Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electrical Engineering | en_US |
| dc.creator | Fu, Ying | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/2817 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Hybrid network reduction and artificial neural network based approaches in fast voltage stability analysis | en_US |
| dcterms.abstract | The development of tools for fast on-line voltage stability analysis is a major issue in the operation of modern power system due to the recent trends in deregulation and competitive operation environment. This thesis is focused on the study of fast voltage stability analysis for both static and dynamic security assessment. Two new techniques are developed: network reduction and integrated artificial neural network approaches. An overview of current trends in voltage stability analysis, as well as the current solution techniques, is first presented. Following the introduction on external modeling, an extended Ward equivalent model is then presented. Artificial Neural Networks (ANNs) approaches have been developed to voltage stability evaluation as they are able to solve power system problems where difficulties have been experienced with conventional numerical techniques. Three types of ANN models: multi-layer neural network, Kohonen neural network, and hybrid supervised/unsupervised neural network, are developed in this work. A new methodology for static voltage stability by means of network reduction is presented. By the use of this methodology, Q-V or P-V curve can be quickly determined. The extended Ward equivalent is one of the most popular methods on external network equivalent. However, it is found that the method is not suitable for on-line use. An improved method is developed with hybrid ANN and external network equivalent. This new method combines the merits of the two techniques since it uses the extended Ward equivalent to build boundary equivalent line modeling and ANN to on-line match boundary equivalent power injection. Hence, this new approach is proposed for fast on-line assessment application. Voltage stability is also a dynamic problem, which mainly involves the loads and the means for voltage control. The dynamic characteristics of induction motor are introduced in this thesis. An improved ANN based method for voltage stability analysis is also developed. This method is based on self-organizing hierarchical neural network (SHNN), which integrates input feature self-organizing map neural network and multi-layer feed-forward neural network. Research results and analysis are presented to show the applicability and efficiency of these methods in power systems operation. | en_US |
| dcterms.extent | x, 155 leaves : ill. ; 30 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2000 | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.educationalLevel | Ph.D. | en_US |
| dcterms.LCSH | Electric power system stability | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | open access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b15057860.pdf | For All Users | 5.32 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/2817