Short-term solar irradiance forecasting using deep learning models

Abstract

Population growth and evolving consumer technology have resulted in an ever-increasing demand for energy and power. Traditional energy sources such as coal, oil, and gas are not only quickly depleting but have also contributed to global pollution. As a result, the demand for renewable energy for power generation has increased tremendously. Short-term solar irradiance is a critical area in renewable energy for the optimal operation and power prediction of grid-connected photovoltaic (PV) plants and other solar energy applications. However, solar irradiance is complex to handle due to the nonuniform characteristics of inconsistent weather conditions. Deep Learning techniques have shown outstanding performance in modeling these complexities. In this paper, short-term solar forecasting models are proposed using deep learning to reliably predict the amount of solar irradiance for optimal power generation. Furthermore, it is also evaluated whether the model can forecast the amount of Global Horizontal Irradiance (GHI) within one hour given the current recorded features including air temperature, azimuth, cloud opacity, and zenith. The data for Penang, Malaysia is used in this research. A Dense Neural Network (DNN) with 32 units achieved a validation MAE of 21.33 and MSE of 1343.68 in the 6th fold. Long-Short Term Memory (LSTM) with 256 units achieved a validation MAE of 8.23 and MSE of 246.98 in the 7th fold. On test data, the DNN achieved MAE and MSE of 31.71 and 2560.80 respectively whereas the LSTM model achieved MAE and MSE of 5.78 and 106.65 respectively.