Hybrid optimisation and machine learning models for wind and solar data prediction

  1. Amoura, Yahia 13
  2. Torres, Santiago 3
  3. Lima, José 12
  4. Pereira, Ana I. 1
  1. 1 Research Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Politécnico de Bragança, Bragança, Portugal
  2. 2 INESC TEC – INESC Technology and Science, Porto, Portugal
  3. 3 University of Laguna, Laguna, Spain
Mostrar afiliaciones +
Revista:
International Journal of Hybrid Intelligent Systems

ISSN: 1448-5869,  1875-8819

Año de publicación: 2023

Volumen: 19

Número: 1,2

Páginas: 45-60

Tipo: Artículo

DOI: 10.3233/HIS-230004 GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: International Journal of Hybrid Intelligent Systems

Resumen

The exponential growth in energy demand is leading to massive energy consumption from fossil resources causing a negative effects for the environment. It is essential to promote sustainable solutions based on renewable energies infrastructures such as microgrids integrated to the existing network or as stand alone solution. Moreover, the major focus of today is being able to integrate a higher percentages of renewable electricity into the energy mix. The variability of wind and solar energy requires knowing the relevant long-term patterns for developing better procedures and capabilities to facilitate integration to the network. Precise prediction is essential for an adequate use of these renewable sources. This article proposes machine learning approaches compared to an hybrid method, based on the combination of machine learning with optimisation approaches. The results show the improvement in the accuracy of the machine learning models results once the optimisation approach is used.

