SDN for End-Nodes: Scenario Analysis and Architectural Guidelines
Alberto Rodriguez-Natal, Vina Ermagan, Kien Nguyen, Sharon Barkai,, Yusheng Ji, Fabio Maino, Albert Cabellos-Aparicio

TL;DR
This paper analyzes the challenges of deploying SDN for scattered, transient end-nodes like smartphones, proposes architectural guidelines, and validates a decentralized controller design through a proof-of-concept.
Contribution
It provides a detailed scenario analysis, identifies unique challenges, and offers a practical, decentralized SDN architecture for end-node control.
Findings
Identified unique challenges in SDN for end-nodes
Proposed a decentralized, distributed controller architecture
Validated the architecture with a proof-of-concept deployment
Abstract
The advent of SDN has brought a plethora of new architectures and controller designs for many use-cases and scenarios. Existing SDN deployments focus on campus, datacenter and WAN networks. However, little research efforts have been devoted to the scenario of effectively controlling a full deployment of end-nodes (e.g. smartphones) that are transient and scattered across the Internet. In this paper, we present a rigorous analysis of the challenges associated with an SDN architecture for end-nodes, show that such challenges are not found in existing SDN scenarios, and provide practical design guidelines to address them. Then, and following these guidelines we present a reference architecture based on a decentralized, distributed and symmetric controller with a connectionless pull-oriented southbound and an intent-driven northbound. Finally, we measure a proof-of-concept deployment to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSoftware-Defined Networks and 5G · Caching and Content Delivery · Cloud Computing and Resource Management
