Two-stage fuzzy stochastic programming with Value-at-Risk criteria

Shuming Wang, Junzo Watada

    Research output: Contribution to journalArticle

    27 Citations (Scopus)

    Abstract

    A new class of fuzzy stochastic optimization models - two-stage fuzzy stochastic programming with Value-at-Risk (FSP-VaR) criteria is built in this paper. Some properties of the two-stage FSP-VaR, such as value of perfect information (VPI), value of fuzzy random solution (VFRS), and bounds of the fuzzy random solution, are discussed. An Approximation Algorithm is proposed to compute the VaR by combining discretization method of fuzzy variable, random simulation technique and bisection method. The convergence of the approximation algorithm is proved. To solve the two-stage FSP-VaR, a hybrid mutation-neighborhood-based particle swarm optimization (MN-PSO) which comprises the Approximation Algorithm is proposed to search for the approximate optimal solution. Furthermore, a neural network-based acceleration method is discussed. A numerical experiment illustrates the effectiveness of the proposed hybrid MN-PSO algorithm. The comparison shows that the hybrid MN-PSO exhibits better performance than the one when using other approaches such as hybrid PSO and GA.

    Original languageEnglish
    Pages (from-to)1044-1056
    Number of pages13
    JournalApplied Soft Computing Journal
    Volume11
    Issue number1
    DOIs
    Publication statusPublished - 2011 Jan

    Fingerprint

    Stochastic programming
    Particle swarm optimization (PSO)
    Approximation algorithms
    Random variables
    Neural networks
    Experiments

    Keywords

    • Fuzzy random variable
    • Fuzzy stochastic programming
    • Particle swarm optimization
    • Value of fuzzy random solution
    • Value of perfect information
    • Value-at-Risk

    ASJC Scopus subject areas

    • Software

    Cite this

    Two-stage fuzzy stochastic programming with Value-at-Risk criteria. / Wang, Shuming; Watada, Junzo.

    In: Applied Soft Computing Journal, Vol. 11, No. 1, 01.2011, p. 1044-1056.

    Research output: Contribution to journalArticle

    Wang, Shuming ; Watada, Junzo. / Two-stage fuzzy stochastic programming with Value-at-Risk criteria. In: Applied Soft Computing Journal. 2011 ; Vol. 11, No. 1. pp. 1044-1056.
    @article{ad22b55decd14c2594f996ff712a1082,
    title = "Two-stage fuzzy stochastic programming with Value-at-Risk criteria",
    abstract = "A new class of fuzzy stochastic optimization models - two-stage fuzzy stochastic programming with Value-at-Risk (FSP-VaR) criteria is built in this paper. Some properties of the two-stage FSP-VaR, such as value of perfect information (VPI), value of fuzzy random solution (VFRS), and bounds of the fuzzy random solution, are discussed. An Approximation Algorithm is proposed to compute the VaR by combining discretization method of fuzzy variable, random simulation technique and bisection method. The convergence of the approximation algorithm is proved. To solve the two-stage FSP-VaR, a hybrid mutation-neighborhood-based particle swarm optimization (MN-PSO) which comprises the Approximation Algorithm is proposed to search for the approximate optimal solution. Furthermore, a neural network-based acceleration method is discussed. A numerical experiment illustrates the effectiveness of the proposed hybrid MN-PSO algorithm. The comparison shows that the hybrid MN-PSO exhibits better performance than the one when using other approaches such as hybrid PSO and GA.",
    keywords = "Fuzzy random variable, Fuzzy stochastic programming, Particle swarm optimization, Value of fuzzy random solution, Value of perfect information, Value-at-Risk",
    author = "Shuming Wang and Junzo Watada",
    year = "2011",
    month = "1",
    doi = "10.1016/j.asoc.2010.02.004",
    language = "English",
    volume = "11",
    pages = "1044--1056",
    journal = "Applied Soft Computing",
    issn = "1568-4946",
    publisher = "Elsevier BV",
    number = "1",

    }

    TY - JOUR

    T1 - Two-stage fuzzy stochastic programming with Value-at-Risk criteria

    AU - Wang, Shuming

    AU - Watada, Junzo

    PY - 2011/1

    Y1 - 2011/1

    N2 - A new class of fuzzy stochastic optimization models - two-stage fuzzy stochastic programming with Value-at-Risk (FSP-VaR) criteria is built in this paper. Some properties of the two-stage FSP-VaR, such as value of perfect information (VPI), value of fuzzy random solution (VFRS), and bounds of the fuzzy random solution, are discussed. An Approximation Algorithm is proposed to compute the VaR by combining discretization method of fuzzy variable, random simulation technique and bisection method. The convergence of the approximation algorithm is proved. To solve the two-stage FSP-VaR, a hybrid mutation-neighborhood-based particle swarm optimization (MN-PSO) which comprises the Approximation Algorithm is proposed to search for the approximate optimal solution. Furthermore, a neural network-based acceleration method is discussed. A numerical experiment illustrates the effectiveness of the proposed hybrid MN-PSO algorithm. The comparison shows that the hybrid MN-PSO exhibits better performance than the one when using other approaches such as hybrid PSO and GA.

    AB - A new class of fuzzy stochastic optimization models - two-stage fuzzy stochastic programming with Value-at-Risk (FSP-VaR) criteria is built in this paper. Some properties of the two-stage FSP-VaR, such as value of perfect information (VPI), value of fuzzy random solution (VFRS), and bounds of the fuzzy random solution, are discussed. An Approximation Algorithm is proposed to compute the VaR by combining discretization method of fuzzy variable, random simulation technique and bisection method. The convergence of the approximation algorithm is proved. To solve the two-stage FSP-VaR, a hybrid mutation-neighborhood-based particle swarm optimization (MN-PSO) which comprises the Approximation Algorithm is proposed to search for the approximate optimal solution. Furthermore, a neural network-based acceleration method is discussed. A numerical experiment illustrates the effectiveness of the proposed hybrid MN-PSO algorithm. The comparison shows that the hybrid MN-PSO exhibits better performance than the one when using other approaches such as hybrid PSO and GA.

    KW - Fuzzy random variable

    KW - Fuzzy stochastic programming

    KW - Particle swarm optimization

    KW - Value of fuzzy random solution

    KW - Value of perfect information

    KW - Value-at-Risk

    UR - http://www.scopus.com/inward/record.url?scp=77957917247&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77957917247&partnerID=8YFLogxK

    U2 - 10.1016/j.asoc.2010.02.004

    DO - 10.1016/j.asoc.2010.02.004

    M3 - Article

    VL - 11

    SP - 1044

    EP - 1056

    JO - Applied Soft Computing

    JF - Applied Soft Computing

    SN - 1568-4946

    IS - 1

    ER -