StatCom's Control by neural networks: Results on a lab prototype

This paper presents the static synchronous compensator (StatCom) voltage regulation by a B-spline neural network. The fact that the electric grid is a non-stationary system, with varying parameters and configurations, adaptive control schemes may be advisable. Thereby the control technique must guarantee its performance on an actual operating environment where the StatCom is embedded. The B-spline neural net (B-SNN) is a convenient tool to execute the power system voltage adaptive control, with the possibility of carrying out such tasks on-line and taking into account non-linearities. The proposed controller presents a simple structure, adaptability, fast response, and robustness. The simplicity and performance of such control are exhibited. The applicability of the proposition is tested on a lab prototype.