Method for optimizing reservoir management using k-means clustering particle swarm optimization

Abstract

A method for performing reservoir management at a wellsite is disclosed. The method includes receiving data from a plurality of sources and generating a reservoir model from the received data. Generating the reservoir model includes initializing a plurality of particles based upon the received data; evaluating an objective function at a position for each of the particles; and updating the position for each of the particles. The method further includes displaying the generated reservoir model on a display.

Description

PATENT Atorney Docket No.: IS24.1190-US-NPMETHOD FOR OPTIMIZING RESERVOIR MANAGEMENT USING K-MEANS CLUSTERING PARTICLE SWARM OPTIMIZATIONCross-Reference to Related Applications

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 730,546, filed on December 11, 2024, which is incorporated by reference.Background

[0002] Reservoir simulation is a tool used to model subsurface flow in porous media. Reservoir simulation is a proven method, used in petroleum and energy industries to assess, model and predict a reservoir’s performance. To assimilate data from different sources and generate a reservoir model capable of reproducing historical data, an inverse problem may be solved by applying non-linear optimization algorithms. Data sources may include seismic data, laboratory data, rock data, and special core analysis (SCAL) data. Laboratory data may include pressurevolume-temperature (PVT) fluid data, while rock data may include porosity or permeability data. Many prior attempts have been made to improve reservoir simulation using some different variation of a particle swarm algorithm in an optimization problem. However, these prior attempts have not combined the clustering K-Means and particle swarm optimization (PSO) methods in a problem with multiple minima.

[0003] What is needed is a new optimization method that tackles practical reservoir simulation problems. The method may be to obtain a good approximation of any number of local minima in a single run, avoiding excessive calls of the reservoir simulator.Summary

[0004] The present disclosure includes a method for performing reservoir management at a wellsite. The method may include receiving data from a plurality of sources and generating a reservoir model from the received data. Generating the reservoir model may include initializing a plurality of particles based upon the received data; evaluating an objective function at a position for each of the particles; and updating the position for each of the particles. The method may further include displaying the generated reservoir model on a display.PATENT Atorney Docket No.: IS24.1190-US-NP

[0005] The present disclosure also includes a computing system. The computing system may include one or more processors and a memory system. The memory system may include one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations. The operations may include receiving data from a plurality of sources disposed at a wellsite; generating a reservoir model from the received data; and displaying the generated reservoir model on a display. Generating the reservoir model may include initializing a plurality of particles based upon the received data and iteratively performing at least one time: evaluating an objective function at a position for each of the particles; and updating the position of the particles based upon the objective function. Updating the position of the particles based upon the objective function may include updating a best position of the particles; updating clusters of the particles; merging at least two particles when a proximity threshold is met; and updating a previous position and a previous velocity of each of the particles.

[0006] The present disclosure further includes a non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, may cause the computing system to perform operations. The operations may include receiving data from a plurality of sources, generating a reservoir model from the received data, displaying the generated reservoir model on a display, and performing a wellsite action based on the generated reservoir model. The sources may include at least one of seismic data, laboratory data, rock data, or special core analysis (SCAL) data. The laboratory data may include pressure-volume- temperature (PVT) fluid data, and the rock data may include at least one of porosity or permeability. The reservoir model may be configured to reproduce historical data of the reservoir. Generating the reservoir model may include initializing a plurality of particles and iteratively performing at least one time: evaluating an objective function at a position for each of the particles and updating the positions of the particles. Each of the particles may include an initial position in a parameter space and an initial velocity in the parameter space. The initial position of each of the particles may be determined using a Latin Hypercube algorithm and the initial velocity of each of the particles is randomly assigned using a uniform distribution to cover a maximum of 5% of a domain in a next iteration in any direction. The parameters in the parameter space may include one or more of permeability, porosity, fluid properties, or relative permeability input relative to the reservoir model. The algorithm may be parallelized such that performance of evaluating thePATENT Atorney Docket No.: IS24.1190-US-NP objective function may be distributed over a plurality of CPU cores or computing cluster nodes. The objective function may include at least one of a difference between measured flow rate and pressure and modeled flow rate and pressure, net present value, or oil and / or gas production rate. Updating the positions may include updating a best position of the particles, updating clusters of the particles, merging at least two particles when a proximity threshold is met, and updating the previous position and previous velocity of each of the particles. Updating the best position of the particles may include defining a location where the objective function for each particle may be lowest during a life cycle of the particle. Updating clusters of the particles may include determining an optimum number of clusters, determining a location of each of the clusters, and identifying a best cluster position based upon the best position of the particles within each cluster. Determining the optimum number of clusters may include maximizing a Silhouette Score, and updating the clusters may further include determining a best particle inside each cluster by evaluating a PBest within each cluster. Merging at least two particles when the proximity threshold is reached may include merging the two particles to a position and resultant velocity corresponding to the best of the two particles and restarting the remaining particle of the two particles in an aleatory position inside a domain, where the best of the two particles may include the particle having the best history, where the best history may include having the lowest or highest objective function value over the entire history of the particle. Updating the position and velocity of each of the particles may be based on the identified best cluster position, where a current velocity of each of the particles may include a weighted sum of at least one of a velocity, a personal velocity, and a social velocity. Performing the wellsite action may include generating or transmitting a signal that instructs or causes an action to occur. The action may include a physical action. The physical action may include selecting where to drill a wellbore in the subsurface formation, drilling the wellbore, varying a trajectory of the wellbore, varying a weight or torque on a drill bit that is drilling the wellbore, varying a rate or concentration of a fluid being pumped into the wellbore, specifying an order of drilling for multiple wells, optimizing well control by opening and closing wells to minimize water production and / or to optimize oil and / or gas flow rate, or a combination thereof.

