In this study, the authors propose an adaptive neural network (NN) excitation control for wide-area power systems. Compared with most existing approaches, the system dynamics is assumed to be totally unknown, which is approximated by a two-layer NN in an online manner, i.e. no offline training is required. With the help of NN approximation, it is not necessary to pay much attention to system modelling since this modelling is of great difficulty and inaccurate. In addition, the tuning of controller parameters in most existing control designs is avoided as well, which simplifies the controller design. It is proved that all the signals in the closed loop are bound using Lyapunov analysis. Finally, numerical analysis has been conducted on an IEEE 39 Bus power system to verify the effectiveness of the proposed adaptive controller.

Additional Metadata
Persistent URL dx.doi.org/10.1049/iet-gtd.2017.0299
Journal IET Generation, Transmission and Distribution
Citation
Meng, W. (Wenchao), Wang, X, Fan, B. (Bo), Yang, Q. (Qinmin), & Kamwa, I. (Innocent). (2017). Adaptive non-linear neural control of wide-area power systems. IET Generation, Transmission and Distribution, 11(18), 4531–4536. doi:10.1049/iet-gtd.2017.0299