Home > Research > Publications & Outputs > A heuristic for moment-matching scenario genera...

Research

Links

Text available via DOI:

Keywords

View graph of relations

A heuristic for moment-matching scenario generation

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

A heuristic for moment-matching scenario generation. / Høyland, Kjetil; Kaut, Michal; Wallace, S W.
In: Computational Optimization and Applications, Vol. 24, No. 2-3, 02.2003, p. 169-185.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Høyland, K, Kaut, M & Wallace, SW 2003, 'A heuristic for moment-matching scenario generation', Computational Optimization and Applications, vol. 24, no. 2-3, pp. 169-185. https://doi.org/10.1023/A:1021853807313

APA

Høyland, K., Kaut, M., & Wallace, S. W. (2003). A heuristic for moment-matching scenario generation. Computational Optimization and Applications, 24(2-3), 169-185. https://doi.org/10.1023/A:1021853807313

Vancouver

Høyland K, Kaut M, Wallace SW. A heuristic for moment-matching scenario generation. Computational Optimization and Applications. 2003 Feb;24(2-3):169-185. doi: 10.1023/A:1021853807313

Author

Høyland, Kjetil ; Kaut, Michal ; Wallace, S W. / A heuristic for moment-matching scenario generation. In: Computational Optimization and Applications. 2003 ; Vol. 24, No. 2-3. pp. 169-185.

Bibtex

@article{0ed7cf7dde7549a398b85145910803d2,
title = "A heuristic for moment-matching scenario generation",
abstract = "In stochastic programming models we always face the problem of how to represent the random variables. This is particularly difficult with multidimensional distributions. We present an algorithm that produces a discrete joint distribution consistent with specified values of the first four marginal moments and correlations. The joint distribution is constructed by decomposing the multivariate problem into univariate ones, and using an iterative procedure that combines simulation, Cholesky decomposition and various transformations to achieve the correct correlations without changing the marginal moments.With the algorithm, we can generate 1000 one-period scenarios for 12 random variables in 16 seconds, and for 20 random variables in 48 seconds, on a Pentium III machine.",
keywords = "stochastic programming, scenario tree generation , Cholesky decomposition , heuristics",
author = "Kjetil H{\o}yland and Michal Kaut and Wallace, {S W}",
year = "2003",
month = feb,
doi = "10.1023/A:1021853807313",
language = "English",
volume = "24",
pages = "169--185",
journal = "Computational Optimization and Applications",
issn = "0926-6003",
publisher = "Springer Netherlands",
number = "2-3",

}

RIS

TY - JOUR

T1 - A heuristic for moment-matching scenario generation

AU - Høyland, Kjetil

AU - Kaut, Michal

AU - Wallace, S W

PY - 2003/2

Y1 - 2003/2

N2 - In stochastic programming models we always face the problem of how to represent the random variables. This is particularly difficult with multidimensional distributions. We present an algorithm that produces a discrete joint distribution consistent with specified values of the first four marginal moments and correlations. The joint distribution is constructed by decomposing the multivariate problem into univariate ones, and using an iterative procedure that combines simulation, Cholesky decomposition and various transformations to achieve the correct correlations without changing the marginal moments.With the algorithm, we can generate 1000 one-period scenarios for 12 random variables in 16 seconds, and for 20 random variables in 48 seconds, on a Pentium III machine.

AB - In stochastic programming models we always face the problem of how to represent the random variables. This is particularly difficult with multidimensional distributions. We present an algorithm that produces a discrete joint distribution consistent with specified values of the first four marginal moments and correlations. The joint distribution is constructed by decomposing the multivariate problem into univariate ones, and using an iterative procedure that combines simulation, Cholesky decomposition and various transformations to achieve the correct correlations without changing the marginal moments.With the algorithm, we can generate 1000 one-period scenarios for 12 random variables in 16 seconds, and for 20 random variables in 48 seconds, on a Pentium III machine.

KW - stochastic programming

KW - scenario tree generation

KW - Cholesky decomposition

KW - heuristics

U2 - 10.1023/A:1021853807313

DO - 10.1023/A:1021853807313

M3 - Journal article

VL - 24

SP - 169

EP - 185

JO - Computational Optimization and Applications

JF - Computational Optimization and Applications

SN - 0926-6003

IS - 2-3

ER -