMSE:

Normalized root-mean-square error

nRMSE:

Normalized root-mean-square error

NWP:

Numerical weather prediction models

PV:

Photovoltaic

r :

Correlation coefficient

RE:

Regression

RELA:

Residual-based ensemble learning approach

RF:

Random forest

RMSE:

Root-mean-square error

RNN:

Recurrent neural network's

SVD:

Singular value decomposition

URAER:

Renewable energy applied research unit

URER-MS:

Research unit in renewable energies in saharan medium

WPD-CNN-LSTM-MLP:

Wavelet packet decomposition convolutional neural network long short-term memory networks, and multi-layer perceptron network

WT:

Wavelet transform

\(\rho\) :

Lag value

\(\sigma_{s}\) :

Sparse solution

\(r_{s}\) :

Residual

References

  1. N. Bailek, K Bouchouicha, M. EL-Shimy, A. Slimani, Updated status of renewable and sustainable energy projects in Algeria. Econ. Var. Renew. Sources Electr. Power Prod. (2017).

  2. M. Guermoui, R. Abdelaziz, K. Gairaa, L. Djemoui, New Temperature-based predicting model for global solar radiation using support vector regression new temperature-based predicting model for global solar radiation using support vector regression. Int. J. Ambient Energy (2019). https://doi.org/10.1080/01430750.2019.1708792

    Article  Google Scholar 

  3. M. Diagne, M. David, J. Boland, N. Schmutz, P. Lauret, Post-processing of solar irradiance forecasts from WRF model at Reunion Island. Sol. Energy 105, 99–108 (2014). https://doi.org/10.1016/j.solener.2014.03.016

    Article  ADS  Google Scholar 

  4. J. Du, Q. Min, P. Zhang, J. Guo, J. Yang, B. Yin, Short-term solar irradiance forecasts using sky images and radiative transfer model. Energies (2018). https://doi.org/10.3390/en11051107

    Article  Google Scholar 

  5. L. Mazorra Aguiar, J. Polo, J.M. Vindel, A. Oliver, Analysis of satellite derived solar irradiance in islands with site adaptation techniques for improving the uncertainty. Renew. Energy (2019). https://doi.org/10.1016/j.renene.2018.11.099

    Article  Google Scholar 

  6. A. Razagui, K. Abdeladim, K. Bouchouicha, N. Bachari, S. Semaoui, A.A. Hadj, A new approach to forecast solar irradiances using WRF and libRadtran models, validated with MERRA-2 reanalysis data and pyranometer measures. Sol. Energy 221, 148–161 (2021). https://doi.org/10.1016/j.solener.2021.04.024

    Article  ADS  Google Scholar 

  7. K. Bouchouicha, N. Bailek, M. Bellaoui, B. Oulimar, D. Benatiallah, ANN-based correction model of radiation and temperature for solar energy application in South of Algeria. Lect. Notes Netw. Syst. (2021). https://doi.org/10.1007/978-3-030-63846-7_55

    Article  Google Scholar 

  8. Q. Paletta, J. Lasenby, A temporally consistent image-based sun tracking algorithm for solar energy forecasting applications. ArXiv (2020)

  9. J. Jiang, Q. Lv, X. Gao, The ultra-short-term forecasting of global horizonal irradiance based on total sky images. Remote Sens. (2020). https://doi.org/10.3390/rs12213671

    Article  Google Scholar 

  10. G. Notton, C. Voyant, A. Fouilloy, J.L. Duchaud, M.L. Nivet, Some applications of ANN to solar radiation estimation and forecasting for energy applications. Appl. Sci. (2019). https://doi.org/10.3390/app9010209

    Article  Google Scholar 

  11. Y. Yu, J. Cao, J. Zhu, An LSTM short-term solar irradiance forecasting under complicated weather conditions. IEEE Access 7, 145651–145666 (2019)

    Article  Google Scholar 

  12. J. Lee et al., Reliable solar irradiance prediction using ensemble learning-based models: A comparative study. Energy Convers Manage 208, 112582 (2020)

    Article  Google Scholar 

  13. M. Guermoui, F. Melgani, K. Gairaa, M.L. Mekhalfi, A comprehensive review of hybrid models for solar radiation forecasting. J. Clean Prod. 258, 120357 (2020). https://doi.org/10.1016/j.jclepro.2020.120357

    Article  Google Scholar 

  14. B. Gao, X. Huang, J. Shi, Y. Tai, J. Zhang, Hourly forecasting of solar irradiance based on CEEMDAN and multi-strategy CNN-LSTM neural networks. Renew. Energy 162, 1665–1683 (2020). https://doi.org/10.1016/j.renene.2020.09.141

