Neural Network Control of the StatCom in Multimachine Power Systems

This paper presents the application of neural networks for controlling the static synchronous compensator (StatCom) device. The primary duty of the StatCom is the regulation of the AC bus bar voltage where the device is connected. Additionally, a secondary task may be added to such device for obtaining a positive interaction with other controllers in order to mitigate low frequency oscillations. For this task, a neural network is proposed due to its simple structure, adaptability, robustness, considering the power grid nonlinearities. The applicability of the proposition is studied by digital simulation exhibiting satisfactory performance. Results of simulation for different disturbances and operating conditions demonstrate the effectiveness of the feedback variables selected in the control scheme.