Cloud Manufacturing Service Composition Research Based On Intelligent Optimization Algorithm

Cloud manufacturing is a new service-oriented manufacturing paradigm,which has fully integrated "decentralized resource centralized management,centralized resource decentralized service" and provides a new way for the optimal allocation of manufacturing resources.However,under the circumstance of various and individualized demands of customes,the single-function service has been unable to meet the needs of users.Thus,the combination of single service is becoming very important.Service composition optimal-selection(SCOS)is a typical NP-hard problem with the characteristics of dynamic and uncertainty.Therefore,it is important to select and improve the intelligent optimization algorithm to solve the large-scale SCOS problem with numerous constraints in CMfg,so as to meet the individual needs of users,which has important theoretical significance and application prospect.In this thesis,the CMfg Service Composition Optimization Selection(CSCOS)is constructed as a fuzzy QoS service evaluation model with better description ability,based on which,a novel intelligent algorithm,namely Local search based Discrete Artificial Bee Colony(LDABC)is developed.Firstly,a fuzzy QoS service evaluation model is constructed,which can solve the problem of bad description ability and data loss.Secondly,the ABC algorithm is improved,and the local search and chaos optimization are introduced for better convergence speed and global optimization ability.Further more,LDABC is applied to solve the complicated CSCOS problem,and the effectiveness and efficiency of the improved algorithm is verified by experiments on small scale and large-scale problems.To validate the performance of LDABC,comparisions with the original Artificial Bee Colony(ABC),Particle Swarm Optimization(PSO)and Differential Evolution(DE)are conducted.The results show that the proposed method is more effective in solving complex CSCOS problem?...