    Article  Google Scholar 

  15. S. Ghimire, R.C. Deo, N. Raj, J. Mi, Wavelet-based 3-phase hybrid SVR model trained with satellite-derived predictors, particle swarm optimization and maximum overlap discrete wavelet transform for solar radiation prediction. Renew. Sustain Energy Rev. 113, 109247 (2019). https://doi.org/10.1016/j.rser.2019.109247

    Article  Google Scholar 

  16. R. Prasad, M. Ali, Y. Xiang, H. Khan, A double decomposition-based modelling approach to forecast weekly solar radiation. Renew. Energy 152, 9–22 (2020). https://doi.org/10.1016/j.renene.2020.01.005

    Article  Google Scholar 

  17. Y. Wang, L. Wu, On practical challenges of decomposition-based hybrid forecasting algorithms for wind speed and solar irradiation. Energy 112, 208–220 (2016). https://doi.org/10.1016/j.energy.2016.06.075

    Article  Google Scholar 

  18. R. Prasad, M. Ali, P. Kwan, H. Khan, Designing a multi-stage multivariate empirical mode decomposition coupled with ant colony optimization and random forest model to forecast monthly solar radiation. Appl. Energy 236, 778–792 (2019). https://doi.org/10.1016/j.apenergy.2018.12.034

    Article  Google Scholar 

  19. S. Sun, S. Wang, G. Zhang, J. Zheng, A decomposition-clustering-ensemble learning approach for solar radiation forecasting. Sol. Energy 163, 189–199 (2018). https://doi.org/10.1016/j.solener.2018.02.006

    Article  ADS  Google Scholar 

  20. F.F. Li, S.Y. Wang, J.H. Wei, Long term rolling prediction model for solar radiation combining empirical mode decomposition (EMD) and artificial neural network (ANN) techniques. J. Renew. Sustain Energy 10, 013704 (2018). https://doi.org/10.1063/1.4999240

    Article  Google Scholar 

  21. S.Y. Wang, J. Qiu, F.F. Li, Hybrid decomposition-reconfiguration models for long-term solar radiation prediction only using historical radiation records. Energies (2018). https://doi.org/10.3390/en11061376

    Article  Google Scholar 

  22. A. Aghmadi, S. El Hani, H. Mediouni, N. Naseri, F. El Issaoui, Hybrid solar forecasting method based on empirical mode decomposition and back propagation neural network. E3S Web Conf. 231:0–4(2021)

  23. X. Huang, J. Shi, B. Gao, Y. Tai, Z. Chen, J. Zhang, Forecasting hourly solar irradiance using hybrid wavelet transformation and elman model in smart grid. IEEE Access 7, 139909–139923 (2019). https://doi.org/10.1109/ACCESS.2019.2943886

    Article  Google Scholar 

  24. T. Peng, C. Zhang, J. Zhou, M.S. Nazir, An integrated framework of Bi-directional long-short term memory (BiLSTM) based on sine cosine algorithm for hourly solar radiation forecasting. Energy 221, 119887 (2021). https://doi.org/10.1016/j.energy.2021.119887

    Article  Google Scholar 

  25. M.K. Behera, N. Nayak, A comparative study on short-term PV power forecasting using decomposition based optimized extreme learning machine algorithm. Eng. Sci. Technol. Int. J. 23, 156–167 (2019). https://doi.org/10.1016/j.jestch.2019.03.006

    Article  Google Scholar 

  26. D. Niu, K. Wang, L. Sun, J. Wu, X. Xu, Short-term photovoltaic power generation forecasting based on random forest feature selection and CEEMD: a case study. Appl. Soft Comput. J. 93, 106389 (2020). https://doi.org/10.1016/j.asoc.2020.106389

    Article  Google Scholar 

  27. M. Guermoui, K. Bouchouicha, N. Bailek, J.W. Boland, Forecasting intra-hour variance of photovoltaic power using a new integrated model. Energy Convers. Manag. 245, 114569 (2021). https://doi.org/10.1016/j.enconman.2021.114569

    Article  Google Scholar 

  28. M. Lefèvre, A. Oumbe, P. Blanc, B. Espinar, B. Gschwind, Z. Qu et al., McClear: A new model estimating downwelling solar radiation at ground level in clear-sky conditions. Atmos. Meas. Tech. (2013). https://doi.org/10.5194/amt-6-2403-2013

  29. M. Guermoui, S. Benkaciali, K. Gairaa, J.W. Boland, A novel ensemble learning approach for hourly global solar radiation forecasting. Neural Comput. Appl. (2021). https://doi.org/10.1007/s00521-021-06421-9

