• DocumentCode
    2181815
  • Title

    Reinforcement learning applied to power system oscillations damping

  • Author

    Ernst, D.

  • Author_Institution
    Inst. Montefiore, Liege Univ., Belgium
  • Volume
    4
  • fYear
    2001
  • fDate
    2001
  • Firstpage
    3043
  • Abstract
    This paper investigates the use of reinforcement learning in electrical power system oscillations damping. The approach consists in using temporal-difference learning algorithms to control a FACTS (Flexible Alternative Current Transmission System) so as to damp power system oscillations. The proposed approach is based only on local measurements and frees itself from the knowledge of power system dynamics. An illustration is carried out on a one machine infinite bus system
  • Keywords
    flexible AC transmission systems; learning (artificial intelligence); power system control; power system dynamic stability; flexible alternative current transmission system; local measurements; one machine infinite bus system; power system dynamics; power system oscillations damping; reinforcement learning; temporal-difference learning algorithms; Control systems; Damping; Equations; Learning; Nonlinear systems; Optimal control; Power system control; Power system dynamics; Power system measurements; Power systems;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Decision and Control, 2001. Proceedings of the 40th IEEE Conference on
  • Conference_Location
    Orlando, FL
  • Print_ISBN
    0-7803-7061-9
  • Type

    conf

  • DOI
    10.1109/.2001.980282
  • Filename
    980282