An Adaptive RTRL Based Neurocontroller for Damping Power System Oscillations

K. C. Sindhu Thampatty, P. C. Reghu Raj


The main objective of this paper is to present the design of an adaptive neuro-controller for series connected FACTS devices like Thyristor Controlled Series Capacitor (TCSC) and Thyristor controlled Power Angle Regulator (TCPAR). This control scheme is suitable for non-linear system control, in which the exact linearised mathematical model of the system is not required. The proposed controller design is based on Real Time Recurrent Learning (RTRL) algorithm in which the Neural Network (NN) is trained in real time. This control scheme requires two sets of neural networks. The first set is a neuro-identifier and the second set is a neurocontroller which generates the required control signals for the thyristors. Performance of the system is analysed with the proposed controller using standard simulation environments like MATLAB/SIMULINK and it has been observed that the controlleris robust and the response is very fast. Performance of the system with proposed controller is compared with conventional PI controllers and GA based PI controllers. Performace of the proposed controller is extremely good.


Thyristor Controlled Series Capacitor (TCSC) Thyristor controlled Power Angle Regulator (TCPAR) Real Time Recurrent Learning Algorithm (RTRL) Recurrent Neural Network (RNN) Dynamic Neural Network (DNN)

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Applied Power Engineering (IJAPE)
p-ISSN 2252-8792, e-ISSN 2722-2624

Web Analytics Made Easy - StatCounter IJAPE Visitors