• DocumentCode
    3480809
  • Title

    Controlling study of D-STATCOM based on reinforcement learning adaptive PID

  • Author

    Meng, Xing-Ping ; Wang, Hui ; Zhao, Liang ; Zhang, Hong

  • Author_Institution
    Dept. of Electr. Eng., Changchun Inst. of Technol., Changchun, China
  • fYear
    2009
  • fDate
    5-7 Aug. 2009
  • Firstpage
    1208
  • Lastpage
    1211
  • Abstract
    Distribution Static Compensator (DSTATCOM) is a shunt compensation device which is generally used to solve power quality problems in distribution systems. In distribution power system, these power quality problems mainly arise due to the pulsed loads, which causes the degradation of the entire system performance. The control strategy of DSTATCOM plays an important role to meet the objectives. A novel adaptive control strategy for the DSTATCOM is based on the Reinforcement Learning Adaptive PID (RLA-PID). With this control method, the compensator can stabilize the PCC voltage around a prescribed value. A distributes power system is developed in MATLAB environment, the validity of the method proposed is verified.
  • Keywords
    adaptive control; learning (artificial intelligence); learning systems; power distribution control; power supply quality; static VAr compensators; three-term control; D-STATCOM control; distribution power system; distribution static compensator; power quality; reinforcement learning adaptive PID control; shunt compensation device; Adaptive control; Automatic voltage control; Degradation; Learning; Power quality; Programmable control; Pulse power systems; STATCOM; System performance; Three-term control; DSTATCOM; Intelligent Control; Power quality; Reinforcement Learning Adaptive PID;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automation and Logistics, 2009. ICAL '09. IEEE International Conference on
  • Conference_Location
    Shenyang
  • Print_ISBN
    978-1-4244-4794-7
  • Electronic_ISBN
    978-1-4244-4795-4
  • Type

    conf

  • DOI
    10.1109/ICAL.2009.5262681
  • Filename
    5262681