Cloud manufacturing service composition based on QoS with geo-perspective transportation using an improved Artificial Bee Colony optimisation algorithm

TLDR

Cloud Manufacturing aims to build dedicated manufacturing clouds by integrating diverse service provider resources, making service selection and composition critical to meet customer requirements and address manufacturing-specific constraints. The study proposes a method that evaluates cloud services using QoS metrics while incorporating the geographic location of manufacturing resources to analyze transportation impacts. The method verifies manufacturing time estimates by accounting for resource availability over time and optimizes the exhaustive composition process using an enhanced Artificial Bee Colony algorithm. Experiments demonstrate the method’s efficiency and precision.

Abstract

Cloud Manufacturing (CMfg) ambitions to create dedicated manufacturing clouds (i.e. virtual enterprises) for complex manufacturing demands through the association of various service providers' resources and capabilities. In order to insure a dedicated manufacturing cloud to match the level of customer's requirements, the cloud service selection and composition appear to be a decisive process. This study takes common aspects of cloud services into consideration such as quality of service (QoS) parameters but extend the scope to the physical location of the manufacturing resources. Unlike the classic service composition, manufacturing brings additional constraints. Consequently, we propose a method based on QoS evaluation along with the geo-perspective correlation from one cloud service to another for transportation impact analysis. We also insure the veracity of the manufacturing time evaluation by resource availability overtime. Since the composition is an exhaustive process in terms of computational time consumption, the proposed method is optimised through an adapted Artificial Bee Colony (ABC) algorithm based on initialisation enhancement. Finally, the efficiency and precision of our method are discussed furthermore in the experiments chapter.