proneftPROНЕФТЬ. Профессионально о нефтиPROneft. Professionally about Oil2587-73992588-0055«Газпром нефть»10.24887/2587-7399-2019-2-30-36proneft-309Research ArticleРАЗРАБОТКА И ЭКСПЛУАТАЦИЯ НЕФТЯНЫХ МЕСТОРОЖДЕНИЙDEVELOPMENT AND OPERATION OF OIL FIELDSТехнология оптимизации фонда скважин системы поддержания пластового давления на основе гибридного моделированияTechnology for optimizing reservoir pressure maintenance system based on hybrid modelingЯубатыровР. Р.YaubatyrovR. R.

Saint-Petersburg

Yaubatyrov.RR@gazpromneft-ntc.ruКотежековВ. С.KotezhekovV. S.

Saint-Petersburg

Kotezhekov.VS@gazpromneft-ntc.ruБабинВ. М.BabinV. M.

Saint-Petersburg

Babin.VM@gazpromneft-ntc.ruНужинЕ. Е.NuzhinE. E.e.e.nuzhin@gmail.comНаучно-Технический Центр «Газпром нефти» (ООО «Газпромнефть НТЦ»)РоссияGazpromneft NTC LLCRussian FederationСколковский институт науки и технологийРоссияSkolkovo Institute of Science and TechnologyRussian Federation201912062022023036Copyright © Яубатыров Р.Р., Котежеков В.С., Бабин В.М., Нужин Е.Е., 20222022Яубатыров Р.Р., Котежеков В.С., Бабин В.М., Нужин Е.Е.Yaubatyrov R.R., Kotezhekov V.S., Babin V.M., Nuzhin E.E.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://proneft.elpub.ru/jour/article/view/309

Приведен сравнительный анализ современных численных алгоритмов гибридной оптимизации применительно к решению задачи повышения эффективности системы поддержания пластового давления (ППД) на разрабатываемом месторождении. При помощи анализируемых оптимизационных алгоритмов на основе гидродинамической модели месторождения многовариантными итерационными расчетами проводится поиск оптимальной стратегии заводнения (оптимальное сочетание режимов работы скважин системы ППД), которая максимизирует экономику разрабатываемого месторождения, выраженную величиной чистого дисконтированного дохода NPV. Сравнение гибридных оптимизационных алгоритмов было проведено на основе решения задачи по оптимизации системы ППД для реально существующего месторождения на поздней стадии разработки с действующим фондом более 100 скважин. Кроме того, данные оптимизационные алгоритмы сравнивались с алгоритмами, в которых не используется гибридное моделирование. Сопоставление оптимизационных алгоритмов проводилось при решении задачи оптимизации фонда ППД на основе гидродинамической модели. Исследовалось улучшение целевой функции NPV по отношению к числу проведенных расчетов на гидродинамической модели. В результате проанализирована эффективность гибридных подходов применительно к конкретной задаче оптимизации, а также получен набор рекомендаций по выбору наиболее эффективного алгоритма в зависимости от доступного проектного времени.

The paper presents a comparative analysis of advanced numerical hybrid optimization algorithms for solving a specific problem of increasing the efficiency of the waterflooding in a mature field (Brownfield). Via multivariate iterative calculations produced by the optimization algorithm, on the basis of the reservoir simulation model the optimal waterflooding strategy (optimal combination of well modes) is determined. This strategy maximizes the economics of the field which is expressed in the value of net present value (NPV). The optimization process in most practically significant cases is complicated by the following factors: large dimension of the solution space, high complexity of the optimized function and high computational cost of each reservoir simulation. As a result, for the allocated project time the final solution can strongly depend on the chosen optimization algorithm. Comparison of the hybrid algorithms was based on the solution of the real Brownfield waterflooding optimization problem with more than 100 active wells. In addition, these optimization algorithms were compared with algorithms that do not use hybrid modeling.Relative improvements of the objective function, NPV, were compared with respect to the number of required reservoir simulations. As a result, the set of recommendations for choosing the most effective algorithm depending on the available project time was obtained. As a result, an analysis was made of the effectiveness of hybrid optimization methods as applied to a specific optimization problem, and a set of recommendations was obtained for choosing the most efficient algorithm depending on the available project time.

