Hybrid teaching-learning-based optimization of correlation-aware service composition in cloud manufacturing

Cloud manufacturing (CMfg) provides a new product development model in which users are enabled to configure, select, and utilize customized manufacturing services on-demand. The service composition with optimal overall quality of service (QoS) is of great significance since it affects the efficiency of resource sharing and optimal allocation in CMfg systems. However, some limitations still exist in manufacturing service composition methods especially in the complicated cloud environment. This owes to two aspects: (1) current service composition approaches assume that the QoS of services is fixed and not influenced by other services, the existence of the service correlation context is not considered adequately, thus resulting in no accordance with practical applications; (2) with the growing number of candidate services in cloud resource pools, the traditional methods might be inefficient for addressing large scale service composition problems. To overcome such drawbacks, this study proposes a new hybrid teaching-learning-based optimization (HTLBO) algorithm for optimal service composition with the consideration of service correlations. Experiments are conducted to verify the effectiveness and feasibility of the proposed algorithm.