Скачать презентацию UC Santa Cruz Center for Information Technology Research Скачать презентацию UC Santa Cruz Center for Information Technology Research

eff0277cc7e934c2138c5722f858970d.ppt

  • Количество слайдов: 50

UC Santa Cruz Center for Information Technology Research in the Interest of Society Jim UC Santa Cruz Center for Information Technology Research in the Interest of Society Jim Demmel, Chief Scientist www. citris. berkeley. edu

Center For Information Technology Research In The Interest Of Society “Never doubt that a Center For Information Technology Research In The Interest Of Society “Never doubt that a small group of thoughtful committed ci can change the world. Indeed, it is the only thing that ever h –Margaret Mead u Major new initiative within the College of Engineering and on the Berkeley Campus u Joint with UC Davis, UC Merced, UC Santa Cruz, LBNL, LLNL u Over 90 faculty from 21 departments u Many industrial partners u Significant State and private support u CITRIS will focus on IT solutions to tough, quality-of -life related problems 2

Outline § Scientific Agenda Overview § § Hardware and Software Building Blocks § § Outline § Scientific Agenda Overview § § Hardware and Software Building Blocks § § § New personnel and facilities Affiliated research centers and activities Financial Building Blocks § § Sensor Networks, Handheld devices, Wireless Networks, Clusters Organizational Building Blocks § § § Applications, Systems, Foundations Industrial partners, funding Current grants Putting the Social into CITRIS Smart Energy – one application in detail Next steps 3

Scientific Agenda Overview Scientific Agenda Overview

Technology Invention in a Social Context: Quality of Life Impact § Energy Efficiency § Technology Invention in a Social Context: Quality of Life Impact § Energy Efficiency § Transportation Planning § Monitoring Health Care 5

Technology Invention in a Social Context: Quality of Life Impact § Education § Land Technology Invention in a Social Context: Quality of Life Impact § Education § Land Environment § Disaster Response 6

The CITRIS Model Core • Technologies Distributed Info Systems • Micro sensors/actuators • Human-Comp The CITRIS Model Core • Technologies Distributed Info Systems • Micro sensors/actuators • Human-Comp Interaction • Prototype Deployment Applications • Initially Leverage Existing Expertise on campuses ocietal-Scale Information Systems (SIS) Foundations • Reliablity • Availability • Security, • Algorithms • Social, policy issues 7

Initial CITRIS Applications (1) u Saving Energy v Smart Buildings that adjust to inhabitants Initial CITRIS Applications (1) u Saving Energy v Smart Buildings that adjust to inhabitants v Make energy deregulation work via real-time metering and pricing v Large potential savings in energy costs: for US commercial buildings l l Turning down heat, lights saves up to $55 B/year, 35 M tons C emission/year 30% of $45 B/year energy bill is from “broken systems” u Transportation Systems v Use SISs to improve the efficiency and utility of highways while v v v reducing pollution Improve carpooling efficiency using advanced scheduling Improve freeway utilization by managing traffic flows Large potential savings in commuter time, lost wages, fuel, pollution: for CA l 15 minutes/commuter/day => $15 B/year in wages l $600 M/year in trucking costs, 150 K gallons of fuel/day u Disaster Mitigation (natural and otherwise) v $100 B-$200 B loss in “Big One”, 5 K to 10 K deaths v Monitor buildings, bridges, lifeline systems to assess damage after 8 disaster

Initial CITRIS Applications (2) u Distributed Biomonitoring v Wristband biomonitors for chronic illness and Initial CITRIS Applications (2) u Distributed Biomonitoring v Wristband biomonitors for chronic illness and the elderly v Monitored remotely 24 x 7 x 365 v Emergency response and potential remote drug delivery v Cardiac Arrest l Raise out-of-hospital survival rate from 6% to 20% => save 60 K lives/year u Distributed Education v Smart Classrooms v Lifelong Learning Center for professional education v Develop electronic versions of UC Merced’s undergraduate CS curriculum u. Environmental Monitoring l CS 3 by Summer 2002 v. Monitor air quality near highways to meet Federal guidelines v. Mutual impact of urban and agricultural areas v. Monitor water shed response to climate events and land use changes 9

