An optimization method of cloud manufacturing service composition based on matching-collaboration degree

Traditional service combination methods in the cloud manufacturing paradigm mainly focus on economic targets, such as time and cost and ignore the matching and collaboration effects between cloud services and manufacturing tasks, resulting in the constructed service combination solutions not fully meeting the individual requirements of users. In this paper, the concepts of service matching degree and service collaboration degree are proposed, and an evaluation system of cloud manufacturing service composition is established to measure the quality of cloud services. Then a double-constraint service composition optimization model is designed considering the interests of both manufacturing service requestors and resource providers, which is solved by using the improved ant colony algorithm (IACO). Finally, an automobile bumper cloud manufacturing case is carried out to demonstrate the feasibility and effectiveness of the proposed method.