Neural Stabilization/Excitation Control of a High-Order Power System by Adaptive Feedback Linearization

摘要

This paper discusses the systematic design of an adaptive feedbacklinearizing neurocontroller for a high-order model of the synchronousmachine/infinite bus power system. The power system is first modelled as aninput-output nonlinear discrete-time system approximated by two neuralnetworks. The approach allows a simple linear pole-placement controller (whichis itself not a neural network) to be designed. The control law is specifiedsuch that the controller adaptively calculates an appropriate feedbacklinearizing control law at each sampling instant by utilizing plant parameterestimates provided by the neural system model. The control system also adaptsitself on-line. This avoids the requirement for exact knowledge of the powersystem dynamics and full state measurement as well as other difficultiesassociated with implementing analytical input-output feedback linearizingcontrol for a complex power system model. Furthermore, a departure is made fromthe `ad hoc' manner in which many neural controllers have been designed forpower systems; the approach used here has foundations in control theoreticconcepts of adaptive feedback linearization and pole-placement control design. Simulation results demonstrate the performance of this controller for arepresentative example of a single-machine/infinite bus power systemconfiguration under various operational conditions.