You need JavaScript to view this

Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis [of power systems]

Abstract

In heavily stressed power systems, post-fault transient voltage dips can lead to undesired tripping of industrial drives and large induction motors. The lowest transient voltage dips occur when fault clearing times are less than critical ones. In this paper, we propose a new iterative analytical methodology to obtain more accurate estimates of voltage dips at maximum angular swing in direct transient stability analysis. We also propose and demonstrate the possibility of storing the results of these computations in the associative memory (AM) system, which exhibits remarkable generalization capabilities. Feature-based models stored in the AM can be utilized for fast and accurate prediction of the location, duration and the amount of the worst voltage dips, thereby avoiding the need and cost for lengthy time-domain simulations. Numerical results obtained using the example of the New England power system are presented to illustrate our approach. (Author)
Authors:
Djukanovic, M; [1]  Sobajic, D J; Pao, Yohhan [2] 
  1. Inst. 'Nikola Tesla', Belgrade (Yugoslavia)
  2. Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Electrical Engineering and Applied Physics Case Western Reserve Univ., Cleveland, OH (United States). Dept. of Computer Engineering and Science AI WARE inc., Cleveland, OH (United States)
Publication Date:
Oct 01, 1992
Product Type:
Journal Article
Reference Number:
GB-93-050665; EDB-93-089564
Resource Relation:
Journal Name: International Journal of Electrical Power and Energy Systems; (United Kingdom); Journal Volume: 14:5
Subject:
24 POWER TRANSMISSION AND DISTRIBUTION; POWER SYSTEMS; STABILITY; COMPUTER CALCULATIONS; MATHEMATICAL MODELS; NEURAL NETWORKS; TRANSIENTS; VALIDATION; TESTING; 240100* - Power Systems- (1990-)
OSTI ID:
6502926
Country of Origin:
United Kingdom
Language:
English
Other Identifying Numbers:
Journal ID: ISSN 0142-0615; CODEN: IEPSDC
Submitting Site:
GB
Size:
Pages: 341-350
Announcement Date:
Aug 01, 1993

Citation Formats

Djukanovic, M, Sobajic, D J, and Pao, Yohhan. Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis [of power systems]. United Kingdom: N. p., 1992. Web. doi:10.1016/0142-0615(92)90015-2.
Djukanovic, M, Sobajic, D J, & Pao, Yohhan. Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis [of power systems]. United Kingdom. doi:10.1016/0142-0615(92)90015-2.
Djukanovic, M, Sobajic, D J, and Pao, Yohhan. 1992. "Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis [of power systems]." United Kingdom. doi:10.1016/0142-0615(92)90015-2. https://www.osti.gov/servlets/purl/10.1016/0142-0615(92)90015-2.
@misc{etde_6502926,
title = {Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis [of power systems]}
author = {Djukanovic, M, Sobajic, D J, and Pao, Yohhan}
abstractNote = {In heavily stressed power systems, post-fault transient voltage dips can lead to undesired tripping of industrial drives and large induction motors. The lowest transient voltage dips occur when fault clearing times are less than critical ones. In this paper, we propose a new iterative analytical methodology to obtain more accurate estimates of voltage dips at maximum angular swing in direct transient stability analysis. We also propose and demonstrate the possibility of storing the results of these computations in the associative memory (AM) system, which exhibits remarkable generalization capabilities. Feature-based models stored in the AM can be utilized for fast and accurate prediction of the location, duration and the amount of the worst voltage dips, thereby avoiding the need and cost for lengthy time-domain simulations. Numerical results obtained using the example of the New England power system are presented to illustrate our approach. (Author)}
doi = {10.1016/0142-0615(92)90015-2}
journal = {International Journal of Electrical Power and Energy Systems; (United Kingdom)}
volume = {14:5}
journal type = {AC}
place = {United Kingdom}
year = {1992}
month = {Oct}
}