Adaptive conventional power system stabilizer based on artificial neural network

Conference · Sun Dec 31 00:00:00 EST 1995

OSTI ID:474576

Kothari, M L ^[1]; Segal, R ^[2]; Ghodki, B K ^[3]

---

1. Indian Inst. of Tech., New Delhi (India). Dept. of Electrical Engineering
2. Bharat Heavy Electricals Ltd., New Delhi (India)
3. Tata Hydro, Bombay (India)

This paper deals with an artificial neural network (ANN) based adaptive conventional power system stabilizer (PSS). The ANN comprises an input layer, a hidden layer and an output layer. The input vector to the ANN comprises real power (P) and reactive power (Q), while the output vector comprises optimum PSS parameters. A systematic approach for generating training set covering wide range of operating conditions, is presented. The ANN has been trained using back-propagation training algorithm. Investigations reveal that the dynamic performance of ANN based adaptive conventional PSS is quite insensitive to wide variations in loading conditions.

• OSTI ID: 474576
• Report Number(s): CONF-9601119-; ISBN 0-7803-2795-0; TRN: IM9723%%469
• Resource Relation: Conference: IEEE international conference on power electronics, drives and energy systems for industrial growth (PEDES 96). Vols I & II, New Delhi (India), 8-11 Jan 1996; Other Information: PBD: 1995; Related Information: Is Part Of 1996 international conference on power electronics, drives and energy systems for industrial growth: Proceedings. Volume 2; Murthy, S.S.; Roy, S. [eds.] [Indian Inst. of Tech., New Delhi (India)]; Divan, D. [ed.] [Univ. of Wisconsin, Madison, WI (United States)]; Doradla, S.R. [ed.] [Indian Inst. of Tech., Kanpur (India)]; Murthy, B.V. [ed.] [General Motors, Detroit, MI (United States)]; PB: 472 p.
• Country of Publication: United States
• Language: English

Related Subjects

24 POWER TRANSMISSION AND DISTRIBUTION
POWER SYSTEMS
COMPUTERIZED CONTROL SYSTEMS
STABILIZATION
NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE
OSCILLATIONS
DAMPING