Agent-based models (ABMs) provide a fast alternative to traditional partial differential equation (PDE)-based oil reservoir models by applying localized inexpensive simulations, rather than solving a partial differential equation at every time-step. However, while there have been theoretical and numerical results obtained with ABMs in social science applications, the accuracy of ABMs has not been analyzed in the context of oil reservoir modeling. This paper quantifies the accuracy of a specific ABM by comparing its results to a single-phase flow reservoir. We show that the proposed ABM matches results given by the PDE-based model with less than 5.4% difference. Results are obtained for reservoirs with single and double producers, with varying permeability and with impermeable barriers.

Keywords:
reservoir simulation, eq rate, Artificial Intelligence, permeability value, Reservoir Characterization, structural geology, equalization rate, double producer test, simulator, equation
Subjects:
Reservoir Characterization, Reservoir Simulation, Information Management and Systems, Exploration, development, structural geology, Data mining, Artificial intelligence
Copyright 2019, Society of Petroleum Engineers
You can access this article if you purchase or spend a download.