[0007] The present disclosure addresses the above challenges by providing an optimization method that is designed to solve problems with a time consuming objective function and multiple minima. In reservoir simulations, any history matching or optimization workflow needs to run a full simulation case to evaluate the objective function, making this method an appropriatePATENT Atorney Docket No.: IS24.1190-US-NP application. This method may also be easily parallelized, helping the application in multi-CPU scenarios, including clusters and cloud architectures.

[0008] It will be appreciated that this summary is intended merely to introduce some aspects of the present methods, systems, and media, which are more fully described and / or claimed below. Accordingly, this summary is not intended to be limiting.Brief Description of the Drawings

[0009] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures:

[0010] Figure 1 illustrates an example of a system that includes various management components to manage various aspects of a geologic environment, according to an embodiment.

[0011] Figure 2 illustrates a visual representation of a clustering procedure used by the current workflow, according to an embodiment.

[0012] Figure 3 illustrates a visual representation of a splash procedure when applied in two particles, according to an embodiment.

[0013] Figure 4 illustrates a graphical representation of how velocity of a particle may be updated using the current workflow, according to an embodiment.

[0014] Figure 5 illustrates a flowchart of a method for optimizing reservoir management, according to an embodiment.

[0015] Figure 6 illustrates a schematic view of a computing system for performing at least a portion of the method(s) described herein, according to an embodiment.Detailed Description

[0016] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to one of ordinary skill in the art that the disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.PATENT Atorney Docket No.: IS24.1190-US-NP

[0017] It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope of the present disclosure. The first object or step, and the second object or step, are both, objects or steps, respectively, but they are not to be considered the same object or step.

[0018] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in this description and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Further, as used herein, the term “if’ may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.

[0019] Attention is now directed to processing procedures, methods, techniques, and workflows that are in accordance with some embodiments. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined and / or the order of some operations may be changed.System Overview

[0020] Figure 1 illustrates an example of a system 100 that includes various management components 110 to manage various aspects of a geologic environment 150 (e.g., an environment that includes a sedimentary basin, a reservoir 151, one or more faults 153-1, one or more geobodies 153-2, etc.). For example, the management components 110 may allow for direct or indirect management of sensing, drilling, injecting, extracting, etc., with respect to the geologic environment 150. In turn, further information about the geologic environment 150 may becomePATENT Atorney Docket No.: IS24.1190-US-NP available as feedback 160 (e.g., optionally as input to one or more of the management components 110).

[0021] In the example of Figure 1, the management components 110 include a seismic data component 112, an additional information component 114 (e.g., well / logging data), a processing component 116, a simulation component 120, an attribute component 130, an analysis / visualization component 142 and a workflow component 144. In operation, seismic data and other information provided per the components 112 and 114 may be input to the simulation component 120.

[0022] In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 may include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114). An entity may be characterized by one or more properties (e.g., a geometrical pillar grid entity of an earth model may be characterized by a porosity property). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.

[0023] In an example embodiment, the simulation component 120 may operate in conjunction with a software framework such as an object -based framework. In such a framework, entities may include entities based on pre-defined classes to facilitate modeling and simulation. A commercially available example of an object-based framework is the MICROSOFT18" .NET® framework (Redmond, Washington), which provides a set of extensible object classes. In the .NET® framework, an object class encapsulates a module of reusable code and associated data structures. Object classes may be used to instantiate object instances for use in by a program, script, etc. For example, borehole classes may define objects for representing boreholes based on well data.

