236 - The power of weather

DNB Working Papers
Date 25 January 2010

This paper examines the predictive power of weather for electricity prices in day ahead markets in real time. We find that next-day weather forecasts improve the forecast accuracy of Scandinavian day-ahead electricity prices substantially in terms of point forecasts, suggesting that weather forecasts can price the weather premium. This improvement strengthens the confidence in the forecasting model, which results in high center-mass predictive densities. In density forecast, such a predictive density may not accommodate forecasting uncertainty well. Our density forecast analysis confirms this intuition by showing that incorporating weather forecasts in density forecasting does not deliver better density forecast performances.

Keywords: Electricity prices, weather forecasts, point and density forecasts, GARCH models.

JEL Classification Code: C53, G15, Q40.