1. FINDing a GENI in a CCCastle Reinventing the Internet (and More) – January 2007 Ellen W. Zegura

2. Footer Information 2 My role in GENI 1.Member of GENI Research Coordination Working Group 2.Member of CRA GENI Community Advisory Board (interim body) 3.Member of CCC Interim Council (interim body) Thanks to Dave Clark, Peter Freeman, Guru Parulkar, many others for raw material

3. Footer Information 3 Outline A short story What is GENI? –A research program (see FIND) –A “facility” for experimenting at scale CCC and other acronyms Opportunities

4. Footer Information 4 Once upon a time… There was a research project ARPANET Logical Map, March 1977

5. Footer Information 5 That grew up to be the Internet.

6. Footer Information 6 Times changed, and it kept up… IP KazaaVoIPMail News VideoAudioIMU Tube Applications TCPSIPUDPRTP Transport protocols Ethernet 802.11SatelliteOpticalPower linesBluetoothATM IP on everything HTTP Everything on WEB Modified John Doyle Slide

7. Footer Information 7 And everyone (and thing) relied on it. User Home Computer PDA Telephone Entertainment Systems Car Surveillance and Security (at home, work, or in public) Building Automation Banking and Commerce Photography Home Appliances Games Inventory/Sales tracking Health/Medical Communications User

8. Footer Information 8 Then one day, People realized it wasn’t working so well –Lots of spam –Phishing attacks to steal identity and more –Too hard to set up my home network –Can’t tell why it isn’t working –Would you have tele-surgery over the Internet? –(Why) is Google building their own network? And there were things it couldn’t do –“Can you print my dream?” (4 year old Bethany)

9. Footer Information 9 Scientists were heroic (and stymied) What is the Internet structure? How does it change and why? How robust is the Internet? What happens during a failure event? What are the properties of Internet paths? How do attacks propagate? What are users doing?

10. Footer Information 10 Even experts had to admit: “… in the thirty-odd years since its invention, new uses and abuses, …, are pushing the Internet into realms that its original design neither anticipated nor easily accommodates.” “Freezing forevermore the current architecture would be bad enough, but in fact the situation is deteriorating. These architectural barnacles—unsightly outcroppings that have affixed themselves to an unmoving architecture— may serve a valuable short-term purpose, but significantly impair the long-term flexibility, reliability, security, and manageability of the Internet. ” Overcoming Barriers to Disruptive Innovation in Networking, NSF Workshop Report, 2005.

11. Footer Information 11 Along came the idea of a Future Internet KazaaVoIPMail News VideoAudioIMU Tube Applications Ethernet 802.11SatelliteOpticalPower linesBluetoothATM Future Internet (FI) E2E Networking and Distributed Systems Modified John Doyle Slide Link Technologies

12. Footer Information 12 Outline A short story What is GENI? –A research program (see FIND) –A facility/testbed for experimenting at scale CCC and other acronyms Opportunities

13. Footer Information 13 What is GENI? Global Environment for Networking Innovations Two parts: –The GENI Research Program, which will develop and evaluate ideas for the Future Internet –The GENI Facility, which will provide the instrument for at-scale experimentation

14. Footer Information 14 GENI research program FIND: U.S. National Science Foundation program to fund research on Future Internet Design (focus on architecture) Key areas of concern: –Security and robustness –Mobility of hosts and networks –Control and management –Addressing, naming and (inter-domain) routing –End-to-end principle vs in-network processing

15. Footer Information 15 Security trends Increasing vulnerabilities, viruses, attacks, worms … –20 new vulnerabilities reported every day –120,000 known viruses and worms -- 50 new ones per day –Large scale attacks doubling every year Increasing economic cost –Viruses alone => $60B –Worldwide => $105B+ Some ISPs have more than 90% traffic that is spam Identity thefts has emerged as a significant and serious threat And more … Source: Spafford Talk

