SDNator is Not Another SDN Controller: Enabling Extensible Data-Driven Control in Cyber-Physical Systems

2026-05-22

AI Summary

This work addresses the lack of general-purpose support for cross-domain, scalable data-driven applications in existing cyber-physical system (CPS) frameworks. We propose and open-source SDNator—the first domain-agnostic, scalable, data-driven control framework tailored for CPS—featuring an application- and data-centric design that enables applications to act as both producers and consumers in collaboratively defining controller workflows. SDNator integrates dual data storage backends to uniformly support event-driven and data-driven programming paradigms and adopts an SDN-like centralized architecture to enable flexible workflow orchestration and dynamic scheduling. Experimental results demonstrate that SDNator achieves scalability on par with the mainstream SDN controller Ryu, significantly reduces production cycle times and enhances robustness to anomalies in additive manufacturing and networking scenarios, and efficiently responds to urgent task demands.

Abstract

An SDN-like centralized control architecture is increasingly popular and has been widely explored in cyber-physical systems (CPS) such as manufacturing, internet-of-things, and autonomous vehicle systems for higher flexibility, programmability and scalability. However, no existing frameworks can offer domain-agnostic, easily extensible support for data-driven CPS applications. In this work, we design, implement, and open-source \textit{SDNator}, the first framework to enable extensible, data-driven control in CPS. SDNator embraces an application- and data-driven design where applications function as data consumers and producers to collectively define the workflows of the controller. SDNator also incorporates two data store backends to support both event-driven and data-driven programming patterns. Benchmarks show that SDNator is highly scalable, and delivers comparable performance to Ryu, a widely used SDN controller. Moreover, we demonstrate the capabilities and usability of SDNator through our case studies of manufacturing and networking systems. By integrating applications from respective domains, we build different ``controllers'' for different scenarios. Most notably, we leverage SDNator to implement the first digital-twin-equipped central controller for additive manufacturing fleets. We show through extensive and realistic simulations that SDNator-based scheduling can (1) significantly shorten production time and improve reliability in the presence of anomalies compared to decentralized approaches, and (2) flexibly adjust and optimize production plans upon urgent requests such as producing Personal Protective Equipment during the COVID-19 pandemic.

Problem

• cyber-physical systems
• data-driven control
• extensibility
• domain-agnostic
• SDN-like control

Innovation

• data-driven control
• extensible framework
• cyber-physical systems
• digital twin
• SDN-like architecture