The present invention generally relates to a method of analyzing an oil and gas production project and, more particularly, relates to an oil and gas management program for designing a production project and analyzing equipment requirements, costs, and other information associated with the project.
To produce natural gas, companies enter land leases to gain access to mineral rights. Different crews are then dispatched to construct drill pads, drill horizontal wells into rock, pressurize the wells by plugging them to perform hydraulic fracturing and finally drill out the plugs to extract natural gas, oil, and natural gas liquids. A typical production field may require several years of drilling to develop a half dozen wells that are expected to be in production for 10 to 15 years.
Unconventional shale wells are drilled using 21st-century vertical or horizontal technologies. Vertical wells are sometimes first drilled in an area to obtain information valuable for planning the drilling of more costly and technically demanding horizontal wells.)
Prior to drilling an unconventional shale well, operators must obtain several permits and adhere to a number of local, state and federal laws and regulations from constructing the well pad, building the access drive and constructing and operating the well itself.
The drilling process focuses first on reaching—and protecting—water-bearing zones beneath the ground. Drilling is completed using a small amount of lubricating agents. The entire length of the well, from the surface to the groundwater strata, is cased and cemented tightly with a series of steel pipes and concrete to form a barrier between the wellbore and the earth. As drilling continues to push deeper into the earth, a series of long drilling pipes follow it to establish the well.
After drilling vertically to the depth that reaches slightly above the targeted unconventional shale formation, the drill bit can then turn to push its way horizontally into the unconventional shale formation, sometimes as much as 10,000 to 15,000 feet into the formation. This allows for the extraction of larger quantities of natural gas from a single wellhead. Unconventional shale wells generally take between 15 to 30 days to drill, depending on the timetable of the individual operator.
Historically, the production planning activities have been manually intensive, rely heavily on experiential knowledge, and focus on a short-term time horizon of one year or less. In order to determine the final schedule, a planner models various scenarios in a spreadsheet to ensure operational constraints are respected. At the end of the planning process, there is no way to determine if the final schedule is optimal because of a large number of combinatorial factors are not solvable by a human with a spreadsheet.
The claimed invention is a scheduling system that optimizes a company's schedule planning process to maximize production from their natural gas leases and wells. The invention uses an algorithm that efficiently solves for high-value scenarios over a long-term time horizon and allows for the flexibility required.
The present invention provides a novel method and system for improving oil and gas drilling scheduling. A plurality of project projections are performed by accessing data elements, each associated with criteria.
In one example, the criteria used to project expected gas production includes 1) location of a gas well, 2) expected length of a gas well, 4) a location of a pad, 5) an identifier of a basin to which a pad belongs, 6) an identifier of a lease for any timing constraints, 7) types of jobs at a pad, 8) a number of days allocated to perform a job, 9) a number of days each pad is in a recovery state, or 10) any combination thereof.
Next, each of the criteria is used to project expected gas production from gas wells, and the criteria include a number of crews to perform jobs and a total number of jobs. The criteria are converted into a uniform data format. Next, a total number of simulations (M) are executed in parallel up to the total number of jobs or until a time period expires. The total number of simulations, the time period, or both are settable by a user.
The simulations include evaluating each of the jobs to be performed and which crews are available to perform the jobs and executing an algorithm to produce results, wherein the results include a schedule of crews and jobs and a production timeline. The results are ranked with the highest gas production. The results are sent to a display. The algorithm may be selectable by a user. The algorithm is an epsilon-greedy algorithm or a random algorithm.
In one example, the results from each step using the epsilon-greedy algorithm is given by:
where p is a pad in a set P of all pads being scored, wn is a user-specified weight of each of the plurality of criteria N, and xn is a computed value of each of i) maximum expected production from each pad, ii) the work already completed on the pad if any, iii) an estimated likelihood of a frack hit, and iv) time remaining before the pad must be developed. The wn is assigned by a user using a graphical user interface.