[0024] In the example of Figure 1, the simulation component 120 may process information to conform to one or more attributes specified by the attribute component 130, which may include a library of attributes. Such processing may occur prior to input to the simulation component 120 (e.g., consider the processing component 116). As an example, the simulation component 120 may perform operations on input information based on one or more attributes specified by the attribute component 130. In an example embodiment, the simulation component 120 mayPATENT Atorney Docket No.: IS24.1190-US-NP construct one or more models of the geologic environment 150, which may be relied on to simulate behavior of the geologic environment 150 (e.g., responsive to one or more acts, whether natural or artificial). In the example of Figure 1, the analysis / visualization component 142 may allow for interaction with a model or model-based results (e.g., simulation results, etc.). As an example, output from the simulation component 120 may be input to one or more other workflows, as indicated by a workflow component 144.

[0025] As an example, the simulation component 120 may include one or more features of a simulator such as the ECLIPSE™ reservoir simulator (SLB, Houston Texas), the INTERSECT™ reservoir simulator (SLB, Houston Texas), etc. As an example, a simulation component, a simulator, etc. may include features to implement one or more meshless techniques (e.g., to solve one or more equations, etc.). As an example, a reservoir or reservoirs may be simulated with respect to one or more enhanced recovery techniques (e.g., consider a thermal process such as SAGD, etc ).

[0026] In an example embodiment, the management components 110 may include features of a commercially available framework such as the PETREL® seismic to simulation software framework (SLB, Houston, Texas). The PETREL® framework provides components that allow for optimization of exploration and development operations. The PETREL® framework includes seismic to simulation software components that can output information for use in increasing reservoir performance, for example, by improving asset team productivity. Through use of such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) can develop collaborative workflows and integrate operations to streamline processes. Such a framework may be considered an application and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc.).

[0027] In an example embodiment, various aspects of the management components 110 may include add-ons or plug-ins that operate according to specifications of a framework environment. For example, a commercially available framework environment marketed as the OCEAN® framework environment (SLB, Houston, Texas) allows for integration of add-ons (or plug-ins) into a PETREL® framework workflow. The OCEAN® framework environment leverages .NET® tools (Microsoft Corporation, Redmond, Washington) and offers stable, user-friendly interfaces for efficient development. In an example embodiment, various components may be implementedPATENT Atorney Docket No.: IS24.1190-US-NP as add-ons (or plug-ins) that conform to and operate according to specifications of a framework environment (e.g., according to application programming interface (API) specifications, etc.).

[0028] Figure 1 also shows an example of a framework 170 that includes a model simulation layer 180 along with a framework services layer 190, a framework core layer 195 and a modules layer 175. The framework 170 may include the commercially available OCEAN® framework where the model simulation layer 180 is the commercially available PETREL® model-centric software package that hosts OCEAN® framework applications. In an example embodiment, the PETREL® software may be considered a data-driven application. The PETREL® software can include a framework for model building and visualization.

[0029] As an example, a framework may include features for implementing one or more mesh generation techniques. For example, a framework may include an input component for receipt of information from interpretation of seismic data, one or more attributes based at least in part on seismic data, log data, image data, etc. Such a framework may include a mesh generation component that processes input information, optionally in conjunction with other information, to generate a mesh.

[0030] In the example of Figure 1, the model simulation layer 180 may provide domain objects 182, act as a data source 184, provide for rendering 186 and provide for various user interfaces 188. Rendering 186 may provide a graphical environment in which applications can display their data while the user interfaces 188 may provide a common look and feel for application user interface components.

[0031] As an example, the domain objects 182 may include entity objects, property objects and optionally other objects. Entity objects may be used to geometrically represent wells, surfaces, bodies, reservoirs, etc., while property objects may be used to provide property values as well as data versions and display parameters. For example, an entity object may represent a well where a property object provides log information as well as version information and display information (e.g., to display the well as part of a model).

[0032] In the example of Figure 1, data may be stored in one or more data sources (or data stores, generally physical data storage devices), which may be at the same or different physical sites and accessible via one or more networks. The model simulation layer 180 may be configured to model projects. As such, a particular project may be stored where stored project information may include inputs, models, results and cases. Thus, upon completion of a modeling session, aPATENT Atorney Docket No.: IS24.1190-US-NP user may store a project. At a later time, the project may be accessed and restored using the model simulation layer 180, which can recreate instances of the relevant domain objects.

