Well Placement Optimization With Cat Swarm Optimization Algorithm Under Oilfield Development Constraints

Abstract

Proper well placement can improve the oil recovery and economic benefits during oilfield development. Due to the nonlinear and complex properties of well placement optimization, an effective optimization algorithm is required. In this paper, cat swarm optimization (CSO) algorithm is applied to optimize well placement for maximum net present value (NPV). CSO algorithm, a heuristic algorithm that mimics the behavior of a swarm of cats, has characteristics of flexibility, fast convergence, and high robustness. Oilfield development constraints are taken into account during well placement optimization process. Rejection method, repair method, static penalization method, dynamic penalization method and adapt penalization method are, respectively, applied to handle well placement constraints and then the optimal constraint handling method is obtained. Besides, we compare the CSO algorithm optimization performance with genetic algorithm (GA) and differential evolution (DE) algorithm. With the selected constraint handling method, CSO, GA, and DE algorithms are applied to solve well placement optimization problem for a two-dimensional (2D) conceptual model and a three-dimensional (3D) semisynthetic reservoir. Results demonstrate that CSO algorithm outperforms GA and DE algorithm. The proposed CSO algorithm can effectively solve the constrained well placement optimization problem with adapt penalization method.

Cat Swarm Optimization Algorithm: A Survey and Performance Evaluation

“…[102] Applied Cauchy mutated CSO to make linear aperiodic arrays, where the goal was to reduce sidelobe level and control the null positions e proposed system outperformed both CSO and PSO [103] Applied CSO and analytical formula-based objective function to optimize well placements CSO outperformed DE algorithm [104] Applied CSO to optimize well placements considering oilfield constraints during development. CSO outperformed GA and DE algorithms [105] CSO applied to optimize the network structure and learning parameters of an ANN model, which is used to predict an ASP flooding oil recovery index e system successfully forecast the ASP flooding oil recovery index [42] Applied CSO to build an identification model to detect early cracks in beam type structures CSO yields a desirable accuracy in detecting early cracks [106] Computational Intelligence and Neuroscience wavelet entropy, ANN, and CSO algorithm to develop an alcohol use disorder (AUD) identification system [64]. Kumar et al combined the CSO algorithm with functional link artificial neural network (FLANN) to remove the unwanted Gaussian noises from CT images [45].…”

“…CSO algorithm has also been applied in the petroleum engineering field. For example, it was used as a good placement optimization approach by Chen et al in [104,105]. Furthermore, Wang et al used CSO algorithm as an ASP flooding oil recovery index forecasting approach [43].…”

Cat Swarm Optimization Algorithm - A Survey and Performance Evaluation

“…CSO outperformed GA and DE algorithms [107] CSO applied to optimize the network structure and learning parameters of an ANN model, which is used to predict an ASP flooding oil recovery index…”

“…Pappula et al also used Cauchy mutated CSO to make linear aperiodic arrays, where the goal was to reduce sidelobe level and control the null positions[105].5.6 Petroleum Engineering: CSO algorithm has also been applied in the petroleum engineering field. For example, it was used as a good placement optimization approach by Chen et al in[106,107]. Furthermore, Wang et al used the CSO algorithm as an ASP flooding oil recovery index forecasting approach[44].…”

Optimizing the wells location using the Machine learning algorithms, as well as optimizing the drilling time of production and injection wells in one of the reservoirs in south west of Iran

“…In 2019, Hongwei Chen and et al used three algorithms, CSO (Cat Swarm Optimization), GA, and DE (Differential Evolution), in a simulated model to optimize the placement of oil wells. After conducting simulations, the results showed that the CSO algorithm outperformed GA and DE, effectively addressing the well placement optimization challenge [31]. In 2019, Yazdanpanah, and et al utilized optimization algorithms, including GA, PSO, and HGAPSO (Hybrid GA-PSO), to optimize the placement of oil wells.…”