• DocumentCode
    2682772
  • Title

    Better prediction models for renewables by training with entropy concepts

  • Author

    Miranda, V. ; Cerqueira, C. ; Monteiro, C.

  • Author_Institution
    INESC Porto
  • fYear
    0
  • fDate
    0-0 0
  • Abstract
    Prediction models for generation from renewables are needed in the context of a power system with a diversified portfolio. The presentation discusses a new criterion and procedure to develop prediction models based on Renyi´s entropy combined with Parzen windows (an approach named information theoretic learning) that is applied to wind prediction and suggested as a better training paradigm for fuzzy or neural systems
  • Keywords
    entropy; neural nets; power engineering computing; renewable energy sources; wind power plants; Parzen windows; Renyi entropy; diversified portfolio; entropy concepts; fuzzy systems; information theoretic learning; neural systems; prediction models; training paradigm; wind prediction; Context modeling; Entropy; Kernel; Portfolios; Power generation; Power system modeling; Predictive models; Wind energy; Wind energy generation; Wind forecasting; Entropy; forecasting; prediction; wind power;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Power Engineering Society General Meeting, 2006. IEEE
  • Conference_Location
    Montreal, Que.
  • Print_ISBN
    1-4244-0493-2
  • Type

    conf

  • DOI
    10.1109/PES.2006.1709505
  • Filename
    1709505