Microservices-Based Design of Cloud-Edge Collaboration Architecture

With the emergence of the Internet of Things, cloud computing is beginning to reveal its potential flaws. In recent years, with the rapid development of edge computing, the cloud-edge computing model that introduces edge computing has been widely recognized in the academic, commercial, and governmental fields, which has evolved into a core topic of a national strategy. Therefore, Cloud Edge Collaborative Computing is crucial in the future and valuable for research. In this paper, we design a cloud-edge intelligent collaboration architecture. Based on the idea of micro-service, we decouple the function layers of the Artificial Intelligence plane into six network functions (NFs) on a four-layer, three-plane network architecture. Then, orchestrating Cloud-Edge NFs with Kubernetes to provide customized services, and monitoring and managing the NFs in real time throughout their respective lifecycles. Finally, the Cloud-Edge Intelligent Collaborative Experiment Platform is built by integrating open-source software and general-purpose hardware, and the efficiency of the proposed architecture is verified through the performance of the platform. Experiment results demonstrate the feasibility and reliability of the proposed architecture, which improve the system utility and efficiency obviously.