Data-driven evolutionary algorithm for oil reservoir well-placement and control optimization

Well placement and control scheme optimization is crucial for hydrocarbon, groundwater and geothermal development, and generally involves a large number of discrete and correlated decision variables. Meta-heuristic algorithms have showed good performance in solving complex, nonlinear and non-continuous optimization problems. However, a large number of numerical simulation runs are involved during the optimization process. In this work, a novel and efficient data-driven evolutionary algorithm, called generalized data-driven differential evolutionary algorithm (GDDE), is proposed to reduce the number of simulation runs on well-placement and control optimization problems. Probabilistic neural network (PNN) is adopted as the classifier to select informative and promising candidates, and the most uncertain candidate based on Euclidean distance is prescreened and evaluated with a numerical simulator. Subsequently, local surrogate model is built by radial basis function (RBF) and the optimum of the surrogate, found by optimizer, is evaluated by the numerical simulator to accelerate the convergence. It is worth noting that the shape factors of RBF model and PNN are optimized via solving hyper-parameter sub-expensive optimization problem. The results show the optimization algorithm proposed in this study is very promising for a well-placement optimization problem of two-dimensional reservoir and joint optimization of Egg model. The convergence curves of the proposed algorithm reveal that the simulation runs significantly reduced to around 20 percent during the optimization process in comparison with conventional differential evolutionary algorithm. The proposed algorithm of this study can help for better decision making on computationally expensive simulation-based optimization problems.