Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks

Alireza Heidari, Vassilios Agelidis, Josep Pou, Jamshid Aghaei*, Amer M. Y. M. Ghias

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Reliability worth analysis is of great importance in the area of distribution network planning and operation. The reliability worth's precision can be affected greatly by the customer interruption cost model used. The choice of the cost models can change system and load point reliability indices. In this study, a cascade correlation neural network is adopted to further develop two cost models comprising a probabilistic distribution model and an average or aggregate model. A contingency-based analytical technique is adopted to conduct the reliability worth analysis. Furthermore, the possible effects of adding distributed generation units into the network are evaluated. The proposed approach has been tested on a radial distribution test network evaluating the reliability worth. The results show that the probabilistic distribution model provides a more realistic model for the reliability analysis.
Original languageEnglish
JournalI E E E Transactions on Power Systems
Volume33
Issue number1
Pages (from-to)412-420
ISSN0885-8950
DOIs
Publication statusPublished - 2018

Keywords

  • Customer interruption cost model
  • Distributed generation
  • Neural networks
  • Reliability worth analysis

Cite this

Heidari, Alireza ; Agelidis, Vassilios ; Pou, Josep ; Aghaei, Jamshid ; Ghias, Amer M. Y. M. / Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks. In: I E E E Transactions on Power Systems. 2018 ; Vol. 33, No. 1. pp. 412-420.
@article{2ad7d192625c43d7860a0f4316df991d,
title = "Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks",
abstract = "Reliability worth analysis is of great importance in the area of distribution network planning and operation. The reliability worth's precision can be affected greatly by the customer interruption cost model used. The choice of the cost models can change system and load point reliability indices. In this study, a cascade correlation neural network is adopted to further develop two cost models comprising a probabilistic distribution model and an average or aggregate model. A contingency-based analytical technique is adopted to conduct the reliability worth analysis. Furthermore, the possible effects of adding distributed generation units into the network are evaluated. The proposed approach has been tested on a radial distribution test network evaluating the reliability worth. The results show that the probabilistic distribution model provides a more realistic model for the reliability analysis.",
keywords = "Customer interruption cost model, Distributed generation, Neural networks, Reliability worth analysis",
author = "Alireza Heidari and Vassilios Agelidis and Josep Pou and Jamshid Aghaei and Ghias, {Amer M. Y. M.}",
year = "2018",
doi = "10.1109/TPWRS.2017.2705185",
language = "English",
volume = "33",
pages = "412--420",
journal = "I E E E Transactions on Power Systems",
issn = "0885-8950",
publisher = "Institute of Electrical and Electronics Engineers",
number = "1",

}

Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks. / Heidari, Alireza; Agelidis, Vassilios; Pou, Josep; Aghaei, Jamshid; Ghias, Amer M. Y. M.

In: I E E E Transactions on Power Systems, Vol. 33, No. 1, 2018, p. 412-420.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Reliability Worth Analysis of Distribution Systems Using Cascade Correlation Neural Networks

AU - Heidari, Alireza

AU - Agelidis, Vassilios

AU - Pou, Josep

AU - Aghaei, Jamshid

AU - Ghias, Amer M. Y. M.

PY - 2018

Y1 - 2018

N2 - Reliability worth analysis is of great importance in the area of distribution network planning and operation. The reliability worth's precision can be affected greatly by the customer interruption cost model used. The choice of the cost models can change system and load point reliability indices. In this study, a cascade correlation neural network is adopted to further develop two cost models comprising a probabilistic distribution model and an average or aggregate model. A contingency-based analytical technique is adopted to conduct the reliability worth analysis. Furthermore, the possible effects of adding distributed generation units into the network are evaluated. The proposed approach has been tested on a radial distribution test network evaluating the reliability worth. The results show that the probabilistic distribution model provides a more realistic model for the reliability analysis.

AB - Reliability worth analysis is of great importance in the area of distribution network planning and operation. The reliability worth's precision can be affected greatly by the customer interruption cost model used. The choice of the cost models can change system and load point reliability indices. In this study, a cascade correlation neural network is adopted to further develop two cost models comprising a probabilistic distribution model and an average or aggregate model. A contingency-based analytical technique is adopted to conduct the reliability worth analysis. Furthermore, the possible effects of adding distributed generation units into the network are evaluated. The proposed approach has been tested on a radial distribution test network evaluating the reliability worth. The results show that the probabilistic distribution model provides a more realistic model for the reliability analysis.

KW - Customer interruption cost model

KW - Distributed generation

KW - Neural networks

KW - Reliability worth analysis

U2 - 10.1109/TPWRS.2017.2705185

DO - 10.1109/TPWRS.2017.2705185

M3 - Journal article

VL - 33

SP - 412

EP - 420

JO - I E E E Transactions on Power Systems

JF - I E E E Transactions on Power Systems

SN - 0885-8950

IS - 1

ER -