Abstract
Due to the nonlinearity, uncertainty and complexity of the power system, it is a challenging task to design an effective control approach based on the exact model using traditional methods. In this paper, we investigate the application of a novel approximate dynamic programming (ADP) architecture, goal representation heuristic dynamic programming (GrHDP), to a large benchmark power system. Unlike traditional ADP design with an action network and a critic network, GrHDP integrates the third network, a goal network, into the actorcritic design (ACD) to automatically and adaptively build an internal reinforcement signal representation to facilitate learning and optimization. Then the GrHDP is employed to control the benchmark power system including a DFIG based wind farm and a STATCOM with HVDC transmission. Various power system states, including the voltage of STATCOM, current of DFIG and DC current of HVDC inverter, are provided to the GrHDP controller to generate three adaptive supplementary control signals. These adaptive supplementary control signals are then provided to the STATCOM controller, DFIG rotor side controller and HVDC master control, respectively. This control structure is validated in Matlab/Simulink to demonstrate its effectiveness in power system control.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
