MPCSM: Microservice Placement for Edge-Cloud Collaborative Smart Manufacturing

Abstract

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

Dynamic Execution of Engineering Processes in Cyber-Physical Systems of Systems Toolchains

“…Specifically for manufacturing production, the authors of [27] survey the motivations and approaches on why and how Manufacturing Engineering Systems (MES) evolve for Industry4.0, whereas [28] provides an overview for MES-integrated digital twin frameworks. Smart factory reconfiguration for healthcare [29] and Edge-Cloud collaborative manufacturing [30] are further concrete examples of using SOA and microservice approaches at the MES and the manufacturing edge-cloud infrastructures, respectively.…”

IECL: An Intelligent Energy Consumption Model for Cloud Manufacturing

“…To evaluate the energy consumption of servers, the author of [21] created a novel power model based on a performance monitor counter. More recently, the authors of [22] introduced a microservice placement strategy for edge-cloud collaborative smart manufacturing. Their approach tackled the solutions over semiconductor manufacturing case study and elaborated the construction of the latency metric.…”

Reinforcement learning multi-agent system for faults diagnosis of mircoservices in industrial settings

“…Wang et al [16] proposed an ensemble learning approach for capturing outliers in the microservice environment. The approach used a support vector machine and a convolution neural network in each node.…”