Multi-solution well placement optimization using ensemble learning of surrogate models

Salehian, Mohammad; Sefat, Morteza Haghighat; Muradov, Khafiz

doi:10.1016/j.petrol.2021.110076

Cited by 19 publications

(6 citation statements)

References 100 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developed online proxy model is iteratively updated to ensure it mimics the global performance of the objective function with reasonable accuracy. This approach is found to provide superior performance as compared to the offline sampling techniques [53]. Note that the proxy is only used for sensitivity analysis as explained in the next section.…”

Section: Initial Optimization Stagementioning

confidence: 99%

See 1 more Smart Citation

Hybrid Framework for Enhanced Dynamic Optimization of Intelligent Completion Design in Multilateral Wells with Multiple Types of Flow Control Devices

Ahdeema,

Haghighat Sefat,

Muradov

2023

Energies

Self Cite

View full text Add to dashboard Cite

Multilateral wells (MLWs) equipped with multiple flow control devices (FCDs) are becoming increasingly favored within the oil sector due to their ability to enhance well-to-reservoir exposure and effectively handle unwanted fluid breakthrough. However, combining various types of FCDs in multilateral wells poses a complex optimization problem with a large number of highly correlated control variables and a computationally expensive objective function. Consequently, standard optimization algorithms, including metaheuristic and gradient-based approaches, may struggle to identify an optimal solution within a limited computational resource. This paper introduces a novel hybrid optimization (HO) framework combining particle swarm optimization (PSO) and Simultaneous Perturbation Stochastic Approximation (SPSA). It is developed to efficiently optimize the completion design of MLWs with various FCDs while overcoming the individual limitations of each optimization algorithm. The proposed framework is further enhanced by employing surrogate modelling and global sensitivity analysis to identify critical parameters (i.e., highly sensitive) that greatly affect the objective function. This allows for a focused optimization effort on these key parameters, ultimately enhancing global optimization performance. The performance of the novel optimization framework is evaluated using the Olympus benchmark reservoir model. The model is developed by three intelligent dual-lateral wells, with inflow control devices (ICDs) installed within the laterals and interval control valves (ICVs) positioned at the lateral junctions. The results show that the proposed hybrid optimization framework outperforms all industry-standard optimization techniques, achieving a Net Present Value of approximately USD 1.94 billion within a limited simulation budget of 2500 simulation runs. This represents a substantial 26% NPV improvement compared to the open-hole case (USD 1.54 billion NPV). This improvement is attributed to more efficient water breakthrough management, leading to a notable 24% reduction in cumulative water production and, consequently, a 26% increase in cumulative oil production.

show abstract

Section: Initial Optimization Stagementioning

confidence: 99%

“…where SSE and SST represent the sum of square error and the sum of total error, respectively. J act This approach is found to provide superior performance as compared to the offline sampling techniques [53]. Note that the proxy is only used for sensitivity analysis as explained in the next section.…”

Section: Initial Optimization Stagementioning

confidence: 99%

Hybrid Framework for Enhanced Dynamic Optimization of Intelligent Completion Design in Multilateral Wells with Multiple Types of Flow Control Devices

Ahdeema,

Haghighat Sefat,

Muradov

2023

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Therefore, they look for new ways to establish surrogate models as the basis of optimization algorithms, and data-driven artificial intelligence models are one of them (Liu et al, 2021;Peng et al, 2022;Zhang et al, 2022;Zhong et al, 2022). Salehian et al (2022) utilized an ensemble learning of surrogatemodels-assisted optimization framework, incorporating Convolutional Neural Network (CNN) and Simultaneous Perturbation Stochastic Approximation (SPSA), to provide diverse and near-optimum well placement solutions with reduced computational cost, achieving superior operational flexibility and computational efficiency compared to conventional methods in the Brugge and Egg field case studies. Moolya et al (2022) employed a hybrid approach combining surrogate modeling and Multiperiod Mixed-Integer Linear Programming (MILP), alongside a novel methodology of Spatial Aggregation and Disaggregation, to efficiently determine optimal producer locations accounting for surface infrastructure constraints, significantly reducing computational expenses while ensuring maximization of the NPV.…”

Section: Figurementioning

confidence: 99%

Horizontal well placement optimization based on matrix directional continuous element summation algorithm

Huang,

Wang,

et al. 2024

Front. Energy Res.

