From OpenFlow Wiki
Packet and Circuit Network Convergence
Wide area networks are expensive to own from a service provider perspective and it is widely understood that much of this cost is in operational expenses. However, service providers such as AT&T and Verizon are obliged to own and operate two distinct networks for IP and Transport. These networks are typically planned, designed and managed by separate divisions within the same organization, leading to substantial management overhead, functionality/resource duplication, and increased Opex.
There have been may attempts to unify the control and management of packet-switched (IP) and circuit-switched (Transport) networks, but none have taken hold, mainly because such attempts have assumed that the control architecture of the networks cannot be changed. We believe that only architectural changes will enable true network convergence. We reason that if such changes allow both types of switching technologies to be controlled in a common way, it allows the network operator maximum flexibility in using the correct mix of technologies while designing and operating their networks. To that end, we propose a converged architecture and control plane based on Software Defined Networking (SDN) and OpenFlow.
IP routers today are connected over the wide-area by static circuits provisioned in the Transport network. Some propose connecting the packet-switched routers by direct point-to-point optical WDM links and eliminating the transport layer switching altogether. We don't believe optical circuit switching will (or should) be eliminated; on the contrary, we believe it offers significant advantages in the core of the network.
- First, optical switching is much more scalable; an optical circuit switch can switch much higher data rates, and consume much less power than an electronic packet switch. As a consequence, they are simpler, lower cost and more space efficient than an equivalent electronic packet switch. A useful rule of thumb - optical switches consume about 1/10th the volume, 1/10th the power and cost about 1/10th the price of an electronic packet switch of the same capacity.
- Second, IP and transport networks do not dynamically interact. But if lightpaths could dynamically created, modified and destroyed, a converged network could reap the benefits of both kinds of switching technologies - for example packet switching closer to the edge for fine grain control and statistical multiplexing benefits, and dynamic circuit switching in the core where dynamic circuits can recover faster from failures, provide guaranteed bandwidth and bandwidth-on-demand, or guaranteed low-latency, jitter free paths, all of which are very hard to provide in today’s packet-only networks
Briefly, SDN tenets can be summarized as follows: separation of data and control paths in packet networks; flow based datapath where flows (not packets) are the fundamental unit of control; a rich API called OpenFlow(OF) into the switch flow tables for programming and controlling the datapath; a logically centralized network-wide controller which in-turn provides another API for programming networking applications; and lastly, a means to provide network virtualization by slicing the network and isolating the slices, so that experimental slices can run in parallel to production slices, and backward compatibility is maintained with today’s networks.
With separation of data and control, and the treatment of packets as flows, together with the introduction of circuit-flow features in the OpenFlow protocol, a unified architecture becomes realizable for converged packet-circuit networks. OpenFlow abstracts each data-plane switch as a flow table. It allows the definition of a flow to be any combination of L2- L4 packet headers for packet flows, as well as L0-L1 circuit parameters for circuit flows. We have made draft experimental extensions to the OpenFlow protocol to support various circuit switching technologies - time-slot, wavelength and fiber.
By providing a standardized open interface to the data plane for both packet and circuit switches (the OpenFlow protocol), innovation can take place at a much faster pace than today. Network operators, vendors, researchers and 3rd party developers, can all add new functionality and services to the network by creating networking applications that run on top of the network operating system, thereby helping network services evolve more rapidly, leading to a Capex and Opex efficient infrastructure.
Experimental Extensions to OpenFlow
This document describes the requirements of an OpenFlow enabled circuit switch as well as a hybrid switch with both packet and circuit interfaces or switching fabrics. We recommend that you read the latest version of the OpenFlow Switch Specification for packet switches. This specification should be viewed as an addendum to the packet switch spec. It covers the components and basic functions of circuit switches based on switching time-slots, wavelengths or fibers.
- Addendum to OpenFlow Switch Specification, Version 1.0 (Draft v0.3)
- Addendum to OpenFlow Switch Specification, Version 0.8.9 (Draft v0.2)
NOTE: The Open Networking Foundation is now responsible for the development of the OpenFlow protocol. Proposals for extending the protocol to circuit switches should be submitted there.
