A neural network based optimal wide area control scheme for a power system

With deregulation of the power industry, many tie lines between control areas are driven to operate near their maximum capacity, especially those serving heavy load centers. Wide area control systems (WACSs) using wide-area or global signals can provide remote auxiliary control signals to local controllers such as automatic voltage regulators, power system stabilizers, etc to damp out inter-area oscillations. This paper presents the design and the DSP implementation of a nonlinear optimal wide area controller based on adaptive critic designs and neural networks for a power system on the real-time digital simulator (RTDS/spl reg/). The performance of the WACS as a power system stability agent is studied using the Kundur's two area power system example. The WACS provides better damping of power system oscillations under small and large disturbances even with the inclusion of local power system stabilizers.