    Article  Google Scholar 

  30. M. Guermoui, J. Boland, A. Rabehi, On the use of BRL model for daily and hourly solar radiation components assessment in a semiarid climate. Eur. Phys. J. Plus (2020). https://doi.org/10.1140/epjp/s13360-019-00085-0

    Article  Google Scholar 

  31. M. Guermoui, A. Rabehi, Soft computing for solar radiation potential assessment in Algeria. Int. J. Ambient Energy (2018). https://doi.org/10.1080/01430750.2018.1517686

    Article  Google Scholar 

  32. D. Jia, J. Hua, L. Wang, Y. Guo, H. Guo, P. Wu et al., Estimations of global horizontal irradiance and direct normal irradiance by using fengyun-4a satellite data in northern china. Remote Sens. 13, 1–15 (2021). https://doi.org/10.3390/rs13040790

    Article  Google Scholar 

  33. M. Guermoui, A. Rabehi, K. Gairaa, S. Benka-, EPJ Plus (2018). https://doi.org/10.1140/epjp/i2018-11845-y

    Article  Google Scholar 

  34. A. Cicone, Iterative filtering as a direct method for the decomposition of nonstationary signals. Numer. Algorithms 85, 811–827 (2020). https://doi.org/10.1007/s11075-019-00838-z

    Article  MathSciNet  MATH  Google Scholar 

  35. J. Yuan, K. Wang, T. Yu, M. Fang, Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression. Int. J. Mach. Tools Manuf. (2008). https://doi.org/10.1016/j.ijmachtools.2007.07.011

    Article  Google Scholar 

  36. K. Wang, T. Chen, R. Lau, Bagging for robust non-linear multivariate calibration of spectroscopy. Chemom. Intell. Lab. Syst. (2011). https://doi.org/10.1016/j.chemolab.2010.10.004

    Article  Google Scholar 

  37. Y. Liu, Z. Gao, Real-time property prediction for an industrial rubber-mixing process with probabilistic ensemble Gaussian process regression models. J. Appl. Polym. Sci. (2015). https://doi.org/10.1002/app.41432

    Article  Google Scholar 

  38. M. Guermoui, K. Gairaa, A. Rabehi, D. Djafer, S. Benkaciali, EPJ Plus (2018). https://doi.org/10.1140/epjp/i2018-12029-7

    Article  Google Scholar 

  39. A.Y. Sun, D. Wang, X. Xu, Monthly streamflow forecasting using Gaussian process regression. J. Hydrol. 511, 72–81 (2014). https://doi.org/10.1016/j.jhydrol.2014.01.023

    Article  ADS  Google Scholar 

  40. A. Kumler, Y. Xie, Y. Zhang, A physics-based smart persistence model for intra-hour forecasting of solar radiation (PSPI) using GHI measurements and a cloud retrieval technique. Sol. Energy 177, 494–500 (2019). https://doi.org/10.1016/j.solener.2018.11.046

    Article  ADS  Google Scholar 

  41. A. Fouilloy, C. Voyant, G. Notton, F. Motte, C. Paoli, M.L. Nivet et al., Solar irradiation prediction with machine learning: forecasting models selection method depending on weather variability. Energy (2018). https://doi.org/10.1016/j.energy.2018.09.116

    Article  Google Scholar 

  42. R. Perez et al., Short-term irradiance variability: Preliminary estimation of station pair correlation as a function of distance. Solar Energy 86(8), 2170–2176 (2012)

    Article  ADS  Google Scholar 

  43. A. Rabehi, M. Guermoui, D. Lalmi, Hybrid models for global solar radiation prediction: a case study. Int. J. Ambient Energy 41, 31–40 (2020). https://doi.org/10.1080/01430750.2018.1443498

    Article  Google Scholar 

  44. M. Guermoui, K. Gairaa, J. Boland, T. Arrif, A novel hybrid model for solar radiation forecasting using support vector machine and bee colony optimization algorithm: review and case study. J. Sol. Energy Eng. Trans. ASME (2021). https://doi.org/10.1115/1.4047852

    Article  Google Scholar 

  45. K. Bouchouicha, M.A. Hassan, N. Bailek, N. Aoun, Estimating the global solar irradiation and optimizing the error estimates under Algerian desert climate. Renew. Energy 139, 844–858 (2019). https://doi.org/10.1016/j.renene.2019.02.071

    Article  Google Scholar 

  46. Z. Dong, D. Yang, T. Reindl, W.M. Walsh, A novel hybrid approach based on self-organizing maps, support vector regression and particle swarm optimization to forecast solar irradiance. Energy 82, 570–577 (2015). https://doi.org/10.1016/j.energy.2015.01.066