The results sent to the display may include 1) a table of jobs, with a crew performing the job and start and end times for each job, 2) an expected cash flow time-series, 3) an expected production time-series, 4) events table that specifies a date of initial production of each well and any shut-ins that occur in that schedule with their duration and production impact, 6) constraint violations, 7) water usage, 8) net present value (NPV) of gas production, 8) internal rate of return (IRR) of gas production or 10) any combination thereof.
The results may include a Gantt chart with a vertical axis denoting a pad, and a horizontal axis including jobs, the crews performing the jobs and the start and end job times at each pad denoted in various colors.
The accompanying figures where like reference numerals refer to identical or functionally similar elements throughout the separate views, and which together with the detailed description below are incorporated in and form part of the specification, serve to further illustrate various embodiments and to explain various principles and advantages all in accordance with the present disclosure, in which:
As required, detailed embodiments are disclosed herein; however, it is to be understood that the disclosed embodiments are merely examples and that the systems and methods described below are embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the disclosed subject matter in virtually any appropriately detailed structure and function. Further, the terms and phrases used herein are not intended to be limiting but rather to provide an understandable description.
Generally, the terms “a” or “an”, as used herein, are defined as one or more than one. The term plurality, as used herein, is defined as two or more than two.
The term “adapted to” describes the hardware, software, or a combination of hardware and software that is capable of, able to accommodate, to make, or that is suitable to carry out a given function.
The term “another”, as used herein, is defined as at least a second or more.
The term “completion schedule” as applied to natural gas and oil production means all steps necessary in site selection, site construction, site drilling, site hydraulic fracturing and gas/oil production over the lifetime of the well.
The term “configured to” describes hardware, software or a combination of hardware and software that is adapted to, set up, arranged, built, composed, constructed, designed, or that has any combination of these characteristics to carry out a given function.
The term “coupled,” as used herein, is defined as “connected,” although not necessarily directly, and not necessarily mechanically.
The term “crew” means a group of people who work on a portion of a completion schedule together for a period of time.
The terms “including” and “having,” as used herein, are defined as comprising (i.e., open language).
The term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless specified otherwise or clear from context, “X employs A or B” is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then “X employs A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form.
The term “simultaneous” means computations are carried out at the same time, which for larger data sets with various constraints is not possible to be carried out completed by a group of humans and must be performed by a computer. For example, one human could not compute one simulation with all the constraints for ten crews across fifty ten jobs. It is infeasible for a human to calculate one simulation loop with one constraint, let alone perform it in parallel to a sort of global optimum.
The term “uniform data format” means data in a given format, whether date format, time format, currency format, scientific format, text format, or fractional format, so that all values of data are presented in a single consistent format for a given category or criteria.
It should be understood that the steps of the methods set forth herein are not necessarily required to be performed in the order described, and the order of the steps of such methods should be understood to be merely exemplary. Likewise, additional steps may be included in such methods, and certain steps may be omitted or combined in methods consistent with various embodiments of the present device.
Although the elements in the following method claims, if any, are recited in a particular sequence with corresponding labeling unless the claim recitations otherwise imply a particular sequence for implementing some or all of those elements, those elements are not necessarily intended to be limited to being implemented in that particular sequence.
The claimed invention is a scheduling system that optimizes a company's schedule planning process to maximize production from their natural gas leases and wells. The invention uses an algorithm that efficiently solves for high-value scenarios over a long-term time horizon and allows for the flexibility required.
Drilling rigs 102, 104, 106, such as those shown in
Conventional oil or gas comes from formations that are “normal” or straightforward to extract products from. Extracting fossil fuels from these geological formations can be done with standard methods that can be used to economically remove the fuel from the deposit. Conventional resources tend to be easier and less expensive to produce simply because they require no specialized technologies and can utilize common methods. Because of this simplicity and relative cheapness, conventional oil and gas are generally some of the first targets of industry activity.
