Application of artificial neural networks for online voltage stability monitoring and enhancement of an electric power system

Chakrabarti, Saikat (2006) Application of artificial neural networks for online voltage stability monitoring and enhancement of an electric power system. Doctoral (PhD) thesis, Memorial University of Newfoundland.

[img] [English] PDF - Accepted Version
Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission.

Download (12Mb)

Abstract

Due to economic reasons arising out of deregulation and open market of electricity, modem day power systems are being operated closer to their stability limits. When a fault occurs, there is a great possibility of occurrence of cascading outages, as observed in the August 2003 Blackout in the North-East USA and Canada. Power system voltage stability is one of the challenging problems faced by the utilities. Innovative methods and solutions are required to evaluate the voltage stability of a power system and implement suitable strategies to enhance the robustness of the power system against voltage stability problems. This is the motivation behind the research carried out as a part of the PhD program and presented in this dissertation. Artificial neural networks (ANNs) have gained widespread attention from researchers in recent years as a tool for online voltage stability assessment. Two major areas requiring investigation are identified after doing a thorough survey of the existing literature on online voltage stability monitoring using ANN. The first one is the effective method of selecting important features among numerous possible measurable parameters as potential inputs to the ANN. The second one is the feasibility of using a single ANN for monitoring voltage stability for multiple contingencies. In the first phase of the research, a regression-based method of computing sensitivities of the voltage stability margin with respect to different parameters is proposed. Using the sensitivity information, important features are chosen selectively to train separate Multilayer Perceptron Networks (MLP) to monitor voltage stability for different contingencies. In the second phase of the research, an enhanced Radial Basis Function Network (RBFN) is proposed for online voltage stability monitoring. Important features of the proposed RBFN are: (1) the same network is trained for multiple contingencies, thus eliminating the need for training different ANNs for different contingencies, (2) the number of neurons in the hidden layers is decided automatically using a sequential learning strategy, (3) the RBFN can be adapted online, with changing operating scenario, (4) a network pruning strategy is used to limit the growth of the network size as a result of the adaptation process. In the next phase of the research, a sensitivity-based voltage stability enhancement method is proposed, considering multiple contingencies. Considering the limitations of the existing analytical methods, the sensitivities of the voltage stability margin with respect to parameters are found by using the RBFN proposed in the second phase of the research. Using the sensitivity information, correct amounts of generation rescheduling are found by using linear optimization. Case studies are presented throughout different sections of the thesis to illustrate the application of the proposed methods.

Item Type: Thesis (Doctoral (PhD))
URI: http://research.library.mun.ca/id/eprint/12237
Item ID: 12237
Additional Information: Includes bibliographical references (pages 116-124).
Department(s): Engineering and Applied Science, Faculty of
Date: October 2006
Date Type: Submission
Library of Congress Subject Heading: Electric power system stability; Electric power systems--Control; Neural networks (Computer science); Voltage regulators

Actions (login required)

View Item View Item

Downloads

Downloads per month over the past year

View more statistics