Transcript Slide

FINDing a GENI in a CCCastle
Reinventing the Internet (and More) – January 2007
Ellen W. Zegura
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
Footer Information
2
Outline
• A short story
• What is GENI?
– A research program (see FIND)
– A “facility” for experimenting at scale
• CCC and other acronyms
• Opportunities
Footer Information
3
Once upon a time…
•There was a research project
ARPANET Logical Map, March 1977
Footer Information
4
That grew up to be the Internet.
Footer Information
5
Times changed, and it kept up…
Kazaa VoIP Mail
Applications
Everything
News
on Video
WEB Audio
IM
U Tube
HTTP
Transport protocols
TCP
SIP
UDP
RTP
IP
Ethernet 802.11
Power linesIPATM
on Optical
Satellite Bluetooth
everything
Modified John Doyle Slide
Footer Information
6
And everyone (and thing) relied on it.
User
User
Communications
Games
Photography
Inventory/Sales
tracking
Entertainment Systems
Health/Medical
Home Computer
Home Appliances
Banking
and
Commerce
User
Surveillance and Security
(at home, work, or in public)
PDA
Telephone
Car
Building Automation
User
Footer Information
7
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)
Footer Information
8
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?
Footer Information
9
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.
Footer Information
10
Along came the idea of a Future Internet
Applications
Kazaa VoIP Mail
News
Video
Audio
IM
U Tube
Future Internet (FI)
E2E Networking and Distributed Systems
Ethernet 802.11
Power lines ATM
Optical
Satellite Bluetooth
Link Technologies
Modified John Doyle Slide
Footer Information
11
Outline
• A short story
• What is GENI?
– A research program (see FIND)
– A facility/testbed for experimenting at scale
• CCC and other acronyms
• Opportunities
Footer Information
12
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
Footer Information
13
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
Footer Information
14
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
Footer Information
15
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
Footer Information
16
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
Footer Information
17
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
Footer Information
18
Snapshot of research challenges
Security and
Robustness
Pervasive
Computing w
Mobility
Bridging
Physical and
Cyber space
Realize
Potential of
OptoElectronics
GENI
Capability:
Information
Access with
High
Availability
& Trust
Footer Information
Capability:
Seamless
information
access any
where and any
time
Capability:
Capability:
Access
information
about physical
world in real
time
Access to
Bandwidth-onDemand with
low latency &
guarantees
19
Outline
• A short story
• What is GENI?
– A research program (see FIND)
– A “facility” for experimenting at scale
• CCC and other acronyms
• Opportunities
Footer Information
20
GENI facility: motivation
Maturity
Need for Large experimental
facility/infrastructure
Shared
Deployed
Infrastructure
This chasm represents a major
barrier to impact real world
Small Scale
Testbeds
Research
Prototypes
Foundations
Research
Funded by current programs
Time
Footer Information
21
Link between research and facility
• Goal: Seamless conception-to-deployment
process
Deployment
Analysis
Simulation / Emulation
(models)
Experiment At Scale
(code)
(Facility)
(results)
(measurements)
Footer Information
22
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
Footer Information
23
Facility design: key concepts
Sensor Network
Edge Site
Mobile Wireless Network
Federated Facilities
Slicing, Virtualization, Programmability
Footer Information
24
Scope
Applications
Dist Sys Y
Dist Sys Z
E2E Architectures and Components
Arch Comp
X
Arch Comp
Y
Service C
Dist Sys X
Arch C
Distributed Systems and Services
Applications
Service B
Applications
Arch B
Arch A
Service A
Applications
Arch Comp
Z
GENI Facility Substrate: Sharable Physical Infrastructure
Backbones
Campus/Access
Backbone
Edge Networks
Combination of All optical transport and
Packet service networks
Numerous Wired, Mobile Wireless, and Sensor Networks
Footer Information
Campus/Access
Backbone
Edge Networks
25
Details of the Facility
Sensor Network
backbone wavelength
backbone switch
Customizable
Router
Internet
Edge Site
Wireless Subnet
Footer Information
26
Outline
• A short story
• What is GENI?
– A research program (see FIND)
– A “facility” for experimenting at scale
• CCC and other acronyms
• Opportunities
Footer Information
27
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)
Footer Information
28
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
Footer Information
29
Opportunities
• Researchers
– Contribute to research vision and agenda
– Engage in peer-to-peer collaborations and
conversations about experiments
• Researchers+Government
• Industry
Footer Information
30
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
Footer Information
31
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
Footer Information
32
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.
Footer Information
33
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
Footer Information
34
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
Footer Information
35
Backup slides
Footer Information
36
Fitting parts together
Infrastructure services
RDS PS
CS
MS
LS
. . . and others . . .
Slice Manager
Core
Resource Controller
Auditing Archive
node
control
sensor
data
CM
CM
CM
Node substrate
Node substrate
Node substrate
Components
Footer Information
37
Another Important Trend: Networking
the Physical World
New Machines
New Environments
New Applications
New Scale
Billion to trillion devices!
Footer Information
38
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
Footer Information
39
Photonics Integration Trends
Source: Vinod Khosla
Source: Dan Blumenthal
10ps Delay using deep-etched waveguide
Dual SGDBR Signal
Booster SOAs
Label Rewrite EAM
SGDBR
Flared Input Pre- 1mm MZI SOAs
Input Signal Blanking EAM Tunable Laser
amp SOAs
Almost Free OEO!!
1.6 Tbps on a chip: 40 x 40
Packet Switching
Buffering in Optical Domain
High capacity “dynamic” optical networks a certainty
Footer Information
40
Future Internet and Dynamic Optical
Networks
Circuit and Packet
Service Layer
All Optical
Transport Core
How can Future Internet exploit an optical core that can
provide “bandwidth on demand” dynamically with low
latency and guarantees?
Footer Information
41
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
Footer Information
42