부산대학교 도서관

By collecting and processing smart healthcare data in real-time, mobile edge networks can bridge the gap between doctors and patients, which is a representative consumer-level data interaction scenario in Industry 5.0. To improve the flexibility and timeliness of suchlike Industry 5.0 services, microservices are deployed extensively on edge servers. The major challenge facing microservice deployment is how to reduce the cost. However, cost and quality of service (QoS) are a pair of contradictory objectives, and different scenarios have different preferences for the two objectives, which is easy to be ignored. In order to solve this problem, this paper considers service responsiveness and user mobility in the response process of requests. Then a Constrained Multi-objective Optimization Problem (CMOP) is formulated by combining deployment cost and task completion rate. Considering the differentiated requirements of users in different scenarios, this paper proposes a Multi-objective Optimization Evolutionary Algorithm with the Penalty Mechanism (MOEA-PM) to solve this CMOP. Simulation results demonstrate that adding a penalty segment to the fitness function can boost algorithm efficiency significantly. Compared with baseline algorithms, MOEA-PM always yields a microservice deployment strategy set adapted to a variety of industry 5.0 scenarios.