16. Footer Information 16 In the Future Internet Information disclosure control and integrity –Important and well understood High availability -- suitable for even mission critical scenarios Balance of privacy and accountability Usable security for a range of users Context aware –Different parts of the world have different requirements Appropriate for emerging devices and networks –Mobile wireless and sensor networks, sensors, PDAs, … Need coherent and comprehensive design

17. Footer Information 17 Mobile wireless trends 2B+ cell phones 400M+ cell phones with Internet capability -- rising rapidly New data devices (blackberry, PDA, iPod) and services 240M vehicles on the road -- will soon get network connectivity with mobility Mobile computing and embedded devices to dominate future computing and communication Closed vertically integrated networks and services

18. Footer Information 18 In the Future Internet Seamless integration of networks –Cellular WAN, wireless PAN, LAN and MANs, ad hoc mesh Build on current and new radio technologies –4G, WiMax,.11n, MIMO, cognitive radios, and more to come New protocol capabilities –Cross-layer support, spectrum coordination, discovery, QoS, multi- hop Autonomic, self-* Secured and privacy protecting –Over otherwise shared wireless medium Accelerate new services and ability to deploy them –location-aware, multimedia, dynamic communities

19. Footer Information 19 Snapshot of research challenges Security and Robustness Capability: Information Access with High Availability & Trust Pervasive Computing w Mobility Capability: Seamless information access any where and any time Bridging Physical and Cyber space Capability: Access information about physical world in real time Realize Potential of Opto- Electronics Capability: Access to Bandwidth-on- Demand with low latency & guarantees GENI

20. Footer Information 20 Outline A short story What is GENI? –A research program (see FIND) –A “facility” for experimenting at scale CCC and other acronyms Opportunities

21. Footer Information 21 GENI facility: motivation Time Maturity Foundations Research Research Prototypes Small Scale Testbeds Funded by current programs Shared Deployed Infrastructure Need for Large experimental facility/infrastructure This chasm represents a major barrier to impact real world

22. Footer Information 22 Link between research and facility Goal: Seamless conception-to-deployment process AnalysisSimulation / Emulation Experiment At Scale (Facility) Deployment (models)(code) (results) (measurements)

23. Footer Information 23 Facility goals Enable exploration of new network architectures, mechanisms, and distributed system capabilities A shared facility that allows: –Concurrent exploration of a broad range of experimental networks and distributed services –Interconnection among experimental networks & the commodity Internet –Users and applications able to “opt-in” –Observation, measurement, and recording of outcomes Help develop stronger scientific base

24. Footer Information 24 Facility design: key concepts Slicing, Virtualization, Programmability Mobile Wireless Network Edge Site Sensor Network Federated Facilities

25. Footer Information 25 Scope Applications GENI Facility Substrate: Sharable Physical Infrastructure Backbones Edge Networks Numerous Wired, Mobile Wireless, and Sensor Networks Combination of All optical transport and Packet service networks Campus/Access Backbone E2E Architectures and Components Arch A Arch B Arch C Arch Comp Y Arch Comp X Arch Comp Z Service A Service B Service C Dist Sys YDist Sys XDist Sys Z Distributed Systems and Services

26. Footer Information 26 Details of the Facility Internet backbone wavelength backbone switch Sensor Network Edge Site Wireless Subnet Customizable Router

27. Footer Information 27 Outline A short story What is GENI? –A research program (see FIND) –A “facility” for experimenting at scale CCC and other acronyms Opportunities

28. Footer Information 28 What is the CCC? Computing Community Consortium –Solicited by US NSF, “calling for the computing research community to unite in the establishment of a Computing Community Consortium” –Serve as “a community proxy responsible for facilitating the conceptualization and design of promising infrastructure-intensive projects identified by the computing research community to address compelling scientific ‘grand challenges’ in computing.” –Initial responsibility would be “guiding the design of the Global Environment for Network Innovations (GENI) … on behalf of the research community, ensuring broad community participation in the GENI design process and identifying necessary pre-construction development activities.” Award made to Computing Research Association (CRA)