Moving a drilling rig 102 between two well sites previously involved disassembling the rig and reassembling it at the new location (“rigging down” and “rigging up”) even if the new location was only a few yards away. Today, a drilling pad may have five to ten wells, which are horizontally drilled in different directions, spaced fairly close together at the surface. Once one well is drilled, the fully constructed rig can be lifted and moved a few yards over to the next well location using hydraulic walking or skidding systems.
In
In contrast to this, unconventional oil or gas resources are much more difficult to extract. Some of these resources are trapped in reservoirs with poor permeability and porosity, meaning that it is extremely difficult or impossible for oil or natural gas to flow through the pores and into a standard well. To be able to produce from these difficult reservoirs, specialized techniques and tools are used. For example, the extraction of shale oil, tight gas, and shale gas must include a hydraulic fracturing step in order to create cracks for the oil or gas to flow through. In the oil sands, in situ deposits must utilize steam-assisted gravity drainage to be able to extract thick bitumen from underground deposits. All of these methods are more costly than those used to produce fossil fuels from a traditional reservoir, but this stimulation allows for the production of oil and gas from resources that were previously not economical to extract from. These resources become reserves when they can be utilized economically.
This starting point and ending point of each well location information is used made available to create this overlay plot for all the possibilities for that geographic location. The simulation environment or scheduling system models the impact of the sequencing of oil and natural gas well production (“simultaneous operations”), which is of vital importance to the planning process. The oil and natural gas well information is important for this sequencing because there are constraints based on the location of well. An example of a constraint is that two given wells may not have specific jobs performed on them simultaneously if they are within a given geographic distance from each other. An example of this is that a well cannot be drilled if a nearby well is being completed/hydraulically fractured (fracked)
The present invention may employ a reinforced learning approach to optimize drilling completion schedules. However, after further investigation, the reinforced learning approach was paused, and heuristic techniques were developed, including a random and epsilon-greedy algorithm approach.
The algorithm leverages an Epsilon Greedy Agent with inputs to model the financial, contractual, and operational constraints of the planning process. Financial constraints ensure that computed schedules do not exceed the budget for labor and equipment. Contractual and operational constraints guarantee adherence to land lease terms, safety considerations, and factors in the availability of crews and materials needed for production.
The simulation environment or scheduling system also models the impact of drilling and completion on wells that are nearby already producing natural gas wells (“shut in process”), which is of vital importance to the planning process. Extraction activities in each oil and natural gas well can significantly impact the production of nearby wells—similar to wind turbine waking effects, in which resource capture at one turbine can affect those of nearby turbines.
After the environment is configured, an Epsilon Greedy Agent iterates through possible choices of crews and available jobs over the forecast horizon and ranks potential scheduling decisions by value.
Most of the time, the Epsilon Greedy Agent selects the highest value decision. However, there is a small chance that the Epsilon Greedy Agent will make a lower value decision that could unlock additional hidden value in subsequent time steps. This type of combined random & greedy decision-making is a simple technique that allows the Epsilon Greedy Agent to arrive at high-value drilling schedules over many iterations. An advantage of using the Epsilon Greedy Agent versus a more traditional constrained optimization framework is that Epsilon Greedy Agent quickly accommodates rapidly changing (and new) constraints and objective functions.
The scheduling system includes a user interface (UI) that streamlines the planning process. Users can enter the oil and natural gas well data, like location and production potential, then kick off simulations. Simulations are typically complete in a matter of minutes and solve for schedules up to five years out.
The UI displays output in the form of expected production (Net Dry Gas), net present value (NPV), cash flow forecasts, and crew schedules. The user can evaluate each of the scenarios to select a plan, taking into consideration evolving business preferences. The UI is intuitive and allows for fast parsing through up to a thousand scenarios to find a schedule that meets customer preferences for crew utilization, production profile, and simultaneous operations.
