Well Placement in Complex Carbonate Reservoirs Using Simulation Optimization
Simulation–optimization, a term that refers to the coupling of models to optimization drivers, has received extensive attention in the petroleum and groundwater remediation literature. The goal of optimization for this type of problem is usually to find one or more combinations of extraction and injection well locations that will at least contain and preferably clean up the contamination at minimum cost or time in case of a groundwater aquifer-cleanup problem and maximize the production at minimum cost for petroleum engineering problems. Although the number of well combinations is potentially infinite, it has been customary in both in groundwater and production optimization work to pre-specify a grid of potentially good well locations and then formulate the search to locate the most time- or cost-effective subset of those locations that meets remediation and production goals. In this study, a knowledge base of representative solutions were created, artificial neural networks (ANN) to predict selected simulator outcomes were trained and tested. In the next step well combinations via optimization to predict outcomes with ANN were generated. Finally, the outcomes were verified by simulations.
Related Publications