Societal-Scale Systems New System Architectures New Enabled Applications Diverse, Connected, Physical, Virtual, Fluid “Server” Societal-Scale Systems New System Architectures New Enabled Applications Diverse, Connected, Physical, Virtual, Fluid “Server” “Client” Massive Cluster Gigabit Ethernet Clusters Scalable, Reliable, Secure Services Information Appliances MEMS Sensors 10

Societal-Scale Information System (SIS) § Information Utility – Planetary-scale/non-stop; secure, reliable, highperformance access, even Societal-Scale Information System (SIS) § Information Utility – Planetary-scale/non-stop; secure, reliable, highperformance access, even when overloaded, down, disconnected, under repair, under attack § Smart System – Learns usage/adapts functions & interfaces § Managing Diversity – Component plug-and-play; integrate sensors / actuators, hand-held appliances, workstations, building-sized cluster supercomputers § Always Connected – Short-range wireless nets to high-bandwidth, highlatency long-haul optical backbones 11

Some SIS Design Research Problems u Sensor network level architecture v Culler, Pister, Rabaey, Some SIS Design Research Problems u Sensor network level architecture v Culler, Pister, Rabaey, Brodersen, Boser, … v How to program, synch, maintain sensor net u Service architecture for distributed systems v Katz, Joseph, Kubiatowicz, Brewer, … v How to create, peer, interface services in real time u Adaptive data management and query processing v Franklin, Hellerstein, … v How to collect, summarize, filter, index sensor data u Human centered computing v Canny, Hearst, Landay, Mankoff, Morgan, Feldman, … v How to determine and support needs of diverse users 12

Some Foundational Research Problems u How do we make SISs secure? v Tygar, Wagner, Some Foundational Research Problems u How do we make SISs secure? v Tygar, Wagner, Samuelson, … v Lightweight authentication and digital signatures v Graceful degradation after intrusion v Protecting privacy, impact of related legislation u How do we make SISs reliable? v Henzinger, Aiken, Necula, Sastry, Wagner, … v Complexity => hybrid modeling v Multi-aspect interfaces to reason about properties v Software quality => combined static/dynamic analysis u How do we make SISs available? v Patterson, Yelick, … v Repair-Centric Design v Availability modeling and benchmarking v Performance fault adaptation u What algorithms do we need? v Papadimitriou, Demmel, Jordan, … v Algorithm to design, operate and exploit data from SISs 13

Hardware and Software Building Blocks Hardware and Software Building Blocks

Experimental Testbeds in UCB EECS Soda Hall IBM Work. Pad Velo Nino Smart Dust Experimental Testbeds in UCB EECS Soda Hall IBM Work. Pad Velo Nino Smart Dust LCD Displays MC-16 Motorola Pagewriter 2000 CF 788 Smart Classrooms Audio/Video Capture Rooms Pervasive Computing Lab Co. Lab WLAN / Bluetooth GSM BTS Wearable Displays Pager H. 323 GW Network Infrastructure TCI @Home Adaptive Broadband LMDS Millennium Cluster 15 Cal. Ren/Internet 2/NGI

Pico. Radio Extending the Scope and … Pushing the Envelope Wireless node Entrance Exhibits Pico. Radio Extending the Scope and … Pushing the Envelope Wireless node Entrance Exhibits Office s Cafe 16

Smart Dust MEMS-Scale Sensors/Actuators/Communicators u Create a dynamic, ad-hoc network of power- aware sensors Smart Dust MEMS-Scale Sensors/Actuators/Communicators u Create a dynamic, ad-hoc network of power- aware sensors u Explore system design issues u Provide a platform to test Dust components u Use off the shelf components initially 17

