Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM)

Nur Fadilah Ab Aziz, T. K.Abdul Rahman, Z. Zakaria

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

This paper presents a new hybrid optimisation technique for voltage stability prediction called Artificial Immune Least Square Support Vector Machine (AILSVM). In this paper, a newly developed index named as Voltage Stability Condition Indicator (VSCI) was used to assess the stability condition of load buses in a system. VSCI was derived from a current equation in a complex form of a general 2-bus system. Support Vector Machine (SVM) has been proven to be a powerful tool for solving numerous problems in many fields. However, in order to obtain its best performance, a right combination of SVM parameters is needed. Therefore, Artificial Immune System (AIS) was used as the evolutionary search technique to optimise the value of SVM parameters. The simulations were carried out in a steady state analysis and the data generated were trained and tested under various types of loading conditions either due to an increase in active and/or reactive power. The obtained results show that the proposed methods can successfully give a very good prediction with the predicted values very close to the actual value. All simulations were tested on IEEE 30 bus Reliability Test Systems (RTS).

Original languageEnglish
Pages613-618
Number of pages6
DOIs
Publication statusPublished - 01 Jan 2014
Event2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014 - Langkawi, Malaysia
Duration: 24 Mar 201425 Mar 2014

Other

Other2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014
CountryMalaysia
CityLangkawi
Period24/03/1425/03/14

Fingerprint

Voltage control
Support vector machines
Immune system
Reactive power

All Science Journal Classification (ASJC) codes

  • Energy Engineering and Power Technology
  • Fuel Technology

Cite this

Ab Aziz, N. F., Rahman, T. K. A., & Zakaria, Z. (2014). Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM). 613-618. Paper presented at 2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014, Langkawi, Malaysia. https://doi.org/10.1109/PEOCO.2014.6814501
Ab Aziz, Nur Fadilah ; Rahman, T. K.Abdul ; Zakaria, Z. / Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM). Paper presented at 2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014, Langkawi, Malaysia.6 p.
@conference{1da8b241066f47549b552a5dfbefc942,
title = "Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM)",
abstract = "This paper presents a new hybrid optimisation technique for voltage stability prediction called Artificial Immune Least Square Support Vector Machine (AILSVM). In this paper, a newly developed index named as Voltage Stability Condition Indicator (VSCI) was used to assess the stability condition of load buses in a system. VSCI was derived from a current equation in a complex form of a general 2-bus system. Support Vector Machine (SVM) has been proven to be a powerful tool for solving numerous problems in many fields. However, in order to obtain its best performance, a right combination of SVM parameters is needed. Therefore, Artificial Immune System (AIS) was used as the evolutionary search technique to optimise the value of SVM parameters. The simulations were carried out in a steady state analysis and the data generated were trained and tested under various types of loading conditions either due to an increase in active and/or reactive power. The obtained results show that the proposed methods can successfully give a very good prediction with the predicted values very close to the actual value. All simulations were tested on IEEE 30 bus Reliability Test Systems (RTS).",
author = "{Ab Aziz}, {Nur Fadilah} and Rahman, {T. K.Abdul} and Z. Zakaria",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/PEOCO.2014.6814501",
language = "English",
pages = "613--618",
note = "2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014 ; Conference date: 24-03-2014 Through 25-03-2014",

}

Ab Aziz, NF, Rahman, TKA & Zakaria, Z 2014, 'Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM)', Paper presented at 2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014, Langkawi, Malaysia, 24/03/14 - 25/03/14 pp. 613-618. https://doi.org/10.1109/PEOCO.2014.6814501

Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM). / Ab Aziz, Nur Fadilah; Rahman, T. K.Abdul; Zakaria, Z.

2014. 613-618 Paper presented at 2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014, Langkawi, Malaysia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM)

AU - Ab Aziz, Nur Fadilah

AU - Rahman, T. K.Abdul

AU - Zakaria, Z.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents a new hybrid optimisation technique for voltage stability prediction called Artificial Immune Least Square Support Vector Machine (AILSVM). In this paper, a newly developed index named as Voltage Stability Condition Indicator (VSCI) was used to assess the stability condition of load buses in a system. VSCI was derived from a current equation in a complex form of a general 2-bus system. Support Vector Machine (SVM) has been proven to be a powerful tool for solving numerous problems in many fields. However, in order to obtain its best performance, a right combination of SVM parameters is needed. Therefore, Artificial Immune System (AIS) was used as the evolutionary search technique to optimise the value of SVM parameters. The simulations were carried out in a steady state analysis and the data generated were trained and tested under various types of loading conditions either due to an increase in active and/or reactive power. The obtained results show that the proposed methods can successfully give a very good prediction with the predicted values very close to the actual value. All simulations were tested on IEEE 30 bus Reliability Test Systems (RTS).

AB - This paper presents a new hybrid optimisation technique for voltage stability prediction called Artificial Immune Least Square Support Vector Machine (AILSVM). In this paper, a newly developed index named as Voltage Stability Condition Indicator (VSCI) was used to assess the stability condition of load buses in a system. VSCI was derived from a current equation in a complex form of a general 2-bus system. Support Vector Machine (SVM) has been proven to be a powerful tool for solving numerous problems in many fields. However, in order to obtain its best performance, a right combination of SVM parameters is needed. Therefore, Artificial Immune System (AIS) was used as the evolutionary search technique to optimise the value of SVM parameters. The simulations were carried out in a steady state analysis and the data generated were trained and tested under various types of loading conditions either due to an increase in active and/or reactive power. The obtained results show that the proposed methods can successfully give a very good prediction with the predicted values very close to the actual value. All simulations were tested on IEEE 30 bus Reliability Test Systems (RTS).

UR - http://www.scopus.com/inward/record.url?scp=84901339889&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901339889&partnerID=8YFLogxK

U2 - 10.1109/PEOCO.2014.6814501

DO - 10.1109/PEOCO.2014.6814501

M3 - Paper

AN - SCOPUS:84901339889

SP - 613

EP - 618

ER -

Ab Aziz NF, Rahman TKA, Zakaria Z. Voltage stability prediction by using Artificial Immune Least Square Support Vector Machines (AILSVM). 2014. Paper presented at 2014 IEEE 8th International Power Engineering and Optimization Conference, PEOCO 2014, Langkawi, Malaysia. https://doi.org/10.1109/PEOCO.2014.6814501