    Article  Google Scholar 

  47. F.O. Hocaoglu, F. Serttas, A novel hybrid (Mycielski-Markov) model for hourly solar radiation forecasting. Renew. Energy 108, 635–643 (2017). https://doi.org/10.1016/j.renene.2016.08.058

    Article  Google Scholar 

  48. D. Yang, V. Sharma, Z. Ye, L.I. Lim, L. Zhao, A.W. Aryaputera, Forecasting of global horizontal irradiance by exponential smoothing, using decompositions. Energy 81, 111–119 (2015). https://doi.org/10.1016/j.energy.2014.11.082

    Article  Google Scholar 

  49. R. Jovanovic, L.M. Pomares, Y.E. Mohieldeen, D. Perez-Astudillo, D. Bachour, An evolutionary method for creating ensembles with adaptive size neural networks for predicting hourly solar irradiance. In Proc. Int. Jt. Conf. Neural Networks, vol. 2017-May. Institute of Electrical and Electronics Engineers Inc. (2017), pp. 1962–1967. doi:https://doi.org/10.1109/IJCNN.2017.7966091.

  50. C. Voyant, M. Muselli, C. Paoli, M.L. Nivet, Numerical weather prediction (NWP) and hybrid ARMA/ANN model to predict global radiation. Energy 39, 341–355 (2012). https://doi.org/10.1016/j.energy.2012.01.006

    Article  Google Scholar 

  51. C. Voyant, M. Muselli, C. Paoli, M.L. Nivet, Hybrid methodology for hourly global radiation forecasting in Mediterranean area. Renew. Energy 53, 1–11 (2013). https://doi.org/10.1016/j.renene.2012.10.049

    Article  Google Scholar 

  52. J. Huang, M. Korolkiewicz, M. Agrawal, J. Boland, Forecasting solar radiation on an hourly time scale using a coupled autoregressive and dynamical system (CARDS) model. Sol. Energy 87, 136–149 (2013). https://doi.org/10.1016/j.solener.2012.10.012

    Article  ADS  Google Scholar 

  53. C. Voyant, C. Darras, M. Muselli, C. Paoli, M.L. Nivet, P. Poggi, Bayesian rules and stochastic models for high accuracy prediction of solar radiation. Appl. Energy 114, 218–226 (2014). https://doi.org/10.1016/j.apenergy.2013.09.051

    Article  Google Scholar 

  54. C. Sing Lai, C. Zhong, K. Pan, W.W.Y. Ng, L.L. Lei, A deep learning based hybrid method for hourly solar radiation forecasting. Expert Syst. Appl. (2021). https://doi.org/10.1016/j.eswa.2021.114941

    Article  Google Scholar 

  55. X. Huang, Q. Li, Y. Tai, Z. Chen, J. Zhang, J. Shi et al., Hybrid deep neural model for hourly solar irradiance forecasting. Renew. Energy (2021). https://doi.org/10.1016/j.renene.2021.02.161

    Article  Google Scholar 

  56. R.H. Inman, H.T.C. Pedro, C.F.M. Coimbra, Solar forecasting methods for renewable energy integration. Prog. Energy Combust. Sci. 39, 535–576 (2013). https://doi.org/10.1016/j.pecs.2013.06.002

    Article  Google Scholar 

Download references

Acknowledgements

We would like to acknowledge the German federal bureau for supplying instrumentations used in this work, as part of the enreMENA project.

Author information

Authors and Affiliations

  1. Unité de Recherche Appliquée en Energies Renouvelables, URAER, Centre de Développement des Energies Renouvelables, CDER, 47133, Ghardaïa, Algeria

    Mawloud Guermoui, Said Benkaciali & Kacem Gairaa

  2. Unité de Recherche en Energies Renouvelables en Milieu Saharien (URERMS), Centre de Développement des Energies Renouvelables (CDER), 01000, Adrar, Algeria

    Kada Bouchouicha

  3. Energies and Materials Research Laboratory, Faculty of Sciences and Technology, University of Tamanghasset, 10034, Tamanrasset, Algeria

    Nadjem Bailek

Authors
  1. Mawloud Guermoui
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kada Bouchouicha
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Said Benkaciali
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Kacem Gairaa
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Nadjem Bailek
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mawloud Guermoui.

Ethics declarations

Conflict of interest

No declaration of interest.

Data Availability Statement

This manuscript has associated data in a data repository. [Authors’ comment: The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.]

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guermoui, M., Bouchouicha, K., Benkaciali, S. et al. New soft computing model for multi-hours forecasting of global solar radiation. Eur. Phys. J. Plus 137, 162 (2022). https://doi.org/10.1140/epjp/s13360-021-02263-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1140/epjp/s13360-021-02263-5

Search

Navigation