Current One-Inch Networked Sensor Culler, Pister u 1” x 1. 5” motherboard v ATMEL Current One-Inch Networked Sensor Culler, Pister u 1” x 1. 5” motherboard v ATMEL 4 Mhz, 8 bit MCU, 512 bytes RAM, 8 K pgm flash v 900 Mhz Radio (RF Monolithics) 10 -100 ft. range v Radio Signal strength control and sensing v Base-station ready v stackable expansion connector l all ports, i 2 c, pwr, clock… u Several sensor boards v basic protoboard v tiny weather station (temp, light, hum, press) v vibrations (2 d acc, temp, light) v accelerometers v magnetometers 18

Tiny. OS Approach u Stylized programming model with extensive static information v Program = Tiny. OS Approach u Stylized programming model with extensive static information v Program = graph of TOS components v TOS component = command/event interface + behavior u Rich expression of concurrency v Events propagate across many components v Tasks provide internal concurrency u Regimented storage management u Very simplementation u For More see http: //tinyos. millennium. berkeley. edu 19

Emerging “de facto” tiny system u Feb. 01 bootcamp v 40 people v UCB, Emerging “de facto” tiny system u Feb. 01 bootcamp v 40 people v UCB, UCLA, USC, Cornell, Rutgers, Wash. , v LANL, Bosch, Accenture, Intel, crossbow u Several groups actively developing around tiny. OS on “rene” node u Concurrency framework has held up well. u Next generation(s) selected as DARPA networked embedded system tech (NEST) open platform u Smaller building blocks for ubicomp 20

Micro Flying Insect u ONR MURI/ DARPA funded u Year 3 of 5 year Micro Flying Insect u ONR MURI/ DARPA funded u Year 3 of 5 year project u Professors Dickinson, Fearing (PI), Liepmann, Majumdar, Pister, Sands, Sastry 21

Synthetic Insects (Smart Dust with Legs) Goal: Make silicon walk. • Autonomous • Articulated Synthetic Insects (Smart Dust with Legs) Goal: Make silicon walk. • Autonomous • Articulated • Size ~ 1 -10 mm • Speed ~ 1 mm/s 22

MEMS Technology Roadmap (Pisano/BSAC) 201 0 200 5 200 4 MEMS Micro Sensor Networks MEMS Technology Roadmap (Pisano/BSAC) 201 0 200 5 200 4 MEMS Micro Sensor Networks (Smart Dust) 200 2 200 3 MEMS Immunological Sensors MEMS Single Molecule Detection Systems MEMS Rotary Engine Power System MEMS “Mechanical” Micro Radios 23

Organizational Building Blocks Organizational Building Blocks

CITRIS Director Prof. Ruzena Bajcsy § Distinguished engineer, member of NAE/NIM § Senior professor CITRIS Director Prof. Ruzena Bajcsy § Distinguished engineer, member of NAE/NIM § Senior professor at UPenn, with appointments in CIS, § § § Mech. E, Medical School Established & ran major interdisciplinary research laboratory Major leadership & management experience in DC federal agencies—Assistant Director, CISE, NSF Served as Department Chair, 1986 -1990 Highly influential among leaders of CS field and national research funding circles Strong advocate for women in technical careers 25

CITRIS-Affiliated Research Activities (please Science Institute (ICSI) (5 u International Computer send contributions!) faculty, CITRIS-Affiliated Research Activities (please Science Institute (ICSI) (5 u International Computer send contributions!) faculty, 18 u u u students) studies network protocols and applications and speech and language-based human-centered computing. Millennium Project (15 faculty) is developing a powerful, networked computational test bed of nearly 1, 000 computers across campus to enable interdisciplinary research. Berkeley Sensor and Actuator Center (BSAC) (14 faculty, 100 students) is a world-leading effort specializing in microelectromechanical devices (MEMS), micro-fluidic devices, and “smart dust. ” Microfabrication Laboratory (71 faculty, 254 students) is a campus-wide resource offering sophisticated processes for fabricating micro-devices and micro-systems. Gigascale Silicon Research Center (GSRC) (23 faculty, 60 students) addresses problems in designing and testing complex, single-chip embedded systems using deep submicron technology. Berkeley Wireless Research Center (BWRC) (16 faculty, 114 26 students) is a consortium of companies and DARPA programs to support research in low-power wireless devices.

