Socio-Inspired Multi-Cohort Intelligence and Teaching-Learning-Based Optimization for Hydraulic Fracturing Parameters Design in Tight Formations

Abstract Hydraulic fracturing is one of the revolutionary technologies widely applied to develop tight hydrocarbon reservoirs. Moreover, hydraulic fracture design optimization is an essential step to optimize production from tight reservoirs. This study presents the implementation of three new socio-inspired algorithms on hydraulic fracturing optimization. The work integrates reservoir simulation, artificial neural networks, and preceding optimization algorithms to attain the optimized fractures. For this study, a tight gas production dataset is initially generated numerically for a defined set of the fracture half-length, fracture height, fracture width, fracture conductivity, and the number of fractures’ values. Secondly, the generated dataset is trained through a neural network to predict the effects of preceding parameters on gas production. Lastly, three new socio-inspired algorithms including cohort intelligence (CI), multi-cohort intelligence (multi-CI), and teaching learning-based optimization (TLBO) are applied to the regressor output to obtain optimized gas production performance with the combination of optimum fracture design parameters. The results are then compared with the traditionally used optimizers including particle swarm optimization (PSO) and genetic algorithm (GA). The results demonstrated that the multi-CI and TLBO converge at the global best position more often with a success rate of at least 95% as compared to CI, PSO, and GA. Moreover, the CI, PSO, and GA are found to stuck many times at the local maximum. This concludes that the multi-CI and TLBO are good alternatives to PSO and GA considering their high performance in determining the optimum fracture design parameters in comparison.