Bayesian Regression for Solar Power Forecasting

Abstract

The solar power forecasting is important factor that provides support to planning terms of power distribution organizations. The time based forecasting is feasible due to dependable outcome of solar power generation on weather status. The weather status itself is prediction method involving approach which is becoming considerably accurate these days. The power generation outcome is the multiple parameter regression model. This paper shows the experimental outcome of solar power generation forecasting with linear, ridge and Bayesian regression models. The best performing Bayesian model is compared with other existing methods in which Bayesian model outperforms in terms of mean square error for 15 minutes time interval data in batch processing approach.