Short-Term PV Generation Forecasting Using Quantile Regression Averaging

The globally increasing demand for energy to carry out the various day-to-day activities needs renewable sources in conjunction with existing power plants. PV technology has seen tremendous growth over the past decades. However, the integration of PV generation to the power systems invites numerous planning and operational challenges. In the short-term, the real-time operation of PV-integrated power systems requires the characterization of the uncertainties associated with the PV generation. A probabilistic framework, such as the quantile regression averaging (QRA), has been successful in forecasting load power and electricity spot prices. This paper applies QRA to accomplish a probabilistic forecast of PV generation using its historical record from a rooftop installation at Lincoln, USA. This paper's main contribution is the use of two appropriate individual point forecasters, i.e., autoregressive conditional heteroscedastic and multiple linear regression models, to complement each other and make accurate quantile forecasts. The proposed model is used in the short-term forecasting of PV generation for the four major seasons up to two weeks ahead. A detailed result analysis shows that the combination of both models improves overall forecasting performance rather than using any of the models alone.