Prediction of hourly solar radiation in Indonesia using LSTM

The value of solar radiation has many advantages to support optimal utilization of solar energy, from building design, solar power plant and agricultural system. However, solar radiation is an element that will affect to other weather parameters. Forecasting systems that have been carried out by previous researchers are predictions for data per-hour, per-day, per-month and even per-year. All forecasting processes are carried out using different multivariate meteorological parameters. Fluctuations in solar radiation can occur due to data errors or moving fast of clouds. In this study, we are using meteorological parameter: solar radiation, sun duration, relative humidity, dew point, air temperature, and sky cover. All these parameters will be used to predict hourly solar radiation. Long short-term memory (LSTM) is proposed in our works to discover best activation: ReLU, sigmoid, tanh. As a result, RELU is best activation which has the smallest Mean Square Error (MSE) value is 0.1885, compared with other activation value: sigmoid MSE value is 0.2359 and tanh MSE value is 0.3270. By using ReLU, the wall time is 1min 51s and calculation process stops in 18th epoch. Optimum learning rate become 0.00249 and wall time 1min 38s. The output prediction is hourly solar radiation one-day ahead that we can used as a data solar radiation information.

[1]  Eui-Jong Kim,et al.  Next-Day Prediction of Hourly Solar Irradiance Using Local Weather Forecasts and LSTM Trained with Non-Local Data , 2020, Energies.

[2]  K. Vijayaprabakaran,et al.  Towards activation function search for long short-term model network: A differential evolution based approach , 2020, J. King Saud Univ. Comput. Inf. Sci..

[3]  Shanlin Yang,et al.  A hybrid deep learning model for short-term PV power forecasting , 2020 .

[4]  Ridha Bouallegue,et al.  Deep Learning Forecasting Based on Auto-LSTM Model for Home Solar Power Systems , 2018, 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS).

[5]  Yugang Niu,et al.  Hourly day-ahead solar irradiance prediction using weather forecasts by LSTM , 2018 .

[6]  Amandeep Sharma,et al.  Forecasting daily global solar irradiance generation using machine learning , 2018 .

[7]  Tek Tjing Lie,et al.  Hourly global solar irradiation forecasting for New Zealand , 2015 .

[8]  Michael J. Savage,et al.  Comparison of estimates of daily solar radiation from air temperature range for application in crop simulations , 2008 .

[9]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[10]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  2021 International Seminar on Application for Technology of Information and Communication (iSemantic) , 2021 .

[12]  Sumanta Pasari,et al.  Wind Energy Prediction Using Artificial Neural Networks , 2020, Sustainable Production, Life Cycle Engineering and Management.

[13]  Na Dong,et al.  A novel convolutional neural network framework based solar irradiance prediction method , 2020 .

[14]  Magdy Bayoumi,et al.  Effects of Different Activation Functions for Unsupervised Convolutional LSTM Spatiotemporal Learning , 2019, Advances in Science, Technology and Engineering Systems Journal.