Companies often have some uncertainty in the metric to maximize. This stems from an unclear understanding of all the components applied to estimate the NPV of a project schedule. On the other hand, total gas production appears to be a preferred metric but doesn't answer significant questions surrounding expected future gas revenues and the time value of money, particularly since the production curves typically go out over 50 years. To address these questions and uncertainty, the scheduling system of the claimed invention applies a heuristic algorithm that maximizes production by generating multiple schedules with slight variations and allowing the user to select the best performing schedule either based on total gas production or NPV since they are positively correlated.
Inputs to the scheduling system of the claimed invention include:
Outputs produced by the scheduling system of the claimed invention include:
Physical Constraints
Business Requirements
The scheduling system is a custom Open AI Gym environment and implements the required step and reset public methods. When the scheduling system is initialized, it requires the inputs listed above, e.g., a list of crews, pads, basins, leases, water basins, and the episode start time. Also, other inputs described above—The crews, pads, basins, leases, and water basins are distinct classes in the code. They require other data (such as wells, jobs, capital expenditures (CAPEX), etc.) to initialize them.
After initialization, the step method can be called with an action that conforms to the scheduling systems' action space. The scheduling system environment action space is,
When a “step” is called with an appropriate action, the scheduling system will check the validity of the action against all the physical and business requirements. If the action is valid, each crew is assigned to the first available job at the specified pad (all jobs are sequential). The scheduling system then moves to the next logical time step and repeats its crew assignment and crew, pad, and production update steps until at least one crew is free to be assigned a new job AND the episode is not complete. If true, the method returns a tuple of,
And waits for the next action from the agent. An episode is considered complete when all the jobs at all pads are done, at which point the reset method can be called and will return the scheduling system to its initial state.
The present invention uses one or two algorithms or agents to implement the claimed scheduling system.
Where p is a pad in the set P of all pads being scored, wn is the user specified weight/importance of each of the N criteria and xn is the computed value of each of the criteria described below,
For each agent type 1) Random Agent and 2) Epsilon Greedy Agent
Comparing Agent Performance. In every metric, the Epsilon Greedy Agent outperformed the Random Agent.
Each “Project” is comprised of a plurality of data elements, including pads, gas wells, basins, land leases, water reservoirs, jobs, crews, the expected gas, oil and NGL production per well, and a time-series of prices for gas, oil and natural gas liquids (NGL). Each pad is comprised of a plurality of gas wells. Basins, land leases, and water reservoirs contain a plurality of pads. Multiple jobs are to be performed at each pad by one of the available crews (pad construction, drilling, fracking, plug drill-out) until all jobs are completed. The claimed invention performs numerous simulations in parallel per project. Each simulation has the number of steps divided into a per simulation loop and a per project loop as follows.
Per Simulation Loop:
Project Loop:
Turning now to
In step 306, the data elements which have been accessed are converted into a uniform data format within each of the associated criteria. Example formats include alpha-numeric, currency, exponential numbers, decimal numbers, floating-point numbers, and more. The process continues to step 308.
In step 308, the simulation loops begin by executing a total number of simulations (M) in parallel. Shown is an inner loop per simulation loop 310, 312, 314 and an outer per project loop 316, 318, each of which is further described below.
The project loop may include several steps not shown. These steps include prompting the user, which algorithm or agent to run random or greedy and the number of simulations (M)
For the inner loop, in step 310, each job to be performed is evaluated, and which crews are available to perform the jobs. The inner loop continues to step 312. In step 312, an algorithm is executed to produce results, wherein the results include a schedule of crews and jobs and a production timeline. The inner loop continues to step 314 in which a test is made. In step 314, a test is made to determine if a total number of jobs is completed or a time period expires. If the test returns a false value, the process continues the inner loop by returning to step 308 above. Otherwise, if the test returns true, meaning that the total number of jobs is complete or the time expired, the process continues to the outer loop in step 316.
In step 316, the results from the total number of simulations (M) are ranked with the highest gas production. The process continues to step 318.
In step 318, a portion of the results with the highest gas production is sent to a display, and the process ends in step 320.