CITRIS-Affiliated Research Activities (continued) u Berkeley Information Technology and Systems (BITS) (20 faculty, 60 CITRIS-Affiliated Research Activities (continued) u Berkeley Information Technology and Systems (BITS) (20 faculty, 60 students) a new networking research center will address large emerging networking problems (EECS, ICSI, SIMS) u Berkeley Institute of Design (BID) (10 faculty) a new interdisciplinary center (EECS, ME, Haas, SIMS, IEOR, CDV, CED, Art Practice) to study the design of software, products and living spaces based on the convergence of design practices in information technology, industrial design, and architecture u Center for Image Processing and Integrated Computing (CIPIC) (8 faculty, 50 students) (UCD) focuses on data analysis, visualization, computer graphics, optimization, and electronic imaging of large-scale, multi 27 dimensional data sets.

Applications-Related Current Activities (please send contributions!) u Partners for Advanced Transit and Highways, PATH, Applications-Related Current Activities (please send contributions!) u Partners for Advanced Transit and Highways, PATH, (20 faculty, 70 students), a collaboration between UC, Caltrans, other universities, and industry to develop technology to improve transportation in California. u Berkeley Seismological Laboratory (15 faculty, 14 students) operates, collects, and studies data from a regional seismological monitoring system, providing earthquake information to state and local governments. u Pacific Earthquake Engineering Research Center, PEER ( 25 faculty, 15 students), a Berkeley-led NSF center, is a consortium of nine universities (including five UC campuses) working with industry and government to identify and reduce earthquake risks to safety and to the economy. u National Center of Excellence in Aviation Operations Research, NEXTOR (6 faculty, 12 students), a multi 28 campus center, models and analyzes complex airport

Applications-Related Current Activities (continued) u Center for the Built Environment (CBE) (19 faculty/staff) provides Applications-Related Current Activities (continued) u Center for the Built Environment (CBE) (19 faculty/staff) provides timely, unbiased information on promising new building technologies and design techniques. u Lawrence Berkeley National Laboratory (LBNL) v National Energy Research Supercomputing Center (NERSC) provides high-performance computing tools and expertise that enable computational science of scale v Environmental Energy Technologies (EET) performs research and development leading to better energy technologies and reduction of adverse energy-related environmental impacts. u Center for Environmental and Water Resources Engineering (CEWRE) (9 faculty, 45 students) (UCD) applications of advanced methods to environmental and water management problems. 29

Financial Building Blocks Financial Building Blocks

California Institutes in Science and Technology u Governor Gray Davis’ Initiative u $100 M California Institutes in Science and Technology u Governor Gray Davis’ Initiative u $100 M state funding for capital projects over 4 years--matched 2: 1 by Federal, industrial, private support u Focus on “hot” areas for 21 st Century, limited to UC campuses u Three initially funded: v UCSF/UCB/UCSC (Bioinformatics) v UCLA/UCSB (Nanotechnology) v UCSD/UCI (Information Technology) u UCB-led CITRIS proposal in 2001 -2002 State budget 31

New CITRIS Facilities Cory Hall EECS Soda Hall EECS § Cory Refurbishment (Berkeley) § New CITRIS Facilities Cory Hall EECS Soda Hall EECS § Cory Refurbishment (Berkeley) § CITRIS Building (Berkeley) § Engineering Building (Santa Cruz) § CITRIS Network (Davis, Berkeley, Merced, SC) 32

