ABSTRACT
This chapter presents a statistical model to formulate the conditional distribution of forecast error for multiple renewable energy farms using copula theory. The short-term uncertainty of renewable energy generation refers to the deviation of renewable energy output compared with its forecasts. The chapter explains the technique of modeling the conditional forecast error of multiple wind farms and photovoltaics (PV) stations by generation scheduling. A forecasting model for the PV day-ahead output points based on the back propagation artificial neural network is established. The evaluation method utilized in probabilistic forecasting is adopted to evaluate the accuracy of the proposed method for estimating the forecast error probabilistic distribution of the PV output. Different from wind power output, PV power generation is more significantly affected by the weather. The stability and predictability of PV power generation vary under different weather conditions, causing significant randomness in PV output.