[0033] In the example of Figure 1, the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and one or more other features such as the fault 153-1, the geobody 153-2, etc. As an example, the geologic environment 150 may be outfitted with any of a variety of sensors, detectors, actuators, etc. For example, equipment 152 may include communication circuitry to receive and to transmit information with respect to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment to acquire information, to assist with resource recovery, etc. Other equipment 156 may be located remote from a well site and include sensing, detecting, emitting or other circuitry. Such equipment may include storage and communication circuitry to store and to communicate data, instructions, etc. As an example, one or more satellites may be provided for purposes of communications, data acquisition, etc. For example, Figure 1 shows a satellite in communication with the network 155 that may be configured for communications, noting that the satellite may additionally or instead include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

[0034] Figure 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation that may include natural fractures, artificial fractures (e g., hydraulic fractures) or a combination of natural and artificial fractures. As an example, a well may be drilled for a reservoir that is laterally extensive. In such an example, lateral variations in properties, stresses, etc. may exist where an assessment of such variations may assist with planning, operations, etc. to develop a laterally extensive reservoir (e.g., via fracturing, injecting, extracting, etc.). As an example, the equipment 157 and / or 158 may include components, a system, systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0035] As mentioned, the system 100 may be used to perform one or more workflows. A workflow may be a process that includes a number of worksteps. A workstep may operate on data, for example, to create new data, to update existing data, etc. As an example, a workflow may operate on one or more inputs and create one or more results, for example, based on one or more algorithms. As an example, a system may include a workflow editor for creation, editing,PATENT Atorney Docket No.: IS24.1190-US-NP executing, etc. of a workflow. In such an example, the workflow editor may provide for selection of one or more pre-defined worksteps, one or more customized worksteps, etc. As an example, a workflow may be a workflow implementable in the PETREL® software, for example, that operates on seismic data, seismic attribute(s), etc. As an example, a workflow may be a process implementable in the OCEAN® framework. As an example, a workflow may include one or more worksteps that access a module such as a plug-in (e.g., external executable code, etc.).

[0036] A network architecture for drilling operations typically involves a multi-layered setup designed to handle the complexities of rig environments, as shown in Figure 1. The infrastructure may be segmented into distinct network zones, such as an information technology (IT) network, an operational technology (OT) network, and a rig network, to ensure security and manageability.

[0037] The IT network may include centralized support and monitoring systems, such as the Service Provider Central Support Network, which interacts with the rig networks via secure communication channels. The OT network may operate within a more restrictive environment, managing essential control systems and acquisition networks, including surface and downhole data acquisition devices. Each network segment may be further isolated using firewalls and hypervisor technologies, enabling network segmentation and perimeter security.

[0038] The rig network connects critical edge devices, such as drilling control units, acquisition systems, and other wellsite equipment which perform various automation and data processing tasks. These edge devices often operate with limited bandwidth, making it challenging to transmit large amounts of data in real time. Therefore, a robust strategy for monitoring and data collection may be chosen to ensure efficient operation without overwhelming the network.Method for Optimizing Reservoir Management Using K-Means Clustering Particle Swarm Optimization

[0039] The present disclosure provides a workflow (e.g. method) for optimization in multivariable space. In certain embodiments, the workflow may increase the divergence during the optimization, potentially improving the domain search. Also, the workflow may be capable of finding multiple minima without increasing the number of objective function calls. In certain embodiments, divergence may be understood to be the calling of an objective function, which may be a time-consuming process. Resource management may be improved by avoiding calling the objective function in regions that are well explored. In certain embodiments, finding multiplePATENT Atorney Docket No.: IS24.1190-US-NP minima may make it easier for the user to decide among the available solutions the solution has the most physical parameters.

[0040] According to certain embodiments, a particle swarm optimization (PSO) workflow may be described by first initializing particles, and then, when counter z is less than a maximum iteration number, an objective function may be computed, particle positions may be updated, and a convergence may be checked. The objective function may include one or more of a difference between measured flow rate and pressure and modeled flow rate and pressure, net present value, or oil and / or gas production rate.Step 1: Initialize particles

[0041] According to certain embodiments, during particle initialization all particles may start the problem with a given position and velocity. The particle position may be initialized using the Latin Hypercube algorithm, while the velocity may be assigned randomly using a uniform distribution to cover a maximum of 5% of the domain in the next iteration in any direction.Step 2a: Compute objective function

[0042] According to certain embodiments, the objective function at each particle position may be evaluated. The objective function algorithm may be parallelized where the objective function for each particle may be evaluated on a different CPU core or computing cluster node.Step 2b: Update particle positions

