| Nowadays, with the development of informatization technology, web service, semantic Web, utility computing, cloud computing, and internet of things, computer integrated manufacturing, agile manufacturing, manufacturing grid, cloud manufacturing (CloudM) and other networked manufacturing modes are proposed and used widely. Based on the analysis of application and promotion problems in the existing mode, as a new generation service-oriented networked manufacturing mode, CloudM is to provide user with on-demand, always-ready, high-quality and low-consumption service, which is available from product design, manufacturing, testing, simulation and maintenance and other manufacturing lifecycle process.Service composition is one of the key issues in implementing CloudM system. Exiting works on service composition are primarily based on quality of service (QoS) to provide high-quality service for user. Few works have been delivered on providing both high-quality and low-energy consumption service and no related theories and methods are proposed. The following problems must be addressed:(1) How to evaluate service energy consumption?(2) How to generate composed service execute path (CSEP) to satisfied complex user requirement?(3) How to evaluate CSEP energy consumption?(4) How to design energy-saving incentive mechanism for enterprise, user and CloudM platform inservice composition process?(5) How to design an efficient algorithm for multi-objective SCOS problem?(6)How to find right balance in conflicting multi-objectives?(7) How to realize service composition to decrease composition and selection times and increase success rate?Considering the specific requirements of service composition in CloudM, this paper researches on the involving theories and technologies of service composition based on service energy consumption, composed service energy consumption and intelligent service composition, which provides the technical supports for the application of CloudM. The main works involving in this paper is as follows: (1) In view of the characteristics of service composition in green CloudM, this paper analyses and descripts service composition in CloudM, proposed energy consumption and QoS aware service composition framework in CloudM, and elaborate key technologies to achieve energy consumption and QoS aware service composition in CloudM.(2) The definitions of CloudM resource and service are given out. Combined with requirement of CloudM green service composition and selection, QoS evaluation model and energy consumption evaluation model supporting lifecycle process are researched. CloudM service energy consumption evaluation framework is proposed, as well as service energy consumption model.To evaluates single service, CloudM service energy consumption evaluation algorithm is design, and the case study is given out.(3) Description of service composition is studied. Multiple objectives service composition and optimal selection model based on energy consumption and QoS (MOSCOS-ECQoS) is proposed, including service composition basic modes, CESP Qos andenergy consumption evaluation. Energy-saving incentive mechanism in service composition process is design.(4) To provide user high-quality and low-energy consumption service, green service composition selection methods based on Group Leader algorithm-Pareto are researched. Mapping relationship between a CESP candidate and a GLA member is discusses. Based on concept of multi-objectives Pareto, solutions of MOSCOS-ECQoS are researched. The structure and process of GLA-Pareto algorithm are designed.The case study and simulation results indicate the proposed methods are valid and effective.(5) Based oncase library, service composition implementation plan are proposed, including structure, design, update and process of service composition case library. The implementation and simulation results indicate that the proposed approaches are sound on promoting the success rate and speed of MOSCOS-ECQoS.(6) To verifies the partly research results, this paper design prototype system of energy consumption aware service composition, the functions of key modules in the prototype system are realized, including QoS evaluation, energy consumption evaluation, multi-objectives optimal service selection modeling, optimal selection algorithm and service composition based on case library, et al. |
PDF Full Text Request