<p>Cloud Manufacturing (CMfg) has emerged as a cutting-edge technology facilitating collaborative manufacturing services delivered over the Internet. However, ensuring appropriate Quality of Service (QoS) attributes that align with user requirements in a cloud environment remains challenging due to the variability in service offerings from numerous cloud providers. Existing population-based optimization techniques often struggle to balance exploitation and exploration effectively. In this study, we propose a solution to achieve optimality in service composition for CMfg by employing Social Group Optimization (SGO), a promising population-based optimization technique. Through rigorous simulations, we demonstrate that SGO yields comparable performance to modern optimization techniques like Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Differential Evolution (DE), with improvements in [specific metrics, e.g., response time, cost efficiency]. By leveraging SGO, CMfg providers can enhance their ability to deliver manufacturing services with improved QoS attributes, ensuring better end-user satisfaction in a highly competitive cloud market. This research contributes to the advancement of CMfg by providing a robust method for optimizing service composition, ultimately benefiting both providers and users.</p> Graphical abstract <p></p>