Drilling Schedule Optimization via Parallel Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Historically, production planning for unconventional shale wells has been manually intensive and focused on short-term horizons, lacking the ability to determine optimal schedules due to the complexity of combinatorial factors, which are not solvable by humans using spreadsheets.
Innovation Solution
A scheduling system utilizing an algorithm that efficiently solves for high-value scenarios over a long-term time horizon, allowing for flexibility, by projecting gas production based on various criteria such as well location, crew allocation, and job timing, and executing multiple simulations to produce a ranked schedule of crews and jobs, using an epsilon-greedy or random algorithm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual planning methods using spreadsheets are used, then the planning process is simple to implement, but the ability to determine optimal schedules is lost due to combinatorial complexity
Solution Approach 1:
The patent replaces manual mechanical planning processes with computer-based simulation and optimization algorithms. The system uses computational models to evaluate multiple scheduling scenarios and automatically determine optimal schedules, substituting human spreadsheet manipulation with automated software that can handle combinatorial complexity.
Solution Approach 2:
The system changes the approach from static spreadsheet parameters to dynamic simulation parameters. By implementing iterative simulation processes that evaluate multiple scenarios with varying parameters (crew allocations, job sequences, timing), the system transforms the planning process from a simple manual procedure to an optimized computational analysis.
2Loss of time
If short-term time horizon planning is used, then the planning process is faster and simpler, but long-term production optimization is lost
Solution Approach 1:
The system performs preliminary computational setup and model configuration that enables both short-term quick planning and long-term comprehensive optimization. By pre-configuring simulation parameters and optimization algorithms, the system can rapidly evaluate scenarios while maintaining the capability to analyze long-term production schedules when needed.
Solution Approach 2:
The planning system is made dynamic and adaptable to different time horizons. The simulation model can be configured to evaluate schedules over varying time periods, allowing users to switch between short-term operational planning and long-term production optimization based on specific needs, rather than being fixed to a single time horizon.
3Productivity
If comprehensive criteria including location, crew allocation, and job timing are evaluated through multiple simulations, then production optimization is maximized, but computational complexity and processing time increase
Solution Approach 1:
The comprehensive scheduling problem is segmented into discrete evaluable components: individual jobs, crews, pads, and time periods. The simulation system evaluates these segmented elements systematically through multiple simulations, breaking down the complex optimization problem into manageable parts that can be analyzed and recombined to determine optimal schedules.
Data Source
AI summary
Disclosed is a system and method for improving oil and gas drilling scheduling. A plurality of project projections is performed by accessing data elements, each associated with criteria. 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 simulations include evaluating each of the jobs to be performed and which crews are available to perform 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.