Multi-objective optimization algorithms are crucial for addressing real-world problems, particularly with regard to optimizing well control parameters, which are often computationally expensive due to their reliance on numerical simulations. Surrogate-assisted models help to reduce this computational burden, but their effectiveness depends on the quality of the surrogates, which can be affected by candidate dimension and noise. This study proposes a novel surrogate-assisted multi-objective optimization framework (MOO-SESA) that combines selective ensemble support-vector regression with NSGA-II. The framework’s uniqueness lies in its adaptive selection of a diverse subset of surrogates, established prior to iteration, to enhance accuracy, robustness, and computational efficiency. To our knowledge, this is the first instance in which selective ensemble techniques with multi-objective optimization have been applied to reservoir well control problems. Through employing an ensemble strategy for improving the quality of the surrogate model, MOO-SESA demonstrated superior well control scenarios and faster convergence compared to traditional surrogate-assisted models when applied to the SPE10 and Egg reservoir models.

It is of great significance to investigate the flow rate and stress distribution of multi-fracture propagation for the optimization of perforation parameters and fracture parameters. Considering the coupling of rock deformation, fracture direction and fluid flow in multi-fracture scenarios, a mathematical model and solution program for the flow and stress distribution of multiple fractures are established, and the analytical model is used for comparison and verification. The effects of perforation cluster number, cluster spacing, perforation diameter on fracture extension trajectory, fracture width, flow rate of each fracture and stress field are studied by the model. The results show that, as the number of perforating clusters increases, the inner fracture is inhibited more severely with less width, length and flow distribution, as well as lower bottom hole pressure. With the increase in cluster spacing, the stress interference between whole fractures is weakened and the flow distribution of the inner fracture is increased with lower bottom hole pressure. With the decrease in perforation diameter, the inhibition effect of inside fractures is weakened, while the inhibition effect of outside fractures, the flow distribution of inside fractures and the bottom hole pressure are increased. The uniform propagation of multiple fractures can be promoted by decreasing the perforation clusters’ number and perforation diameter or increasing fracture spacing.

Natural gas is an eco-friendly energy source with low carbon emissions, making it attractive globally. Understanding gas reservoirs is crucial for sustainable extraction and optimizing potential. However, the complicated fluid flow and production dynamics within intricate gas reservoirs, particularly those characterized by abnormally high pressures and tight porous media, remain partially understood and demand further investigation. In a tight porous medium subjected to high pressure, the assumption of constant permeability is no longer valid. Consequently, a novel composite seepage model has been developed in this study, which considers the responsiveness of permeability to stress. Perturbation theory is employed to address the inherent non-linearity demonstrated by the permeability modulus. The solution of dimensionless pressure responses under constant production conditions is accomplished in the Laplace domain by implementing integral transformation methods. Overall, a comprehensive model is provided to understand the production behaviors of tight gas reservoirs. Moreover, in order to comprehend the transient flow characteristics of tight gas reservoirs, log–log plots are generated through the Stehfest numerical inversion approach, with the flow regimes categorized based on the normalized time phases of the pressure curves. Parametric investigations reveal that stress sensitivity detrimentally affects permeability, resulting in more pronounced pressure declines during the intermediate and late flow phases. The transient seepage model elaborated in this study is able to consider the pertinent formation and well parameters. These interpreted parameters bear significance in designing hydraulic fracturing operations, assessing the potential of tight gas reservoirs, and ultimately enhancing gas production. The presented model not only enhances our understanding of the behavior of horizontal wells in stress-sensitive tight gas reservoirs but also makes a valuable contribution to the broader discussion on transient flow phenomena in petroleum engineering.