SOLAR RADIATION FORECASTING USING MACHINE LEARNING TECHNIQUES

Abstract

A well-known statistical modelling method named ARIMA has been used to forecast the total daily solar radiation generated by a solar panel located in a research facility. The beauty of the ARIMA model lies in its simplicity and it can only be applied to stationary time series. So, our time series data, which is seasonal and non-stationary, is transformed into a stationary one for applying the ARIMA model. The model is developed using sophisticated statistical techniques. The optimum model is chosen and validated using Akaike information criterion (AIC) and residual sum of squares (SSE). Another method used for solar radiation prediction is LSTM. Long short-term memory (LSTM) models based on specialized deep neural network based architecture have emerged as an important model for forecasting time-series. existing models are not good at learning long-term historical dependencies, lead to compromise in modeling non- linear solar irradiance patterns. In this paper, a novel prediction model Long Short Term Memory (LSTM) from deep neural network family is used to predict hourly solar irradiance with enhanced prediction accuracy by considering long-term historical data dependencies. The proposed model is compared with Random forest and Extreme Gradient Boost (XGBoost).