An on-line training radial basis function neural network for optimum operation of the UPFC

Farrag, Mohamed and Putrus, Ghanim (2011) An on-line training radial basis function neural network for optimum operation of the UPFC. European Transactions on Electrical Power, 21 (1). pp. 27-39. ISSN 1430-144X

[img]
Preview
PDF (Article)
An On-line Training Radial Basis Function Neural Network.pdf

Download (335kB) | Preview
Official URL: http://dx.doi.org/10.1002/etep.409

Abstract

The concept of Flexible A.C. Transmission Systems (FACTS) technology was developed to enhance the performance of electric power networks (both in steady-state and transient-state) and to make better utilization of existing power transmission facilities. The continuous improvement in power ratings and switching performance of power electronic devices together with advances in circuit design and control techniques are making this concept and devices employed in FACTS more commercially attractive. The Unified Power Flow Controller (UPFC) is one of the main FACTS devices that have a wide implication on the power transmission systems and distribution. The purpose of this paper is to explore the use of Radial Basis Function Neural Network (RBFNN) to control the operation of the UPFC in order to improve its dynamic performance. The performance of the proposed controller compares favourably with the conventional PI and the off-line trained controller. The simple structure of the proposed controller reduces the computational requirements and emphasizes its appropriateness for on-line operation. Real-time implementation of the controller is achieved through using dSPACE ds1103 control and data acquisition board. Simulation and experimental results are presented to demonstrate the robustness of the proposed controller against changes in the transmission system operating conditions.

Item Type: Article
Uncontrolled Keywords: neural networks
Subjects: F200 Materials Science
Department: Faculties > Engineering and Environment > Mathematics, Physics and Electrical Engineering
Depositing User: EPrint Services
Date Deposited: 07 Apr 2011 14:34
Last Modified: 17 Dec 2023 16:04
URI: https://nrl.northumbria.ac.uk/id/eprint/477

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics