Scalable IoT/M2M Platforms Based on Kubernetes-Enabled NFV MANO Architecture
Hung-Li Chen, Fuchun Joseph Lin · 2019
The Internet of Things (IoT) brings a huge impact to our daily life in recent years. It is anticipated that tens of millions of IoT/M2M (Machine to Machine) devices will be connected to the IoT/M2M platforms hosted in the cloud. In this research, we realize scalable IoT/M2M systems in the OpenStack cloud based on Kubernetes-enabled NFV (Network Function Virtualization) MANO (Management ANd Orchestration) architecture. Our research leverages NFV MANO supported by OpenStack Tacker to achieve the scalability of IoT/M2M platforms. The scaling functionalities are based on Kubernetes in which CNF (Container-based Network Functions) will be scaled out/in. In addition, a Master Node and a Load Balancer Node are designed for scalability supervision and for fair traffic distribution, respectively, among virtualized IoT/M2M servers in the cloud. We compare our proposed system with those NFV platforms without Kubernetes and validate that our proposed system achieves better scalability by reducing the overall scaling time and computational cost of a group of IoT/M2M servers.