Good or Bad Wind Power Forecasts: A Relative Concept

Abstract

This paper reports a study on the importance of the training criteria for Wind Power Forecasting (WPF) and a reflection of the goodness in forecasts. The study combines different training criteria and different users of the forecasts to compare them in terms of the benefits obtained in an electricity market environment. We show that the interests of wind farm owners may lead to the adoption of biased forecasts which are not adequate to good system operating policies. The ideas and conclusions are supported by results of three real wind farms.