Uncertainty Quantification for the Required Fossil Fuel Generation in a Smart Grid

Abstract

Prediction with uncertainty quantification (UQ) is becoming a vital part of the grid management with the increased uncertainty caused by the recent installation of renewable power sources. Specialized algorithms are developed and applied to predict electricity demand, renewable generations and other non-fossil-fuel generations in point predictions. The required fossil fuel generation (RFFG) of a grid is predicted from the subtraction of other generations from the demand. A prediction interval (PI) constructed from intervals of different components results in a higher coverage probability with much higher width. This paper presents the direct construction of smart RFFG PIs, maintains a narrower width with the expected coverage probability. The time series array of the RFFG is obtained from the subtraction of the sum of other generations from the electricity demand. A modified NN based Lower Upper Bound Estimation (LUBE) method is applied with a continuous cost function to construct PIs; as the LUBE method can construct smart PIs for an asymmetric and heteroscedastic probability distribution. Many inter-related uncertainties between the electricity demand and renewables are canceled out with the difference; result in a narrower and smarter PI with less computation.