Skip to Main Content
In this paper, an intelligent approach based on system-centric controller to develop a power system stabilizer is proposed. The approach discuss a methodology that designs a hybrid controller with two algorithms, one a Neural Network (NN) based controller with explicit neuro-identifier, and the other, an adaptive controller evolved from a Model Reference Adaptive Controller (MRAC). This design performs as a system-centric controller. The NN is trained offline with extensive data, and is also adjusted online. Main advantage and uniqueness of the proposed scheme is the controllers' ability to complement each other in case of parametric and functional uncertainty. Moreover, the online neural network approximates the plant in the event of functional change during abnormal operating conditions. The theoretical results are validated by conducting simulation studies on a two area equivalent 5 generator, 8 bus multi-machine power system with varying generator schedules that shows low frequency oscillations.