Project Pronto is building and deploying a beta-production end-to-end 5G connected edge cloud leveraging a fully programmable network empowered by unprecedented visibility, verification and closed-loop control capabilities to fuel innovation while helping to secure future network infrastructure. Universities are executing a research agenda enabled by deep programming methods to explore and create verification and closed-loop control.
ONF’s Aether (an open source Private 4G/5G Connected-Edge-Cloud as a Service platform) is being used as the foundation for the Pronto research. The research will be iteratively upstreamed back into the Aether platform to help move the industry towards robust and secure programmable networks. Universities are executing a research agenda enabled by deep programming methods to explore and create verification and closed-loop control.
Stanford University, Cornell University, Princeton University and the Open Networking Foundation, are jointly collaborating on Pronto, which is in part funded by a $30M grant from DARPA.
Network Becoming a Distributed Computing Platform
With the advent of SDN including programmable forwarding and P4, the network has become a deeply programmable platform that can be controlled by network owners to suit their needs. It is now possible to program the control plane and the forwarding pipeline end-to-end on servers, NICs, switches and middle-boxes. With this, we can now reimagine the network as a dynamic distributed computing platform.
With the network now programmable end-to-end and top-to-bottom, software now defines network behavior, control moves from equipment vendors to network owners, and network functions can be placed where they are best suited which may be in hardware, on device software or on the central SDN controller
With programmability and increasing adoption of open source, the operator can take control of their own destiny as they start to leverage the network as a distributed computing platform, and the network becomes an asset for innovation and competitive advantage. Pronto aims to support and further this goal by leveraging network programmability to enable deep and wide network visibility, verification, and closed-loop control, giving programmers tools to build and dynamically deploy customized network functionality in a secure and reliable manner.
A P4 programmable forwarding path now allows for packet formats and forwarding treatments to be customized to carry information about their provenance (the path they took, the forwarding rules they followed, the delays they encountered, etc.). This is already possible with Inband Network Telemetry (INT).
Couple deep and comprehensive visibility with an understanding of the network state (the contents of forwarding tables, address translation, overlay tunnels, and topology), and it becomes possible to verify that the network’s behavior matches the specified behavior and expected result. If packets, flows, state, or code are found to deviate from what is expected, the network can be automatically repaired and re-verified to ensure the problem is resolved.
Networks that provide complete transparency, visibility, and verifiability become capable of being optimized and secured through programmatic real-time closed loop control.
By defining specific acceptable tolerances for specific settings, measuring for compliance and automatically adapting to deviations, a closed loop network can be created that dynamically and automatically responds to environmental changes.
We can apply closed-loop control for a variety of use cases including resource optimization (traffic engineering, RAN slicing), verification (network paths), security (DDoS mitigation), and others.
Focus on 5G + Edge Cloud
5G and Edge Cloud represent the two most important impending build-outs for networking infrastructure, so Project Pronto will also deliver a fully functional and operational end-to-end private 5G connected edge cloud interconnecting our respective campuses as well as our partner organizations.
We expect our private 5G connected edge cloud will be a platform for others in academia and industry to replicate and build on.
In so doing, Pronto will help to secure future network infrastructure., leveraging an open source foundation.
Aether Used as Open Source Platform for Pronto Research
Since 5G is today’s future network, it only makes sense to focus Pronto’s efforts on a 5G aligned solution.
To this end, ONF’s Aether 5G Edge Cloud Platform will be used as the foundational platform for the Pronto project. Aether provides deep P4 programmability throughout the network in a solution that delivers an end-to-end 5G solution with edge cloud capabilities.
Aether is also open source, making it an ideal platform to help foster research.
Aether is an open source platform enabling mobile connectivity with connected edge cloud all managed from the public cloud. Aether can support multi-site footprints as an elastic and scalable cloud service, simplifying deployment. Management is centralized in the cloud providing enterprise-wide visibility and a centralized dashboard for management and operation of the infrastructure.
Pronto research will build upon the Aether platform, extending the programmability and adding fine grained measurement, verification and closed-loop control capabilities.
The Pronto research results will be iteratively incorporated back into Aether, both enhancing the platform while providing a faster route for commercial adoption for research results.
This synergistic relationship represents a unique collaboration and a transformational opportunity to more rapidly advance research into commercial adoption.
Aether Beta Deployment
As part of Pronto, DARPA is also funding deployment of a modest Aether network to be deployed between Stanford, Cornell, Princeton and ONF to be used as both a proving ground and a Continuous Integration/Continuous Deployment (CI/CD) development platform for Pronto.
Pronto Leadership Team
(L-R): Oguz Sunay, Jennifer Rexford, Larry Peterson, Nate Foster, Guru Parulkar, Nick McKeown
END-TO-END FULLY PROGRAMMABLE NETWORK