ANI: Abstracted Network Inventory for Streamlined Service Placement in Distributed Clouds

Abstract

Scenarios for distributed cloud with multiple edge clouds and centralized data centers are being investigated as the computing and networking underpinnings of next-generation network services such as augmented reality, self-driving vehicles, drones, and more. In such distributed environments, service providers will typically face tens, hundreds, or thousands of compute location candidates (edge, regional, and central) where network service components can be placed. To take optimized placement decisions of network services and execute the management workflows, orchestration systems require up-to-date and accurate resource availability representation, in the form of a network inventory that can be immense in distributed cloud scenarios. As a result, the service management and placement problems may become not tractable. In this work, we propose the Abstracted Network Inventory (ANI) component to generate service-optimized network views over the same network inventory. ANI implements a novel abstraction method where network service requirements are used as an input to generate an optimized abstract network inventory representation, called Logical Network Inventory (LNI). We also provide a formal definition of the network model and problem statement along with the development of three algorithms to efficiently build an LNI. Results show the potential benefits of using an LNI to streamline service management and placement: (i) the relationship between compute nodes and links (i.e., density) in an LNI is reduced between 1.8-2.7x compared to a full network inventory topology; and (ii) up to 50% of time can be saved for service placement after abstracting around 20% of the compute nodes.