Manufacturing Service Reconfiguration Optimization Using Hybrid Bees Algorithm in Cloud Manufacturing

摘要

During the execution process of a cloud manufacturing (CMfg) system, manufacturing service may become faulty to cause the violation of whole production processes against the predefined constraints. It is necessary to timely adjust service aggregation process to the runtime failure during manufacturing process. Therefore it is significant to do service reconfiguration to enhance the reliability of service-oriented manufacturing applications. The issues of the runtime service process reconfiguration based on QoS and energy consumption have been studied. In this paper, by contrast, an effective reconfiguration strategy is proposed to identify reconfiguration regions rather than the whole service process. Moreover, a hybrid bees algorithm (HBA) combining discrete bees algorithm (DBA) with discrete particle swarm optimization (DPSO) is developed to explore the replaceable services during service reconfiguration process. The experiment results show that most of manufacturing service aggregation processes can be repaired by replacing only a small number of services, and HBA is more efficient when finding the replaceable manufacturing services set compared with the existing algorithms.