• DocumentCode
    2396163
  • Title

    Dynamic security margin estimation using artificial neural networks

  • Author

    Sittithumwat, A. ; Tomsovic, Kevin

  • Author_Institution
    Sch. of Electr. Eng. & Comput. Sci., Washington State Univ., Pullman, WA, USA
  • Volume
    3
  • fYear
    2002
  • fDate
    25-25 July 2002
  • Firstpage
    1322
  • Abstract
    This paper focuses on transient stability. Two dynamics problems, i.e., transient stability and voltage collapse, should be considered when performing a dynamic security study. Transient stability assessment is a major concern in the DSA for multi-machine power systems. Particularly, a fault on the system or a loss of a large generator can give rise to large electromechanical oscillations between generating units, which might lead to loss of synchronism in the system. For the voltage stability problem, it is associated with the increased loading of long transmission lines and insufficient local reactive power supply. These types of phenomena are characterized by a voltage drop gradual at first, and then collapse. The time interval of the slow voltage decay phase typically is in between 1 to 10 minutes, which is adequate for the operator to exercise the corrective action.
  • Keywords
    control system analysis; neurocontrollers; power system control; power system faults; power system security; power system state estimation; power system transient stability; 1 to 10 min; corrective action; electromechanical oscillations; generator loss; loss of synchronism; multi-machine power systems; power system transient stability assessment; power system voltage collapse; slow voltage decay phase; system faults; time interval; Artificial neural networks; Power supplies; Power system dynamics; Power system faults; Power system security; Power system stability; Power system transients; Power transmission lines; Reactive power; Voltage;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Power Engineering Society Summer Meeting, 2002 IEEE
  • Conference_Location
    Chicago, IL, USA
  • Print_ISBN
    0-7803-7518-1
  • Type

    conf

  • DOI
    10.1109/PESS.2002.1043583
  • Filename
    1043583