оптимизация системы поддержания пластового давления (ППД)методы оптимизациигидродинамическое моделированиегибридное моделированиеwaterflooding optimizationoptimization methodshydrodynamic simulationhybrid modelingReferencesWaterflood management using two-stage optimization with streamline simulation / W. Tailai, R.T. Marco, D.T. Ciaurri [et al.] // Computers & Geosciences. – 2014. – V. 18. – № 3-4. – Р. 483–504.Tailai W., Marco R.T., Ciaurri D.T., Khalid A., Yinyu Y., Waterflood management using two-stage optimization with streamline simulation, Computational Geosciences, 2014, V. 18, no. 3-4, pp. 483–504.Robust Waterflooding Optimization of Multiple Geological Scenarios / G.M. Van Essen, M.J. Zandvliet, P.M.J. Van den Hof [et al.] // SPE 102913–MS. – 2006.Van Essen G.M., Zandvliet M.J.,. Van den Hof P.M.J, Bosgra O.H., Delft U., Robust waterflooding optimization of multiple geological scenarios, SPE 102913-MS, 2006.Echeverrıa C.D., Mukerji T., Durlofsky L.J. Derivative free optimization for oil field operations / edited by X.S. Yang, S. Koziel // Computational Optimization and Applications in Engineering and Industry, Studies in Computational Intelligence, New York: Springer, 2011. – Р. 19–55.Echeverrıa C.D., Mukerji T., Durlofsky L.J., Derivative free optimization for oil field operations: edited by Yang X.S., Koziel S., Computational Optimization and Applications in Engineering and Industry, Studies in Computational Intelligence, New York: Springer, 2011, pp. 19–55.Müller J., Shoemaker C.A., Piché R. SO–I: A Surrogate Model Algorithm for Expensive Nonlinear Integer Programming Problems Including Global Optimization Applications // Journal of Global Optimization. – 2014. – V. 59. – № 4. – Р. 865–889.Müller J., Shoemaker C.A., Piché R., SO-I: a surrogate model algorithm for expensive nonlinear integer programming problems including global optimization applications, Journal of Global Optimization, 2014, V. 59, no.4, pp. 865–889.Regis R.G., Shoemaker C.A. A stochastic radial basis function method for the global optimization of expensive functions // INFORMS Journal on Computing. – 2007. – V. 19. – № 4. – Р. 497–509.Regis R.G., Shoemaker C.A., A stochastic radial basis function method for the global optimization of expensive functions, INFORMS Journal on Computing, 2007, V. 19, no. 4, pp. 497–509, DOI:10.1287/ijoc.1060.0182Costa A., Nannicini G. RBFOpt: an open-source library for black-box optimization with costly function evaluations // Mathematical Programming Computation. – 2018. – V. 10. – № 4. – Р. 597–629.Costa A., Nannicini G., RBFOpt: an open-source library for black-box optimization with costly function evaluations, Mathematical Programming Computation, 2018, V. 10, no. 4, pp 597–629.Mockus J. Bayesian approach to global optimization: theory and applications. – Springer Netherlands, 1989. – 270 p.Mockus J., Bayesian approach to global optimization: theory and applications, Springer Netherlands, 1989, 270 p., DOI: 10.1007/978-94-009-0909-0.Dudley R.M. Real Analysis and Probability. – Cambridge: Cambridge University Press, 2004. – 555 p.Dudley R.M., Real analysis and probability, Cambridge University Press, 2004, 555 p.Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting / N. Srinivas, A. Krause, Sh.M. Kakade, M.W. Seeger // IEEE Transactions on Information Theory. – 2012. – V. 58. № 5. – Р. 3250–3265.Srinivas N., Krause A., Kakade Sh.M., Seeger M.W., Information-theoretic regret bounds for Gaussian process optimization in the bandit setting, IEEE Transactions on Information Theory, 2012, V. 58, no. 5, pp. 3250–3265.Ho Tin Ka. Random Decision Forests // Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August, 1995 // IEEE Computer Society Washington, DC, USA. – 1995. – V. 1. – P. 278.Ho Tin Ka, Random decision forests, Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, 14–16 August 1995, IEEE Computer Society Washington, DC, USA, V. 1, p. 278.Isebor O.J., Durlofsky L.J., Ciaurri D.E. A derivative-free methodology with local and global search for the constrained joint optimization of well locations and controls // Computational Geosciences. – 2014. – V. 18(3-4). – P. 463-482.Isebor O.J., Durlofsky L.J., Ciaurri D.E., A derivative-free methodology with local and global search for the constrained joint optimization of well locations and controls, Computational Geosciences, 2014, V. 18(3-4), pp. 463-482.Kennedy J., Eberhart R.C. Particle swarm optimization // Proceedings of IEEE International Joint Conference on Neural Networks. – 1995. – P. 1942–1948.Kennedy J., Eberhart R.C., Particle swarm optimization, Proceedings of IEEE International Joint Conference on Neural Networks, 1995, pp. 1942-1948.Yaubatyrov R.R., Babin V.M., Akmadieva L.I. Grid Cluster in the Office: High–Performance Computing for Reservoir Management // SPE 191519-MS. – 2018.Yaubatyrov R.R, Babin, V.M., Akmadieva L.I., Grid cluster in the office: high-performance computing for reservoir management, SPE 191519-MS, 2018.

The authors declare that there are no conflicts of interest present.