Please use this identifier to cite or link to this item:
Title: "Good" or "Bad" Wind Power Forecasts: A Relative Concept
Authors: Jianhui Wang
Ricardo Jorge Bessa
Vladimiro Miranda
Audun Botterud
Issue Date: 2011
Abstract: This paper reports a study on the importance of the training criteria for wind power forecasting (WPF) and calls into question the generally assumed neutrality of the 'goodness' of particular forecasts. The study, focused on the Spanish Electricity Market as a representative example, combines different training criteria and different users of the forecasts to compare them in terms of the benefits obtained. In addition to more classical criteria, an Information Theoretic Learning (ITL) training criterion, called parametric correntropy, is introduced as a means to correct problems detected in other criteria and achieve more satisfactory compromises among conflicting criteria, namely forecasting value and quality. We show that the interests of wind farm owners may lead to a preference for biased forecasts, which do not serve the larger needs of good system operating policies. The ideas and conclusions are supported by results from three real wind farms.
metadata.dc.type: article
Appears in Collections:CPES - Indexed Articles in Journals

Files in This Item:
File Description SizeFormat 
  Restricted Access
168.16 kBAdobe PDFView/Open Request a copy

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.