Abstract

While wind energy predictability is recognized as essential to successfully integrating wind energy into the power grid, the wind energy forecast community strongly prefers to measure the wind energy forecast error by dividing the forecast's mean absolute error (MAE) by the capacity of the wind energy turbines. This paper presents evidence that this approach can create an illusion of predictability. With the hope of dispelling this illusion, this paper presents a statistical methodology to improve the predictability of wind energy generation using data from the Irish power grid. The analysis begins by observing that the existing wind energy forecasts do not fully reflect expected meteorological conditions. It is further noted that wind energy generation is highly volatile at times but also has a significant autoregressive pattern that can be exploited to improve predictability. An ARCH/ARMAX(autoregressive conditional heteroskedasticity/ autoregressive–moving-average with exogenous inputs) time series model is formulated based on these properties. One of the key modeling innovations is the implementation of ARCH-in-mean effects, which boosts predictive accuracy by capturing the information in the conditional variance. The model is estimated using 15-minute data from Jan 2, 2015, through Dec 31, 2021. The model is evaluated using out-of-sample data from Jan 1, 2022, to Dec 31, 2023. The period-ahead out-of-sample predictions have a weighted mean absolute percentage error (WMAPE) of about 5 %, substantially less than the approximately 11.5 % WMAPE associated with the wind energy forecasts used by the system operator over the same period. While this finding is unlikely to induce the apologists of capacity weighting to recant their misleading reporting approach, it may inform regulators that the error metrics reported by the wind energy forecasters cannot be trusted and thus could contribute to an energy transition away from fossil fuels that entails a more resilient power grid.