Day Ahead Solar Irradiance Forecasting using Markov Chain Model

Solar power technologies have emerged as a strong participant in energy market growth. In the past few years, there has been a corresponding increase in its grid penetration. Accurate short-term solar forecasting is very important for scheduling of the solar parks. The paper investigates the use of the Markov Chain Model for solar irradiance forecasting for a short-term period (hourly day-ahead solar irradiance forecast for an individual solar park). The proposed model depends on only one variable, i.e., Solar Irradiance. The geographical station considered for this study is taken at Bhadla, Jodhpur, Rajasthan, India. The performance of the proposed method is evaluated by calculating different statistical error measures like Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).