QoS Evaluation And Scheduling Optimization Of Services Under Collaborative Manufacturing

With the rapid development and wide application of the collaborative manufacturing model,collaborative manufacturing services have attracted more and more users,and the services in the collaborative manufacturing environment have shown a massive growth trend.How can users accurately select the services that meet their needs from a large number of services?Is the focus of current collaborative manufacturing research.However,most of the current service optimization selection methods only combine the functional requirements of the service and the common QoS attributes,and do not combine the characteristics of the collaborative manufacturing environment,and do not perform credibility analysis on the service QoS attribute values,which easily leads to service scheduling failure and resource waste.In response to this problem,the research work of this paper is as follows:1.A QoS evaluation model for services in a collaborative manufacturing environment is constructed.The evaluation model combines the relevant features of the collaborative manufacturing field to construct an evaluation model that comprehensively considers the service providers and users to evaluate QoS attributes,and selects service price,quality,response time,reliability,trust,etc.2.Analysis of the credibility of QoS attribute values.The service provider QoS attribute value is used to analyze the credibility of the QoS attribute value through historical statistics;for the user QoS evaluation information,the user history evaluation information classification,the user personality preference analysis,the similarity calculation process,etc.are obtained,thereby obtaining a reliable user evaluation.3.Service scheduling optimization.According to the QoS evaluation information,the QoS parameters are standardized,the QoS attribute values are determined by the entropy weight method,and the forbidden ant colony algorithm is used for service scheduling.Finally,according to the service scheduling success rate,task execution time,and load balancing of services Compared with particle swarm optimization algorithm and ant colony algorithm,the experimental results show that the proposed algorithm is more efficient for service scheduling and more reasonable for service resource allocation.