We have recently demonstrated at GEC8 a converged packet-circuit network, which offers differential treatment in the circuit network to aggregated packet flows. At GEC8, we showed the ease with which OpenFlow can be used to aggregate packet flows based on a variety of criteria, and then mapped on to circuit flows. We demonstrated how circuit flow properties (guaranteed bandwidth and delay, low jitter, bandwidth-on-demand) can the be used to provide differential treatment to different types of aggregated packet flows - voice, video and web traffic. See the demo video here (unedited) (extended and edited). Demo details as well as instructions on recreating the demo, and downloading controller & application reference code can be found here
we had demonstrated a simple OpenFlow enabled Ethernet and TDM switched network using carrier-class hybrid packet/circuit switches from Ciena, at SuperComputing 2009 (SC09). Our main objectives were, to not only show unified control of different switching technologies, but also show the ease in creating a network application which took advantage of the unified API over the two switching technologies. The application relieves network congestion via Variable Bandwidth Packet Links. More details can be found in the OFC'10 paper below. See the demo video here. For controller & application reference code go here
In addition we have done a lab demonstration of unified control over packet and optical wavelength switches (WSS) with Fujitsu. A bidirectional wavelength circuit is dynamically created to transport a TCP flow. Details are in the publication section. See the demo video here.
- Saurav Das, Unified Control Architecture for Packet and Circuit Network Convergence, PhD Thesis, Stanford University, June 2012.
- Saurav Das, Guru Parulkar, Nick McKeown, Rethinking IP Core Networks, submitted for publication - please do not reference.
- Saurav Das, Guru Parulkar, Nick McKeown, SDN Based Unified Control Architecture, to be presented at IEEE Photonics Society Conference on Optical Networks and Systems, September 2012.
- Saurav Das, Guru Parulkar, Nick McKeown, Why OpenFlow/SDN Can Succeed Where GMPLS Failed, European Conference on Optical Communications (ECOC), September 2012 (Presentation).
- Saurav Das, Yiannis Yiakoumis, Guru Parulkar, Preeti Singh, Dan Getachew, Premal Dinesh Desai, Nick McKeown, Application-Aware Aggregation and Traffic Engineering in a Converged Packet-Circuit Network, OFC/NFOEC, March 2011. (Presentation)
- Saurav Das, Guru Parulkar, Preeti Singh, Daniel Getachew, Lyndon Ong, Nick McKeown, Packet and Circuit Network Convergence with OpenFlow, Optical Fiber Conference (OFC/NFOEC'10), March 2010. (Presentation)
- Vinesh Gudla, Saurav Das, Anujit Shastri, Guru Parulkar, Shinji Yamashita, Leonid Kazovsky, Nick McKeown, Experimental Demonstration of OpenFlow Control of Packet and Circuit Switches, Optical Fiber Conference (OFC/NFOEC'10), March 2010. (Presentation)
- Saurav Das, Guru Parulkar, Nick McKeown, Unifying Packet and Circuit Switched Networks, Below IP Networking workshop in conjunction with Globecom'09, November 2009. (Presentation)
- OpenFlow Tutorial, at OFC/NFOEC, March 2012
- SDN in Carrier Networks, presented to Broadcom Corporation, October 2011.
- Virtualizing the Transport Network: Why it matters and how OpenFlow can help, OFELIA Workshop at European Conference on Optical Communications(ECOC), September 2011.
- Software Defined Networks, presented to the Optical Internetworking Forum (OIF), July 2011.
- pac.c: A Unified Control Architecture for Packet and Circuit Networks, PhD defense presentation, June 2011. (rough transcript)
- OpenFlow in Service Provider Networks, presented to AT&T Labs, October 2010.
- pac.c, presented to Ciena India, April 2010.
- Unifying Packet & Circuit Networks with OpenFlow , presented to Huawei Technologies, February 2010.
- OpenFlow: Converging Packet and Circuit Networks, presented at Stanford Photonics Research Center (SPRC) Annual Symposium, September 2009.
- Simple Unified Control for Packet and Circuit Networks, presented at IEEE Photonics Society's workshop on Future Global Networks, June 2009.
- Simple Unified Control for Packet and Circuit Networks, presented at NFOEC workshop on Optical and Packet Control Planes: Convergence or Divergence?, March 2009
- Other talks in smaller settings have been made to NEC, Fujitsu, Infinera, Ericsson, NSN, CPqD, Vello, Cisco, Deutsche Telekom, ESnet, and Google
- Saurav Das
- Yiannis Yiakoumis
- Vinesh Gudla
[ feel free to add references to your work - please use the same template ]
- Lei Liu, Takehiro Tsuritani, Itsuro Morita, Hongxiang Guo, and Jian Wu. Experimental Validation and Performance Evaluation of OpenFlow-based Wavelength Path Control in Transparent Optical Networks, Optics Express, vol. 19, no. 27, Dec. 2011.