A novel recurrent neural network approach in forecasting short term solar irradiance.

Journal: ISA transactions
Published Date:

Abstract

Forecasting solar irradiance is of utmost importance in supplying renewable energy efficiently and timely. This paper aims to experiment five variants of recurrent neural networks (RNN), and develop effective and reliable 5-minute short term solar irradiance prediction models. The 5 RNN classes are long-short term memory (LSTM), gated recurrent unit (GRU), Simple RNN, bidirectional LSTM (Bi-LSTM), and bidirectional GRU (Bi-GRU); the first 3 classes are unidirectional and the last two are bidirectional RNN models. The 26 months data under consideration, exhibits extremely volatile weather conditions in Jinju city, South Korea. Therefore, after different experimental processes, 5 hyper-parameters were selected for each model cautiously. In each model, different levels of depth and width were tested; moreover, a 9-fold cross validation was applied to distinguish them against high variability in the seasonal time-series dataset. Generally the deeper architectures of the aforementioned models had significant outcomes; meanwhile, the Bi-LSTM and Bi-GRU provided more accurate predictions as compared to the unidirectional ones. The Bi-GRU model provided the lowest RMSE and highest R values of 46.1 and 0.958; additionally, it required 5.25*10 seconds per trainable parameter per epoch, the lowest incurred computational cost among the mentioned models. All 5 models performed differently over the four seasons in the 9-fold cross validation test. On average, the bidirectional RNNs and the simple RNN model showed high robustness with less data and high temporal data variability; although, the stronger architectures of the bidirectional models, deems their results more reliable.

Authors

  • Mustafa Jaihuni
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: mjaihu@gmail.com.
  • Jayanta Kumar Basak
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: basak.jkb@gmail.com.
  • Fawad Khan
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: fawad.pid@gmail.com.
  • Frank Gyan Okyere
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: okyerefrank200@gmail.com.
  • Thavisak Sihalath
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: max7set@gmail.com.
  • Anil Bhujel
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: anil.bhujel@gmail.com.
  • Jihoon Park
    Graduate School of Engineering, Osaka University, 2-1 Yamadaoka, Suita, Osaka 565-0871, Japan.
  • Deog Hyun Lee
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: elqr134@naver.com.
  • Hyeon Tae Kim
    Department of Bio-systems Engineering, Gyeongsang National University (Institute of Smart Farm), Jinju 52828, Republic of Korea. Electronic address: bioani@gnu.ac.kr.