View full text Add to dashboard Cite

During the course of actual oilfield development, judicious selection and design of well placement are paramount due to cost constraints and operating conditions. This paper introduces the Matrix Directional Continuous Elements Summation Algorithm (MDCESA), which is utilized to identify that segment with the largest summation for a given length in a 2D or a 3D matrix. An additional function that accounts for the distance between segments was added when searching for multiple segments to avoid intersections or overlaps between segments. The well placement optimization was transformed into a segment summation on a 3D matrix. Our findings reveal significant advancements in well placement optimization. Employing the MDCESA method, six producers were identified and their production performance was compared against two previously selected producers using a reservoir numerical simulator. The results demonstrated that the wells selected through MDCESA exhibited a substantial improvement in production efficiency. Specifically, there was an 11.6% increase in average cumulative oil production over a 15-year period compared to the wells selected by traditional methods. This research not only presents a significant leap in well placement optimization but also sets a foundation for further innovations in reservoir management and development strategies in offshore oilfields.

show abstract

“…In the domain of reservoir and production engineering, proxy models can provide an alternative to overcome the current computational limitations in reservoir modeling (tremendous run time and memory consumption). In this aspect, most studies have worked with only one geological model and there are few studies focusing on the feasibility of this idea begin applied in different geological models (considering geological uncertainty) [21,22]. Some studies have also mentioned that the proxy would reflect the complexity of the reservoir model, yet quantitative results are to be found [14].…”

Section: Possibilities For Proxy Modeling Improvementmentioning

confidence: 99%

Proxy Model Development for the Optimization of Water Alternating CO2 Gas for Enhanced Oil Recovery

Matthew

Ghahfarokhi

et al. 2023

Energies

View full text Add to dashboard Cite

Optimization studies are an important task in reservoir engineering practices such as production optimization and EOR (Enhanced Oil Recovery) assessments. However, they are extensive studies with many simulations that require huge computational effort and resources. In terms of EOR, CO2 injection is one of the most common methods employed due to a high recovery potential and environmental benefits. To assess the feasibility of CO2-EOR projects, a reservoir design study must be conducted before optimization is performed. Some studies have demonstrated the advantages of employing proxy models to perform this task in terms of saving huge amounts of computer memory space and time. In this study, proxy models were developed to solve a multi-objective optimization problem using NSGA-II (Non-dominated Sorting Genetic Algorithm II) in two selected reservoir models. The study was performed for a CO2-WAG (Water Alternating Gas) application, where gas and water injection rates and half-cycle lengths were assessed to maximize the oil recovery and CO2 stored in the reservoir. One model represents a simple geological model (the Egg Model), while the other represents a complex model (the Gullfaks Model). In this study, the good performance of the proxy models generated accurate results that could be improved by increasing the amount of sampling and segmenting the behavior of the reservoir model (depending on the complexity of the reservoir model). The developed proxies have an average error of less than 2% (compared with simulation results) and are concluded to be robust based on the blind test results. It has also been found that to reach the maximum oil recovery using CO2-WAG, the maximum gas injection rate with the minimum water injection rate is required. However, this configuration may result in a reduction in the total CO2 stored in the reservoir.

show abstract

Multi-solution well placement optimization using ensemble learning of surrogate models

Cited by 19 publications

References 100 publications

Hybrid Framework for Enhanced Dynamic Optimization of Intelligent Completion Design in Multilateral Wells with Multiple Types of Flow Control Devices

Hybrid Framework for Enhanced Dynamic Optimization of Intelligent Completion Design in Multilateral Wells with Multiple Types of Flow Control Devices

Horizontal well placement optimization based on matrix directional continuous element summation algorithm

Proxy Model Development for the Optimization of Water Alternating CO2 Gas for Enhanced Oil Recovery

Contact Info

Product

Resources

About