Title :
Comparative evaluation of neural-network-based and PI current controllers for HVDC transmission
Author :
Sood, V.K. ; Kandil, N. ; Patel, R.V. ; Khorasani, K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Concordia Univ., Montreal, Que., Canada
fDate :
5/1/1994 12:00:00 AM
Abstract :
An investigation into a neural network (NN)-based controller, composed of a NN trained off-line in parallel with a NN trained on-line, is described in this paper. This NN controller has the potential of replacing the PI controller traditionally used for HVDC transmission systems. A theoretical basis for the operational behavior of the individual NN controllers is presented. Comparisons between the responses obtained with the NN and PI controllers for the rectifier of an HVDC transmission system are made under typical system perturbations and faults
Keywords :
DC power transmission; controllers; electric current control; electrical faults; learning (artificial intelligence); neural nets; power system computer control; rectifiers; two-term control; HVDC system faults; HVDC system perturbations; HVDC transmission; PI current controllers; neural-network-based current controllers; off-line trained neural net; on-line trained neural net; Control systems; HVDC transmission; Inverters; Neural networks; Nonlinear control systems; Optimal control; Power harmonic filters; Power system dynamics; Power system harmonics; Rectifiers;
Journal_Title :
Power Electronics, IEEE Transactions on