29. Footer Information 29 And eventually there will be CCC Council –Interim group appointed November 2006 –Nominations for members due late Jan 2007 GENI Science Council (GSC) –Interim group appointed October 2006 –Nominations for members in November 2006 –Initial permanent group to be named soon GENI Project Office (GPO) –Solicitation in fall 2007 –Award due in spring 2007

30. Footer Information 30 Opportunities Researchers –Contribute to research vision and agenda –Engage in peer-to-peer collaborations and conversations about experiments Researchers+Government Industry

31. Footer Information 31 International Partnerships Important Help define facility scope Build national partner facilities to complement US GENI facilities and capabilities Share facilities with researchers in all partner countries Encourage collaborative international research projects and experiments

32. Footer Information 32 Industry Partnerships Important Help to refine R&D objectives Become a member in the GENI consortium Provide leading-edge technology for use in GENI Contract (or subcontract) to build the facility Conduct collaborative research with universities Benefits to partnering –Accelerate the transfer of academic research results to commercial products –Enable a national/international “proving ground” for new technology

33. Footer Information 33 Conclusions The future of the Internet is too important to be left to chance or random developments. True experimentation is needed. The GENI project intends to provide the basic architectures, technologies, and policies that will be needed for successful networking in the 2010-2020 time frame.

34. Footer Information 34 More Information Visit the GENI web site at: http://www.nsf.gov/cise/geni/ Visit the CISE Web site at: http://www.nsf.gov/dir/index.jsp?org=CISE Visit the CRA CCC web site at: http://www.cra.org/ccc

35. Footer Information 35 Acknowledgments The GENI Planning Group –Peterson, Anderson, Blumenthal, Casey, Clark, Estrin, Evans, McKeown, Raychaudhuri, Reiter, Rexford, Shenker, Vahdat, Wroclawski The GENI Working Groups –Research Coordination –Facility Architecture –Backbone –Mobile wireless sensor networks –Distributed services Planning grant workshops participants CISE GENI Team And others

36. Footer Information 36 Backup slides

37. Footer Information 37 Fitting parts together CM Node substrate CM Node substrate Components CM Node substrate Resource ControllerAuditing Archive Slice Manager RDSCSPSLSMS Infrastructure services... and others... Core node control sensor data

38. Footer Information 38 Another Important Trend: Networking the Physical World New Machines New Environments New Applications New Scale Billion to trillion devices!

39. Footer Information 39 Sensor Networking in Future Internet Sensor networks challenge Internet architecture –host-to-host communication, addressing, routing, end-to-end principle, … Sensor networks require Aggregate communication –dissemination, data collection, aggregation Communication with data/logical services, not just devices –Data centric as opposed to host centric Autonomic –Self-configuration, self-management, self-* Sensor networks constraints –Limited resources, intermittent connectivity, mobility, in-network proc

40. Footer Information 40 Photonics Integration Trends Source: Vinod Khosla Almost Free OEO!! 1.6 Tbps on a chip: 40 x 40 Input Signal Blanking EAM 10ps Delay using deep-etched waveguide SGDBR Tunable Laser Flared Input Pre- amp SOAs Dual SGDBR Signal Booster SOAs 1mm MZI SOAs Label Rewrite EAM Packet Switching Buffering in Optical Domain Source: Dan Blumenthal High capacity “dynamic” optical networks a certainty

41. Footer Information 41 Future Internet and Dynamic Optical Networks All Optical Transport Core Circuit and Packet Service Layer How can Future Internet exploit an optical core that can provide “bandwidth on demand” dynamically with low latency and guarantees?

42. Footer Information 42 In-Network Processing Trends Middle boxes: NAT, firewall, IDS, etc.. WEB caching and content distribution networks Network based services: computing, storage Internet’s end-to-end principle (a defining attribute) challenged and revisited