Optimal scheduling of field activities using constraint satisfaction problem theory

Abstract

The challenge of identifying problematic wells and planning their workover operations is common in oil and gas fields. On top of this, the well intervention resources are seldom easily accessible so it is crucial to target the right set of wells at the right time. Oil and gas reservoirs are complex dynamic systems the production and injection patterns of which can significantly affect the reservoir and well response. This represents a complex mathematical optimisation problem where the overall life performance of the field strongly depends on the workover planning decisions. This work presents a reliable and effective tool that is able to screen and explore the large search space of the potential work-overs that adds value to the reservoir management process. The proposed solution considers the overall performance of the field throughout a specified period while respecting all operational limitations as well as considering the risks and costs of the interventions. The proposed workflow combines the commercial optimiser techniques with constraint satisfaction problem optimiser to identify the optimal workover scheduling. The schedule found is guaranteed to satisfy all predefined field constraints. The presented results showed better performance achieved by the proposed hybrid optimiser compared to classical gradient-free optimisation techniques such as Genetic Algorithm in maximising the defined objective function. The suggested workflow can greatly enhance the decisions related to field development and asset management involved with large number of wells and with limited intervention resources.