MPCSM: Microservice Placement for Edge-Cloud Collaborative Smart Manufacturing

Latency-aware service placement is promising in reducing the overall response latency of proliferating edge-cloud collaborative smart manufacturing systems. However, intuitive estimators used by existing approaches cannot accurately depict nonlinear end-to-end (E2E) multihop microservices with complex dependencies, which severely hindering effectiveness latency-aware placement. To address this issue, article, we present a microservice mechanism for (MPCSM), where algorithm supported an accurate data-driven E2E estimation method proposed. We build real-world prototype, and conduct case study on semiconductor to elaborate construction our estimator. Results extensive experiments demonstrate that error estimator up 10× less than ones, MPCSM approaches.