[0043] According to certain embodiments, implementing K-Means Cluster Particle Swarm Optimization (KC-PSO) of the current method may include updating the best positions of the particle, updating the particle clusters, splashing particles, and updating velocities and positions of the particles.Step 2b(i): Update best positions

[0044] According to certain embodiments, for a minimization problem, a particle’s best position (PBest) may be the location where the particle has the lowest objective function during the particle’s whole life (or life cycle). For maximization problems, the best position is treated as the maximum objective function. In certain embodiments, every time a particle moves to a better position, the PBest may be updated within the particle history, where a better position corresponds to a lower objective function. The best of the two particles may be considered the particle having the best history, where the best history includes having the lowest or highest (as appropriate) objective function value over an entire history of the particle.PATENT Atorney Docket No.: IS24.1190-US-NPStep 2b(ii) : Update clusters

[0045] Figure 2 shows a clustering step in a KC-PSO algorithm, according to an embodiment. As a product of this routine, an optimum number of clusters and a location of each one of the clusters may be determined. The optimum number of clusters may be calculated by using the Silhouette Score (SC), where the optimum number of clusters is the one that maximizes the following function given by equation (1):SC = maxs( / c) (1) wherein s(fc) is the average value of the silhouette function, s(i), using k clusters, wherein s(i) may be defined by equation (2):wherein a(i~) is the mean distance between particle i and all other particles in the same cluster, and b(i) the smallest mean distance between particle i and all particles of any other cluster.

[0046] According to certain embodiments, after running the silhouette score algorithm, the number and position of each cluster, represented by the grey circles in Figure 2, may be obtained. In certain embodiments, the best particle may be determined inside each cluster, represented by the gray dots in Figure 2, by evaluating the cluster best position (Cbest), defined as the best PBest within the cluster.Step 2b(iii): Splash Particles

[0047] According to certain embodiments, the interaction of all particles may be evaluated two by two. If two particles reach a proximity threshold, as shown in Figure 3, the algorithm may merge the position and velocity of both particles to the best of the two particles, and then restart the worst of the two particles in an aleatory position inside the domain. The splashing step may be used to increase the divergence of the minimum search, minimizing the objective function calls. The clustering step, otherwise, may be used to help the workflow in finding multiple minima without restarting the workflow.Step 2b(iv): Update velocities and positions

[0048] According to certain embodiments, after computing the cluster positions and splashing the close particles, the velocity for all particles may be updated within the domain as seen in FigurePATENT Atorney Docket No.: IS24.1190-US-NP4. The particle velocity may be an average of the inertia, personal, and social terms that may be calculated by equation (3):wherein winertiahwpersoncdand wsociaiare the weights of each term, and X” is the position of particle i. For the KC-PSO variation, Gbest = Cbest for each cluster. To avoid local minima and increase domain investigation, some randomness may be included during the velocity calculation. Each weight may be defined by a product between a deterministic term c and a random variable r comprised between 0 and 1, (r G (0,1]). Each term c may be constant during the whole optimization, where default values may be used, or may be dynamically determined. The defaults may be determined by studying the behaviour of different optimization cases for reservoir engineering problems. The defaults may be designed in such a way that the personal and inertial effects decrease during the optimization and the social increases, achieving the global optimum point more rapidly. Once the new velocity for each particle has been determined, the position may be calculated by equation 4: xn+l= xn+ vn+l (4)

[0049] The workflow as described above may be used for reservoir management, determining a well location, history matching, and / or any other application where a function must be optimized. According to certain embodiments, the workflow of the current method may be used to optimize a non-linear function having multiple minima in a domain where little or no information is previously known.Exemplary Method

[0050] Figure 5 illustrates a flowchart of a method 500 for optimizing reservoir management. An illustrative order of the method 500 is provided below; however, one or more portions of the method 500 may be performed in a different order, simultaneously, repeated, or omitted. At least a portion of the method 500 may be performed using a computing system.

[0051] In certain embodiments, the method 500 may include receiving data from a plurality of sources disposed at the wellsite, as at 502. The data from the sources may include data collected from oil sites and used to calibrate a reservoir simulation such as pressure gauges, flow rate monitors, water, oil, and gas separators, temperature monitors, and the like. The data may alsoPATENT Atorney Docket No.: IS24.1190-US-NP include laboratory data. The laboratory data can include measurements and analysis performed on rock samples. The rock samples may be core samples taken from a well. In one embodiment, the data includes special core analysis (SCAL) data that may include properties such as porosity, permeability, grain density, fluid saturation, capillary pressure, relative permeability, electrical properties, wettability, or other properties.

