Skip to Main Content
Summary form only given. This paper presents a novel nonlinear optimal controller for a static compensator (STATCOM) connected to a power system, using artificial neural networks and fuzzy logic. The action dependent heuristic dynamic programming (ADHDP), a member of the adaptive critic designs (ACD) family, is used for the design of the STATCOM neuro-fuzzy controller. This neuro-fuzzy controller provides optimal control based on reinforcement learning and approximate dynamic programming, and can effectively perform in the presence of noise and uncertainties. Using a proportional-integrator approach the proposed controller is capable of dealing with actual rather than deviation signals. The STATCOM is connected to a multimachine power system in order to provide voltage support during the steady state performance of the power system and also improve the dynamic stability of the network during faults and disturbances. Two multimachine power systems are considered in this study: a 10-bus 2-generator system and a 45-bus 10-generator system, where the latter is a section of the Brazilian power grid. Simulation results are provided to show that the proposed controller outperforms a conventional PI controller in large scale faults as well as small disturbances.