• DocumentCode
    3300890
  • Title

    Constrained Support Vector Machines for photovoltaic in-feed prediction

  • Author

    Hildmann, Marcus ; Rohatgi, Ajeet ; Andersson, Goran

  • Author_Institution
    Power Syst. Lab., ETH Zurich, Zurich, Switzerland
  • fYear
    2013
  • fDate
    1-2 Aug. 2013
  • Firstpage
    23
  • Lastpage
    28
  • Abstract
    In this paper, we introduce a constrained Support Vector Machine (SVM) to predict photovoltaic (PV) in-feed. We derive the SVM algorithm with linear constraints and test the method on German PV in-feed with constraints reflecting physical boundaries. We show that the new algorithm shows a significant better performance than a constrained ordinary least squares (OLS) estimator.
  • Keywords
    photovoltaic power systems; power engineering computing; support vector machines; tariffs; German PV in-feed; SVM; linear constraints; photovoltaic in-feed prediction; physical boundaries; support vector machines; Correlation; Estimation; Kernel; Optimization; Predictive models; Support vector machines; Temperature;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Technologies for Sustainability (SusTech), 2013 1st IEEE Conference on
  • Conference_Location
    Portland, OR
  • Type

    conf

  • DOI
    10.1109/SusTech.2013.6617293
  • Filename
    6617293
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3300890