A novel multi-objective estimation of distribution algorithm for solving gas lift allocation problem

S. Omid H. Miresmaeili, Peyman Pourafshary, Farhang Jalali Farahani

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Gas lifting is a common practice in the oil industry. Using an appropriate gas lift injection rate can ensure that the desired oil production rate would be achieved. In the case of an oil field, the problem of distributing a certain amount of the available gas among a number of wells is formally known as a gas lift allocation problem. In this paper, a multi-objective optimization algorithm, based on the Gaussian Bayesian Networks and the Gaussian kernels, is proposed in order to determine the best injection points, considering multiple objective functions. Firstly, the problem is solved in a similar approach to the previous literature with similar gas lift data and similar function approximation method, to compare the performance of the proposed algorithm with the older ones. Thereafter, an extended problem is discussed, with minimizing the water production as a new optimization criterion. The developed multi-objective scheme is capable of handling and optimizing a gas-lift problem with several constraints and conflicting objectives such as controlling the gas usage and increasing theoil production, whereas in the conventional single-objective optimizations, any alteration in theconstraints demands a new optimization process and often there is no place for considering anadditional objective in the gas-lift allocation problem. The results obtained by the proposed optimization algorithm significantly overcame those reported in the previous similar literature. For a single-objective fifty-six well problem, the results exhibited 16.24% improvement in the total oil production.

Original languageEnglish
Pages (from-to)272-280
Number of pages9
JournalJournal of Natural Gas Science and Engineering
Volume23
DOIs
Publication statusPublished - Mar 1 2015

Fingerprint

Gas lifts
Gases
Bayesian networks
Oil fields
Multiobjective optimization
Oils
Water
Industry

Keywords

  • Gas lift allocation
  • Gaussian kernel
  • Gaussian network
  • Multi-objective optimization

ASJC Scopus subject areas

  • Energy Engineering and Power Technology

Cite this

A novel multi-objective estimation of distribution algorithm for solving gas lift allocation problem. / H. Miresmaeili, S. Omid; Pourafshary, Peyman; Jalali Farahani, Farhang.

In: Journal of Natural Gas Science and Engineering, Vol. 23, 01.03.2015, p. 272-280.

Research output: Contribution to journalArticle

@article{c3eccf2047a044fcacc2c72eb6c95ea8,
title = "A novel multi-objective estimation of distribution algorithm for solving gas lift allocation problem",
abstract = "Gas lifting is a common practice in the oil industry. Using an appropriate gas lift injection rate can ensure that the desired oil production rate would be achieved. In the case of an oil field, the problem of distributing a certain amount of the available gas among a number of wells is formally known as a gas lift allocation problem. In this paper, a multi-objective optimization algorithm, based on the Gaussian Bayesian Networks and the Gaussian kernels, is proposed in order to determine the best injection points, considering multiple objective functions. Firstly, the problem is solved in a similar approach to the previous literature with similar gas lift data and similar function approximation method, to compare the performance of the proposed algorithm with the older ones. Thereafter, an extended problem is discussed, with minimizing the water production as a new optimization criterion. The developed multi-objective scheme is capable of handling and optimizing a gas-lift problem with several constraints and conflicting objectives such as controlling the gas usage and increasing theoil production, whereas in the conventional single-objective optimizations, any alteration in theconstraints demands a new optimization process and often there is no place for considering anadditional objective in the gas-lift allocation problem. The results obtained by the proposed optimization algorithm significantly overcame those reported in the previous similar literature. For a single-objective fifty-six well problem, the results exhibited 16.24{\%} improvement in the total oil production.",
keywords = "Gas lift allocation, Gaussian kernel, Gaussian network, Multi-objective optimization",
author = "{H. Miresmaeili}, {S. Omid} and Peyman Pourafshary and {Jalali Farahani}, Farhang",
year = "2015",
month = "3",
day = "1",
doi = "10.1016/j.jngse.2015.02.003",
language = "English",
volume = "23",
pages = "272--280",
journal = "Journal of Natural Gas Science and Engineering",
issn = "1875-5100",
publisher = "Elsevier",

}

TY - JOUR

T1 - A novel multi-objective estimation of distribution algorithm for solving gas lift allocation problem

AU - H. Miresmaeili, S. Omid

AU - Pourafshary, Peyman

AU - Jalali Farahani, Farhang

PY - 2015/3/1

Y1 - 2015/3/1

N2 - Gas lifting is a common practice in the oil industry. Using an appropriate gas lift injection rate can ensure that the desired oil production rate would be achieved. In the case of an oil field, the problem of distributing a certain amount of the available gas among a number of wells is formally known as a gas lift allocation problem. In this paper, a multi-objective optimization algorithm, based on the Gaussian Bayesian Networks and the Gaussian kernels, is proposed in order to determine the best injection points, considering multiple objective functions. Firstly, the problem is solved in a similar approach to the previous literature with similar gas lift data and similar function approximation method, to compare the performance of the proposed algorithm with the older ones. Thereafter, an extended problem is discussed, with minimizing the water production as a new optimization criterion. The developed multi-objective scheme is capable of handling and optimizing a gas-lift problem with several constraints and conflicting objectives such as controlling the gas usage and increasing theoil production, whereas in the conventional single-objective optimizations, any alteration in theconstraints demands a new optimization process and often there is no place for considering anadditional objective in the gas-lift allocation problem. The results obtained by the proposed optimization algorithm significantly overcame those reported in the previous similar literature. For a single-objective fifty-six well problem, the results exhibited 16.24% improvement in the total oil production.

AB - Gas lifting is a common practice in the oil industry. Using an appropriate gas lift injection rate can ensure that the desired oil production rate would be achieved. In the case of an oil field, the problem of distributing a certain amount of the available gas among a number of wells is formally known as a gas lift allocation problem. In this paper, a multi-objective optimization algorithm, based on the Gaussian Bayesian Networks and the Gaussian kernels, is proposed in order to determine the best injection points, considering multiple objective functions. Firstly, the problem is solved in a similar approach to the previous literature with similar gas lift data and similar function approximation method, to compare the performance of the proposed algorithm with the older ones. Thereafter, an extended problem is discussed, with minimizing the water production as a new optimization criterion. The developed multi-objective scheme is capable of handling and optimizing a gas-lift problem with several constraints and conflicting objectives such as controlling the gas usage and increasing theoil production, whereas in the conventional single-objective optimizations, any alteration in theconstraints demands a new optimization process and often there is no place for considering anadditional objective in the gas-lift allocation problem. The results obtained by the proposed optimization algorithm significantly overcame those reported in the previous similar literature. For a single-objective fifty-six well problem, the results exhibited 16.24% improvement in the total oil production.

KW - Gas lift allocation

KW - Gaussian kernel

KW - Gaussian network

KW - Multi-objective optimization

UR - http://www.scopus.com/inward/record.url?scp=84922627354&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922627354&partnerID=8YFLogxK

U2 - 10.1016/j.jngse.2015.02.003

DO - 10.1016/j.jngse.2015.02.003

M3 - Article

AN - SCOPUS:84922627354

VL - 23

SP - 272

EP - 280

JO - Journal of Natural Gas Science and Engineering

JF - Journal of Natural Gas Science and Engineering

SN - 1875-5100

ER -