[0052] In certain embodiments, the laboratory data includes pressure-volume-temperature (PVT) data representing properties of reservoir fluids (such as oil gas, and water) that are obtained through laboratory analysis and / or modeling. The PVT data may include information about fluid composition, phase behavior, density, viscosity, compressibility, formation volume factors, solution gas-oil ration, and other measurements.

[0053] According to certain embodiments, the method 500 may include generating a reservoir model from the received data, as at 504. In certain embodiments, the reservoir model may be configured to reproduce historical data of the reservoir. Generation of the reservoir model may include initializing a plurality of particles. As used herein, “initializing the particles” refers to creating a set of different initial cases or reservoir models, where each model may have a different set of variable values that may be optimized by the method. Each of the particles may include an initial position in a parameter space and an initial velocity in the parameter space. Generating the reservoir model may also include evaluating an objective function at a position for each of the particles. Generating the reservoir model may further include updating the positions of the particles. Parameters in the parameter space may include a permeability, a porosity, fluid properties, and a relative permeability input relative to the reservoir mode.

[0054] In certain embodiments, updating the previous position may include updating a best position of the particles, updating clusters, merging at least two particles when a proximity threshold is reached, and updating the initial position and initial velocity of each of the particles. In certain embodiments, updating the best position of the particles may include defining a location where each particle had the lowest function during the particle’s whole life. Updating the clusters of the particles may include determining an optimum number of clusters, determining a location of each of the clusters, and then identifying a best cluster position based by the best position of the particles within each cluster. The number of cluster may be determined by minimizing the silhouette score function. The location of each cluster may be determined by the K-Means algorithm. In certain embodiments, updating the previous position and previous velocity of eachPATENT Atorney Docket No.: IS24.1190-US-NP of the particles may be based on the identified best cluster position. The merging of the at least two particles when a proximity threshold is reached may include merging the two particles to a position and velocity corresponding to the best of the two particles and then restarting the remaining particle of the two particles in an aleatory position inside a domain. In an embodiment, the best of two particles may be determined by choosing the particle with the best personal value (Pbest).

[0055] According to certain embodiments, the method 500 may include displaying the generated reservoir model on a display, as at 506.

[0056] According to certain embodiments, the method 500 may include performing a wellsite action based on the generated reservoir model, as at 508. Performing the wellsite action may include generating or transmitting a signal that recommends, instructs, or causes a physical action to occur. The physical action may include selecting where to drill a wellbore in the subsurface formation, drilling the wellbore, varying a trajectory of the wellbore, varying a weight or torque on a drill bit that is drilling the wellbore, varying a rate or concentration of a fluid being pumped into the wellbore, or a combination thereof. Another physical action that may be an outcome from a reservoir optimization is to open or restrict well flow rates to maximize the operational profit. Better choosing the appropriate water and gas injection flow rates may also be determined after an optimization, where the pumps rates may be dynamically changed to minimize water and gas production and maximize oil flow rates. The choice and volume of special enhanced oil recovery methods (EOR) may be designed by optimization, where special materials such as polymers, surfactants, alkalis, foams, nanofluids, colloids and the like may be injected in the reservoir to maximize the production.Exemplary Computing System

[0057] In some embodiments, the methods of the present disclosure may be executed by a computing system. Figure 6 illustrates an example of such a computing system 600, in accordance with some embodiments. The computing system 600 may include a computer or computer system 601A, which may be an individual computer system 601A or an arrangement of distributed computer systems. The computer system 601A includes one or more analysis modules 602 that are configured to perform various tasks according to some embodiments, such as one or more methods disclosed herein. To perform these various tasks, the analysis module 602 executesPATENT Atorney Docket No.: IS24.1190-US-NP independently, or in coordination with, one or more processors 604, which is (or are) connected to one or more storage media 606. The processor(s) 604 is (or are) also connected to a network interface 607 to allow the computer system 601 A to communicate over a data network 609 with one or more additional computer systems and / or computing systems, such as 60 IB, 601C, and / or 60 ID (note that computer systems 60 IB, 601C and / or 60 ID may or may not share the same architecture as computer system 601 A, and may be located in different physical locations, e.g., computer systems 601 A and 601B may be located in a processing facility, while in communication with one or more computer systems such as 601 C and / or 60 ID that are located in one or more data centers, and / or located in varying countries on different continents).