Shown are two side-by-side panels 408, 410, with a Gantt chart and corresponding data overhead for a five-year period between 2021 and 2025. Point X1 404 corresponds to EBITDA (Earnings Before Interest, Taxes, Depreciation, And Amortization) Gantt Schedules 408 and the data above, and point X2 406 corresponds to EBITDA Gantt Schedules 410 and the data above. The comparison of point X1 versus X2 is shown with the other metrics for each directly above. No two simulations are going to be identical because of changes in input data. Note all the points X1, X2 and others are selectable by a user to see the details of a particular episode or a run.
Turning now to
Quadrant 506 all the runs through the claimed scheduling system for a selected oil and natural gas well in quadrant 504. Again, each run will have different settings and inputs, e.g., a different number of crews or pricing and the number of episodes. The best performing results for the Haynesville-R11-Full in quadrant 504 are shown in quadrant 508. Each simulation may be using different pricing or a different number of crews. In this example, the best-performing episode or run for this top one, i.e., simulation number of episode 67. The data associated with this best-performing run is also shown in the corresponding row.
Turning to
Turning to
The present invention can be implemented on a standalone computer system, a server, a web-server, a cloud computer system or a hybrid cloud system, or other on-demand availability of computer system resources, especially data storage and computing power, without direct active management by the user.
The processor 800 in this example includes a hardware processor or CPU 804 that is communicatively connected to a main memory 806 (e.g., volatile memory), a non-volatile memory 812 to support processing machine instruction and operations. The CPU is further communicatively coupled to a network adapter hardware 816 to support input and output communications with external computing systems such as through the illustrated network 830.
The processor 800 further includes a data input/output (I/O) processor 814 that is able to be adapted to communicate with any type of equipment, such as the illustrated system components 828. The data input/output (I/O) processor, in various examples, is able to be configured to support any type of data communications connections, including present-day analog and/or digital techniques or via a future communications mechanism. A system bus 818 interconnects these system components.
The present subject matter can be realized in hardware, software, or a combination of hardware and software. A system can be realized in a centralized fashion in one computer system or in a distributed fashion where different elements are spread across several interconnected computer systems. Any kind of computer system—or other apparatus adapted for carrying out the methods described herein—is suitable. A typical combination of hardware and software could be a general-purpose computer system with a computer program that, when being loaded and executed, controls the computer system such that it carries out the methods described herein.
The present subject matter can also be embedded in a computer program product, which comprises all the features enabling the implementation of the methods described herein, and which—when loaded in a computer system—is able to carry out these methods. Computer program in the present context means any expression, in any language, code, or notation, of a set of instructions intended to cause a system having an information processing capability to perform a particular function either directly or after either or both of the following a) conversion to another language, code or, notation, and b) reproduction in a different material form.
Each computer system may include, inter alia, one or more computers and at least a computer readable medium allowing a computer to read data, instructions, messages or message packets, and other computer readable information from the computer readable medium. The computer readable medium may include computer readable storage medium embodying non-volatile memory, such as read-only memory (ROM), flash memory, disk drive memory, CD-ROM, and other permanent storage. Additionally, a computer medium may include volatile storage such as RAM, buffers, cache memory, and network circuits. Furthermore, the computer readable medium may comprise computer readable information in a transitory state medium such as a network link and/or a network interface, including a wired network or a wireless network, that allow a computer to read such computer readable information. In general, the computer readable medium embodies a computer program product as a computer readable storage medium that embodies computer readable program code with instructions to control a machine to perform the above-described methods and realize the above-described systems.
Although specific embodiments of the subject matter have been disclosed, those having ordinary skill in the art will understand that changes are made to the specific embodiments without departing from the spirit and scope of the disclosed subject matter. The scope of the disclosure is not to be restricted, therefore, to the specific embodiments, and it is intended that the appended claims cover any and all such applications, modifications, and embodiments within the scope of the present disclosure.