Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine

Mohd Wazir Mustafa, Saifulnizam Abd Khalid, Mohd Herwan Sulaiman, Hussain Shareef

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    6 Citations (Scopus)

    Abstract

    This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.

    Original languageEnglish
    Title of host publication2010 9th International Power and Energy Conference, IPEC 2010
    Pages1164-1169
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event2010 9th International Power and Energy Conference, IPEC 2010 - Singapore
    Duration: 27 Oct 201029 Oct 2010

    Other

    Other2010 9th International Power and Energy Conference, IPEC 2010
    CitySingapore
    Period27/10/1029/10/10

    Fingerprint

    Support vector machines
    Genetic algorithms
    Supervised learning
    Learning systems
    Neural networks

    Keywords

    • Artificial neural network (ANN)
    • Genetic algorithm (GA)
    • Least squares support vector machine (LS-SVM)
    • Machine learning
    • Proportional sharing princple (PSP)

    ASJC Scopus subject areas

    • Energy Engineering and Power Technology

    Cite this

    Mustafa, M. W., Khalid, S. A., Sulaiman, M. H., & Shareef, H. (2010). Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine. In 2010 9th International Power and Energy Conference, IPEC 2010 (pp. 1164-1169). [5696998] https://doi.org/10.1109/IPECON.2010.5696998

    Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine. / Mustafa, Mohd Wazir; Khalid, Saifulnizam Abd; Sulaiman, Mohd Herwan; Shareef, Hussain.

    2010 9th International Power and Energy Conference, IPEC 2010. 2010. p. 1164-1169 5696998.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Mustafa, MW, Khalid, SA, Sulaiman, MH & Shareef, H 2010, Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine. in 2010 9th International Power and Energy Conference, IPEC 2010., 5696998, pp. 1164-1169, 2010 9th International Power and Energy Conference, IPEC 2010, Singapore, 27/10/10. https://doi.org/10.1109/IPECON.2010.5696998
    Mustafa MW, Khalid SA, Sulaiman MH, Shareef H. Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine. In 2010 9th International Power and Energy Conference, IPEC 2010. 2010. p. 1164-1169. 5696998 https://doi.org/10.1109/IPECON.2010.5696998
    Mustafa, Mohd Wazir ; Khalid, Saifulnizam Abd ; Sulaiman, Mohd Herwan ; Shareef, Hussain. / Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine. 2010 9th International Power and Energy Conference, IPEC 2010. 2010. pp. 1164-1169
    @inproceedings{685bc9f7366d4a3e91fb843b913faf93,
    title = "Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine",
    abstract = "This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.",
    keywords = "Artificial neural network (ANN), Genetic algorithm (GA), Least squares support vector machine (LS-SVM), Machine learning, Proportional sharing princple (PSP)",
    author = "Mustafa, {Mohd Wazir} and Khalid, {Saifulnizam Abd} and Sulaiman, {Mohd Herwan} and Hussain Shareef",
    year = "2010",
    doi = "10.1109/IPECON.2010.5696998",
    language = "English",
    isbn = "9781424473991",
    pages = "1164--1169",
    booktitle = "2010 9th International Power and Energy Conference, IPEC 2010",

    }

    TY - GEN

    T1 - Power flow allocation method with the application of hybrid genetic algorithm-least squares support vector machine

    AU - Mustafa, Mohd Wazir

    AU - Khalid, Saifulnizam Abd

    AU - Sulaiman, Mohd Herwan

    AU - Shareef, Hussain

    PY - 2010

    Y1 - 2010

    N2 - This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.

    AB - This paper proposes a new power flow allocation method in pool based power system with the application of hybrid genetic algorithm (GA) and least squares support vector machine (LS-SVM), namely GA-SVM. GA is utilized to find the optimal values of regularization parameter, γ and Kernel RBF parameter, σ2, which are embedded in LS-SVM model so that the power flow allocation problem can be solved by using machine learning adaptation approach. The supervised learning paradigm is used to train the LS-SVM model where the proportional sharing principle (PSP) method is utilized as a teacher. Based on converged load flow and followed by PSP technique for power tracing procedure, the description of inputs and outputs of the training data are created. The GA-SVM model will learn to identify which generators are supplying to which loads. In this paper, the 25-bus equivalent system of southern Malaysia is used to illustrate the proposed method. The comparison result with artificial neural network (ANN) technique is also will be presented.

    KW - Artificial neural network (ANN)

    KW - Genetic algorithm (GA)

    KW - Least squares support vector machine (LS-SVM)

    KW - Machine learning

    KW - Proportional sharing princple (PSP)

    UR - http://www.scopus.com/inward/record.url?scp=79951659496&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79951659496&partnerID=8YFLogxK

    U2 - 10.1109/IPECON.2010.5696998

    DO - 10.1109/IPECON.2010.5696998

    M3 - Conference contribution

    SN - 9781424473991

    SP - 1164

    EP - 1169

    BT - 2010 9th International Power and Energy Conference, IPEC 2010

    ER -