A surrogate assisted quantum-behaved algorithm for well placement optimization

The oil and gas industry faces difficulties in optimizing well placement problems. These problems are multimodal, non-convex, and discontinuous in nature. Various traditional and non-traditional optimization algorithms have been developed to resolve these difficulties. Nevertheless, these techniques remain trapped in local optima and provide inconsistent performance for different reservoirs. This study thereby presents a Surrogate Assisted Quantum-behaved Algorithm to obtain a better solution for the well placement optimization problem. The proposed approach utilizes different metaheuristic optimization techniques such as the Quantum-inspired Particle Swarm Optimization and the Quantum-behaved Bat Algorithm in different implementation phases. Two complex reservoirs are used to investigate the performance of the proposed approach. A comparative study is carried out to verify the performance of the proposed approach. The result indicates that the proposed approach provides a better net present value for both complex reservoirs. Furthermore, it solves the problem of inconsistency exhibited in other methods for well placement optimization.