Availability and Latency Aware Deployment of Cloud Native Edge Slices

Edge computing is one of the key technology of the last decade, enabling several emerging services beyond 5G (e.g., autonomous driving, robotic networks, Augmented Reality (AR)) requiring high availability and low latency communications. While in cloud native paradigm, highly embraced by cloud providers, network functions and applications are decomposed into microservices run in a container. Defacto container orchestration engine, namely Kubernetes, deploys multiple containers inside a pod. The mapping between microservices and pod highly affects the availability and latency of deployed microservices and hence the run application. In this paper, we propose novel availability and latency-aware deployment models for an edge service composed of multiple applications designed as multiple microservices. The two considered deployments are analyzed and evaluated using experimentation and an analytical model, considering critical performance criteria for edge-oriented services, like availability and latency requirements.