[0058] A processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0059] The storage media 606 may be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of Figure 6 storage media 606 is depicted as within computer system 601 A, in some embodiments, storage media 606 may be distributed within and / or across multiple internal and / or external enclosures of computing system 601 A and / or additional computing systems. Storage media 606 may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories, magnetic disks such as fixed, floppy and removable disks, other magnetic media including tape, optical media such as compact disks (CDs) or digital video disks (DVDs), BLURAY® disks, or other types of optical storage, or other types of storage devices. Note that the instructions discussed above may be provided on one computer-readable or machine-readable storage medium, or may be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes. Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture). An article or article of manufacture may refer to any manufactured single component or multiple components. The storage medium or media may be located either in the machine running the machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution.PATENT Atorney Docket No.: IS24.1190-US-NP

[0060] It should be appreciated that computing system 600 is merely one example of a computing system, and that computing system 600 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of Figure 6, and / or computing system 600 may have a different configuration or arrangement of the components depicted in Figure 6. The various components shown in Figure 6 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and / or application specific integrated circuits.

[0061] Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in information processing apparatus such as general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or other appropriate devices. These modules, combinations of these modules, and / or their combination with general hardware are included within the scope of the present disclosure.

[0062] Computational interpretations, models, and / or other interpretation aids may be refined in an iterative fashion; this concept is applicable to the methods discussed herein. This may include use of feedback loops executed on an algorithmic basis, such as at a computing device (e.g., computing system 600, Figure 6), and / or through manual control by a user who may make determinations regarding whether a given step, action, template, model, or set of curves has become sufficiently accurate for the evaluation of the risk index.

[0063] The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or limiting to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. Moreover, the order in which the elements of the methods described herein are illustrated and described may be re-arranged, and / or two or more elements may occur simultaneously. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosed embodiments and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

PATENT Atorney Docket No.: IS24.1190-US-NPCLAIMSWhat is claimed is:

1. A method for performing reservoir management at a wellsite, the method comprising: receiving data from a plurality of sources; generating a reservoir model from the received data, wherein generating the reservoir model comprises: initializing a plurality of particles based upon the received data; evaluating an objective function at a position for each of the particles; and updating the position for each of the particles; and displaying the generated reservoir model on a display.

2. The method of claim 1, wherein the plurality of sources comprise at least one of seismic data, laboratory data, rock data, or special core analysis (SCAL) data.

3. The method of claim 2, wherein: the laboratory data comprises pressure-volume-temperature (PVT) fluid data, and / or the rock data comprises at least one of porosity or permeability.

4. The method of claim 1, wherein the reservoir model is configured to reproduce historical data of a reservoir.

5. The method of claim 1, wherein each of the particles comprises an initial position in a parameter space and an initial velocity in the parameter space.

6. The method of claim 5, wherein the initial position of each of the particles is determined using a Latin Hypercube algorithm.

7. The method of claim 5, wherein the initial velocity of each of the particles is randomly assigned using a uniform distribution to cover a maximum of 5% of a domain in a next iteration in any direction.PATENT Atorney Docket No.: IS24.1190-US-NP8. The method of claim 5, wherein parameters in the parameter space include one or more of a permeability, a porosity, fluid properties, or a relative permeability input relative to the reservoir model.

9. The method of claim 1, wherein an objective function evaluating algorithm is parallelized such that performance of evaluating the objective function is distributed over a plurality of CPU cores or computing cluster nodes.

10. The method of claim 1, wherein the objective function comprises at least one of a difference between measured flow rate and pressure and modeled flow rate and pressure, net present value, or oil and / or gas production rate.

11. The method of claim 1, wherein updating the position comprises updating a best position of the particles.

12. The method of claim 11, wherein updating the best position of the particles comprises defining a location where the objective function for each particle is lowest during a life cycle of the particle.

13. The method of claim 1, wherein updating the position comprises updating clusters of the particles by: determining an optimum number of the clusters; determining a location of each of the clusters; and identifying a best cluster position based upon the best position of the particles within each cluster.

14. The method of claim 13, wherein updating the position comprises merging at least two of the particles when a proximity threshold is reached by: merging the two particles to a position and resultant velocity corresponding to the best of the two particles; andPATENT Atorney Docket No.: IS24.1190-US-NP restarting a remaining particle of the two particles in an aleatory position inside a domain.

15. The method of claim 14, wherein: the best of the two particles comprises the particle having a best history, the best history comprises having a lowest or highest objective function value over an entire history of the particle, and determining the optimum number of clusters comprises maximizing a Silhouette Score.

