Adaptive Critic Designs Based Coupled Neurocontrollers for a Static Compensator
This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1416
There were 5 downloads as of 28 Jun 2016.
A novel nonlinear optimal neurocontroller for a static compensator (STATCOM) connected to a power system, using artificial neural networks, is presented in this paper. The heuristic dynamic programming (HDP) method, a member of the adaptive critic designs (ACD) family, is used for the design of the STATCOM neurocontroller. The proposed controller is a nonlinear optimal controller that provides coupled control for the line voltage and the dc link voltage regulation loops of the STATCOM. An action dependent approach is used, in which the controller is independent of a model of the network. Moreover, a proportional-integrator approach allows the neurocontroller to deal with the actual signals rather than the deviations. Simulation results are provided to show that the proposed ACD based neurocontroller is more effective in controlling the STATCOM compared to finely tuned conventional PI controllers.