Recurrent Damping Neural Controller based on HVDC Transmission System to Improve Dynamic Stability of Power System

This paper presents a novel linearized Phillips- Heffron model of a parallel AC/DC power system in order to studying power system stability. In addition, a supplementary damping online learning recurrent neural network controllers for VSC HVDC to damp low frequency oscillations in a weakly connected system is proposed. Multilayer recurrent neural network, which can be tuned for changing system conditions, is used in this paper for effectively damp the oscillations. Training is based on back propagation with adaptive training parameters. The effectiveness of the proposed controllers on damping low frequency oscillations is checked through eigenvalue analysis and non-linear time simulation under various disturbance conditions of over a wide range of loading. The presented control scheme not only performs damping oscillations but also the voltage and power flow control can be achieved. Simulation results obtained by MATLAB to verify the effectiveness of the VSC HVDC and its control strategy for enhancing dynamical stability.

Keywords:

Power system dynamic stability , Supplementary Damping Controller , Recurrent Neural Network , VSC HVDC.