Forecasting nonstationary energy time series Seminar

Within the energy sector forecasting is an important statistical tool. Each day many forecasts are made across a variety of time scales, such as production of renewables, consumer demand and trader pricing. Traditional statistical techniques assume stationarity of the past in order to produce accurate forecasts. For data arising from the energy sector this stationarity assumption is often violated. This talk will highlight potential issues and propose a new estimator, the local partial autocorrelation function, which will aid us in forecasting nonstationary data. We illustrate the new estimator and forecasting method and show improved forecasting performance using this new technique.