Daily Photovoltaic Power Prediction Enhanced by Hybrid GWO-MLP, ALO-MLP and WOA-MLP Models Using Meteorological Information


Colak M., YEŞİLBUDAK M., BAYINDIR R.

ENERGIES, cilt.13, sa.4, 2020 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 13 Sayı: 4
  • Basım Tarihi: 2020
  • Doi Numarası: 10.3390/en13040901
  • Dergi Adı: ENERGIES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Agricultural & Environmental Science Database, CAB Abstracts, Communication Abstracts, Compendex, INSPEC, Metadex, Veterinary Science Database, Directory of Open Access Journals, Civil Engineering Abstracts
  • Anahtar Kelimeler: photovoltaic power, meteorological input, metaheuristic optimization, artificial neural networks, prediction, SHORT-TERM, GENERATION FORECAST, OUTPUT, WIND, SYSTEMS
  • Gazi Üniversitesi Adresli: Evet

Özet

Solar energy is a safe, clean, environmentally-friendly and renewable energy source without any carbon emissions to the atmosphere. Therefore, there are many studies in the field of solar energy in order to obtain the maximum solar radiation during the day time, to estimate the amount of solar energy to be produced, and to increase the efficiency of solar energy systems. In this study, it was aimed to predict the daily photovoltaic power production using air temperature, relative humidity, total horizontal solar radiation and diffuse horizontal solar radiation parameters as multi-tupled inputs. For this purpose, grey wolf, ant lion and whale optimization algorithms were integrated to the multilayer perceptron. In addition, the effects of sigmoid, sinus and hyperbolic tangent activation functions on the prediction performance were analyzed in detail. As a result of overall accuracy indictors achieved, the grey wolf optimization algorithm-based multilayer perceptron model was found to be more successful and competitive for the daily photovoltaic power prediction. Furthermore, many meaningful patterns were revealed about the constructed models, input tuples and activation functions.