16. The method of claim 14, wherein: updating the position and velocity of each of the particles is based on the identified best cluster position, and a current velocity of each of the particles comprises a weighted sum of at least one of a velocity, a personal velocity, and a social velocity.

17. A computing system, comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising: receiving data from a plurality of sources disposed at a wellsite; generating a reservoir model from the received data, wherein generating the reservoir model comprises: initializing a plurality of particles based upon the received data; and iteratively performing at least one time: evaluating an objective function at a position for each of the particles; and updating the position of the particles based upon the objective function, including; updating a best position of the particles; updating clusters of the particles;PATENT Atorney Docket No.: IS24.1190-US-NP merging at least two particles when a proximity threshold is met; and updating a previous position and a previous velocity of each of the particles; and displaying the generated reservoir model on a display.

18. The computing system of claim 17, wherein the operations further comprise: performing a wellsite action based on the generated reservoir model.

19. The computing system of claim 18, wherein the wellsite action comprises a physical action, the physical action comprising one or more of: selecting where to drill a wellbore in a subsurface formation; drilling the wellbore; varying a trajectory of the wellbore; varying a weight or torque on a drill bit that is drilling the wellbore; varying a rate or concentration of a fluid being pumped into the wellbore; specifying an order of drilling for multiple wells; optimizing well control by opening and / or closing wells to minimize water production and / or to optimize oil and / or gas flow rate; or a combination thereof.

20. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising: receiving data from a plurality of sources, wherein: the sources comprise at least one of seismic data, laboratory data, rock data, or special core analysis (SCAL) data, the laboratory data comprises pressure-volume-temperature (PVT) fluid data, and the rock data comprises at least one of porosity or permeability; generating a reservoir model from the received data, wherein: the reservoir model is configured to reproduce historical data of the reservoir, and generating the reservoir model comprises:PATENT Atorney Docket No.: IS24.1190-US-NP initializing a plurality of particles, wherein: each of the particles comprises an initial position in a parameter space and an initial velocity in the parameter space, the initial position of each of the particles is determined using a Latin Hypercube algorithm, the initial velocity of each of the particles is randomly assigned using a uniform distribution to cover a maximum of 5% of a domain in a next iteration in any direction, the parameters in the parameter space include one or more of permeability, porosity, fluid properties, or relative permeability input relative to the reservoir model; and iteratively performing at least one time: evaluating an objective function at a position for each of the particles, wherein: the algorithm is parallelized such that performance of evaluating the objective function is distributed over a plurality of CPU cores or computing cluster nodes, and the objective function comprises at least one of a difference between measured flow rate and pressure and modeled flow rate and pressure, net present value, or oil and / or gas production rate; and updating the positions of the particles, wherein updating the positions comprises updating a best position of the particles, updating clusters of the particles, merging at least two particles when a proximity threshold is met, and updating a previous position and a previous velocity of each of the particles, wherein: updating the best position of the particles comprises defining a location where the objective function for each particle is lowest during a life cycle of the particle, updating clusters of the particles comprises determining an optimum number of clusters, determining a location of each of thePATENT Atorney Docket No.: IS24.1190-US-NP clusters, and identifying a best cluster position based upon the best position of the particles within each cluster, wherein: determining the optimum number of clusters comprises maximizing a Silhouette Score, and updating the clusters further comprises determining a best particle inside each cluster by evaluating a PBest within each cluster, merging at least two particles when the proximity threshold is reached comprises merging the two particles to a position and resultant velocity corresponding to the best of the two particles and restarting a remaining particle of the two particles in an aleatory position inside a domain, wherein the best of the two particles comprises the particle having a best history, and wherein the best history comprises having a lowest or highest objective function value over an entire history of the particle, and updating the position and velocity of each of the particles is based on the identified best cluster position, wherein a current velocity of each of the particles comprises a weighted sum of at least one of a velocity, a personal velocity, and a social velocity; displaying the generated reservoir model on a display; and performing a wellsite action based on the generated reservoir model, wherein: performing the wellsite action comprises generating or transmitting a signal that instructs or causes an action to occur, the action comprises a physical action, and the physical action comprises selecting where to drill a wellbore in a subsurface formation, drilling the wellbore, varying a trajectory of the wellbore, varying a weight or torque on a drill bit that is drilling the wellbore, varying a rate or concentration of a fluid being pumped into the wellbore, specifying an order of drilling for multiple wells, optimizing well control by opening and closing wells to minimize water production and / or to optimize oil and / or gas flow rate, or a combination thereof.

Images