Referencias bibliográficas

  • Welsby, (2021), Nature, 597, pp. 230, 10.1038/s41586-021-03821-8
  • P. Ekadewi, Moving from New and Renewable Energy to Renewable and CarbonFree Energy, in: Indonesia Post-Pandemic Outlook: Strategy towards Net-Zero Emissions by 2060 from the Renewables and Carbon-Neutral Energy Perspectives, 2022.
  • M.K. Islam, N.M.S. Hassan, M.G. Rasul, K. Emami and A.A. Chowdhury, Green and renewable resources: an assessment of sustainable energy solution for Far North Queensland, Australia, International Journal of Energy and Environmental Engineering (2022).
  • Fatras, (2022), Renewable and Sustainable Energy Reviews, 167, pp. 248
  • Malik, (2022), Archives of Computational Methods in Engineering, 29, pp. 3183, 10.1007/s11831-021-09687-3
  • Goliatt, (2023), Expert Systems with Applications, 212, pp. 118295, 10.1016/j.eswa.2022.118295
  • Zheng, (2023), Renewable and Sustainable Energy Reviews, 172, pp. 113046, 10.1016/j.rser.2022.113046
  • Zhen, (2022), International Journal of Electrical Power and Energy Systems, 135, pp. 107502, 10.1016/j.ijepes.2021.107502
  • Saeed, (2022), Energy, 238, pp. 122012, 10.1016/j.energy.2021.122012
  • Wang, (2022), Journal of Wind Engineering and Industrial Aerodynamics, 220, pp. 104873, 10.1016/j.jweia.2021.104873
  • Altan, (2021), Applied Soft Computing, 100, pp. 106996, 10.1016/j.asoc.2020.106996
  • Acikgoz, (2022), Applied Energy, 305, pp. 117912, 10.1016/j.apenergy.2021.117912
  • Elizabeth Michael, (2022), Applied Energy, 324, pp. 119727, 10.1016/j.apenergy.2022.119727
  • Husein, (2019), Energies, 12, pp. 18, 10.3390/en12101856
  • Haider, (2022), Renewable Energy, 198, pp. 51, 10.1016/j.renene.2022.07.136
  • Kariniotakis, (1996), IEEE Transactions on Energy Conversion, 11, pp. 762, 10.1109/60.556376
  • Wang, (2016), Renewable and Sustainable Energy Reviews, 60, pp. 960, 10.1016/j.rser.2016.01.114
  • Wang, (2021), Applied Energy, 304, pp. 117766, 10.1016/j.apenergy.2021.117766
  • Wang, (2018), Energy Conversion and Management, 157, pp. 123, 10.1016/j.enconman.2017.11.080
  • Verbois, (2018), Solar Energy, 162, pp. 265, 10.1016/j.solener.2018.01.007
  • Arbizu-Barrena, (2017), Solar Energy, 155, pp. 1092, 10.1016/j.solener.2017.07.045
  • Erdem, (2011), Applied Energy, 88, pp. 1405, 10.1016/j.apenergy.2010.10.031
  • Maafi, (1989), Solar & Wind Technology, 6, pp. 247, 10.1016/0741-983X(89)90076-3
  • Yang, (2015), Solar Energy, 114, pp. 314, 10.1016/j.solener.2015.01.016
  • K. Bellinguer, R. Girard, G. Bontron and G. Kariniotakis, Short-term Forecasting of Photovoltaic Generation based on Conditioned Learning of Geopotential Fields, in: 55th International Universities Power Engineering Conference (UPEC), 2020.
  • Bae, (2017), IEEE Transactions on Power Systems, 32, pp. 935
  • Liu, (2019), Energy Conversion and Management, 119, pp. 111975, 10.1016/j.enconman.2019.111975
  • Viet, (2020), Energies, 13, pp. 2873, 10.3390/en13112873
  • Yadav, (2014), Renewable and Sustainable Energy Reviews, 33, pp. 772, 10.1016/j.rser.2013.08.055
  • Kotlyar, (2021), Optics Express, 29, pp. 11254, 10.1364/OE.419314
  • Wang, (2016), Applied Energy, 182, pp. 80, 10.1016/j.apenergy.2016.08.108
  • Begam, (2019), Computers & Electrical Engineering, 78, pp. 32, 10.1016/j.compeleceng.2019.06.018
  • Duan, (2021), Energy, 217, pp. 119397, 10.1016/j.energy.2020.119397
  • Neshat, (2021), Energy Conversion and Management, 236, pp. 114002, 10.1016/j.enconman.2021.114002
  • Singh, (2019), Renewable Energy, 136, pp. 758, 10.1016/j.renene.2019.01.031
  • Lv, (2022), Applied Energy, 311, pp. 118674, 10.1016/j.apenergy.2022.118674
  • Wang, (2022), Energy, 251, pp. 123960, 10.1016/j.energy.2022.123960
  • Amoura, (2022), Sustainable Energy for Smart Cities, pp. 189, 10.1007/978-3-030-97027-7_12
  • Y. Ozaki, Y. Takenaga and M. Onishi, Global Search versus Local Search in Hyperparameter Optimisation, in: IEEE Congress on Evolutionary Computation (CEC), 2022.
  • N. Ettaik and B. Habib, Hyperparameter Optimisation in NLP Architectures, in: Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning, 2021.
  • I. Hudalizaman and S. Wibirama, Network Architecture Search Method on Hyperparameter Optimisation of Convolutional Neural Network: Review, in: 6th International Conference on Science and Technology (ICST), 2020.
  • A. Hussain and A. Ludwig, Hyperparameter Optimisation: Comparing Genetic Algorithm against Grid Search and Bayesian Optimisation, in: 2021 IEEE Congress on Evolutionary Computation (CEC), 2021.
  • Hyperparameter tuning of machine learning algorithms using grid search, in: A.K. Das, S. Mishra, S.S. Gopalan, Predicting COVID-19 community mortality risk using machine learning and development of an online prognostic tool, 2020.
  • Adrian-Catalin, (2019), International Journal of Computers Communications Control, 14, pp. 154, 10.15837/ijccc.2019.2.3514
  • S. Prashant and A. Hellander, Hyperparameter optimisation for approximate bayesian computation, in: 2018 Winter Simulation Conference (WSC), 2018.
  • Agrawal, (2020), Hyperparameter Optimisation in Machine Learning, pp. 81
  • Zulfiqar, (2022), Sensors, 22, pp. 4446, 10.3390/s22124446
  • S. Farshad and S. Niaki, Dynamic Meta-Learning Acquisition Function Method for Bayesian Optimisation with Early Stopping Criteria for Hyperparameter Optimisation, SSRN Electronic Journal (2022).
  • Shun, (2019), Journal of the Physical Society of Japan, 88, pp. 074001, 10.7566/JPSJ.88.074001
  • B. Tomohiro et al., Efficient Hyperparameter Optimisation by Using Bayesian Optimisation for Drug-Target Interaction Prediction, in: IEEE 7th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS), 2017.
  • Amoura, (2023), Innovations in BioInspired Computing and Applications: Proceedings of the 13th International Conference on Innovations in Bio-Inspired Computing and Applications (IBICA 2022) Held During December 15-17, 2022, pp. 31, 10.1007/978-3-031-27499-2_4