Search

Multi-objective optimization (MOO), which involves more than one conflicting objective to be optimized simultaneously, is expected to provide efficient and comprehensive reservoir management (RM) solutions. The multi-objective production optimization problems are considered to be expensive due to the difficulties and cost of operations. Surrogate-assisted evolutionary algorithms (SAEAs), which has proved to be an effective way to solve expensive problems, design computationally cheap function to approximate each objective function. Meanwhile, the optimization process involves a large number of decision variables. However, building a high-quality surrogate model has become difficult due to the "curse of dimensionality". Base on characterization, an efficient multi-objective optimization framework called SA-RVEA-PCA is proposed to effectively deal with large-scale and computationally expensive simulation-based optimization problems, including three parts:1) Given a set of simulation results, a Gaussian process (GP) model based on Principal Component Analysis (PCA) for each objective function is trained so that the surrogate models can guide the optimization more accurately. 2) A reference vector guided evolutionary algorithm (RVEA) recently developed is employed as a multi-objective optimizer. 3) The information of uncertainty given by GP and angle-penalized penalized (APD) proposed in RVEA are used to update the surrogate models. To the best of our knowledge, the proposed algorithm is applied to a benchmark function, and two typical applications of MOO with synthetic reservoir models. Results show that the proposed method can provide more comprehensive and efficient RM with a higher convergence speed. • A new multi-objective framework is proposed based on surrogate-assisted algorithm and dimension-reduction method. • The new methodology is successfully applied to two general multi-objective production optimization problems. • The optimization results of two cases show the great performance of the proposed method. [ABSTRACT FROM AUTHOR]

Recently, evolutionary algorithms (EAs) are becoming more and more popular in oil industry. It should be noted that the existence of various state constraints largely decreases the efficiency of EAs. In this paper, a double-model differential evolution (CSDE) is proposed for waterflooding production optimization with nonlinear inequality constraints. There are two main stages in CSDE: 1) the boundary of feasible region is explicitly constructed by a classifier, support vector machine (SVM), to prescreen the feasible solutions from current population, and 2) the objective function is approximated by radial basis function (RBF) surrogate model which can be used to select the best individual among feasible solutions. It is worth noticing that problems with a large number of constraints can be significantly simplified by distinguishing the feasible solutions and infeasible solutions with one unique SVM classifier. To the best of our knowledge, this is the first foray to integrate SVM and RBF into evolutionary algorithm for waterflooding optimization problem. The CSDE method has been tested on three artificial cases: three-channel, PUNQ-S3 and SPE9. The test results demonstrate that CSDE algorithm can handle constraints more efficient and achieve higher net present value (NPV) compared with the original EAs and other single-model algorithms. • A classification-based surrogate-assisted differential evolution (CSDE) is proposed. • This is the first foray to integrate SVM and RBF into evolutionary algorithm for constrained production optimization. • The experimental results demonstrate that the proposed method can handle constraints better and achieve higher NPV. [ABSTRACT FROM AUTHOR]