Elastic resource management and network slicing for IoT over edge clouds

Elastic resource management and network slicing for IoT over edge clouds

연구 분야: Cryptography

학회: IoT '20: Proceedings of the 10th International Conference on the Internet of Things

The Internet of Things (IoT) application ecosystem is driven by third party developers outside of the telecom domain. Edge infrastructure of communication service providers will therefore be accessible to third party application providers and developers and will host a multitude of application each with different characteristics. We foresee that multiple business actors will contribute to an IoT and edge-ecosystem including Hyperscale Cloud Providers (HCPs), Operation Technology (OT) vendors, communication service providers, and application developers. To reduce cost, efficient use of resources are needed across all business actors. End users, especially in IoT deployment, will look for pay-as-use (elasticity) service offerings similar to IT cloud offerings. Therefore, the layers of orchestration services must be able to elastically resize their respective resource pools by the means of initiating re-configurations via the underlay providers' orchestration services. We propose a workload placement algorithm, which can reconfigure both cloud (e.g., Infrastructure as a Service) and network (e.g., Virtual Private Network) resource underlays during resource orchestration. Our proposed method ensures that different business actors can exercise elastic control of their resources, so their committed services and bought resources are in better (best) alignment. The proposed method is functionally evaluated with 5G network slicing with local break-out to an IoT stack in the network edge.