Design of an Adaptive PSS Based on Recurrent Adaptive Control Theory

Author

Zhao, Peng ; Malik, O.P.

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Calgary, Calgary, AB, Canada

Volume

24

Issue

4

fYear

2009

Firstpage

884

Lastpage

892

Abstract

Inspired by observing the similarity between adaptive control systems and recurrent neural networks (RNNs), a new control scheme, the recurrent adaptive control (RAC), is presented in this paper. Back propagation through time (BPTT), a learning algorithm for RNNs, can be exploited in RAC. Application of truncated BPTT to RAC is also discussed. Further, a new control algorithm for RAC, termed recursive gradient (RG), is developed to improve the performance of the original and truncated BPTT algorithms. Effectiveness of the RG control algorithm as a power system stabilizer is demonstrated.

Keywords

adaptive control; neurocontrollers; power system control; power system stability; recurrent neural nets; adaptive PSS; back propagation through time; power system stabilizer; recurrent adaptive control theory; recurrent neural networks; recursive gradient; Adaptive control; Control systems; Fuzzy systems; Neural networks; Power system control; Power system modeling; Power systems; Programmable control; Recurrent neural networks; Roentgenium; Adaptive control; model reference adaptive control (MRAC); power system stabilizer (PSS); recurrent adaptive control (RAC); recurrent neural networks (RNNs); self-tuning regulator (STR);

fLanguage

English

Journal_Title

Energy Conversion, IEEE Transactions on

Publisher

ieee

ISSN

0885-8969

Type

jour

DOI

10.1109/TEC.2009.2025337

Filename

5336285