Committed Support from Industry Founding Corporate Members of CITRIS u. We have received written Committed Support from Industry Founding Corporate Members of CITRIS u. We have received written pledges to CITRIS of over $170 million from individuals and corporations committed to the CITRIS long-range vision 33

Large NSF ITR Award u $7. 5 M over 5 years u Support for Large NSF ITR Award u $7. 5 M over 5 years u Support for 30 faculty (Berkeley, Davis) for subset of CITRIS u 2 applications: v Energy (Rabaey, Pister, Arens, Sastry) v Disaster Response (Fenves, Glaser, Kanafani, Demmel) u Most SW aspects of systems, no hardware v Service architecture (Katz, Joseph) v Data/Query management (Franklin, Hellerstein) v Human Centered Computing (Canny, Hearst, Landay, Saxenian) v Data Visualization (Hamann, Max, Joy, Ma, Yoo) v Sensor Network Architecture (Culler, Pister) l (in original proposal, reduced support) u Collaboration with UC Merced u www. cs. berkeley. edu/~demmel/ITR_CITRIS 34

Commerce. Net Incubator u State-funded NGI (Next Generation Internet) incubator v http: //www. commerce. Commerce. Net Incubator u State-funded NGI (Next Generation Internet) incubator v http: //www. commerce. net u At Bancroft/Shattuck in shared CCIT space v http: //www. path. berkeley. edu/PATH/CCIT/Default. htm u Companies will incubate and collaborate with CITRIS faculty and students v Kalil, Demmel, Sastry, Teece (advisors) v http: //www. cs. berkeley. edu/~demmel/Commerce. Net u Companies chosen for closeness to CITRIS 35

WEb. S - Wireless Embedded Systems u $2. 44 M from DARPA’s Networked Embedded WEb. S - Wireless Embedded Systems u $2. 44 M from DARPA’s Networked Embedded Systems (NEST) program u Culler, Brewer, Wagner, Sastry, Pister, 13 students u Development of “rene” node and tiny. OS u Upcoming Boot Camp to program nodes 36

Other support u Long list, at least $27 M u More pending u More Other support u Long list, at least $27 M u More pending u More proposals being written 37

Putting the “Social” into CITRIS Courtesy of John Canny, Tom Kalil More input requested! Putting the “Social” into CITRIS Courtesy of John Canny, Tom Kalil More input requested!

Bringing the “social” into CITRIS u CITRIS needs to engage v Sociologists v Economists Bringing the “social” into CITRIS u CITRIS needs to engage v Sociologists v Economists v Anthropologists v Lawyers v Political scientists v Scholars of public policy v Business-school faculty v… 39

Possible roles for Social Scientists u Address risks (e. g. privacy of sensor nets) Possible roles for Social Scientists u Address risks (e. g. privacy of sensor nets) u Examine deployment issues associated with SISs v Economic, social, legal factors in rate of deployment u User-centered design (e. g. ethnography) u Suggest new application areas or themes u Broader ethical, legal, social implications of the Information Revolution u See web page for more extensive document v www. citris. berkeley. edu, click on “Kick Off” 40

Energy Efficiency Detailed Example Energy Efficiency Detailed Example

The Inelasticity of California’s Electrical Supply 800 700 $/MWh 600 500 400 300 200 The Inelasticity of California’s Electrical Supply 800 700 $/MWh 600 500 400 300 200 100 0 20000 25000 30000 MW 35000 40000 45000 Power-exchange market price for electricity versus load (California, Summer 2000) 42

How to Address the Inelasticity of the Supply u Spread demand over time (or How to Address the Inelasticity of the Supply u Spread demand over time (or reduce peak) v Make cost of energy l l visible to end-user function of load curve (e. g. hourly pricing) v “demand-response” approach u Reduce average demand (demand side) v Eliminate wasteful consumption v Improve efficiency of equipment and appliances u Improve efficiency of generation and distribution network (supply side) Enabled by Information! 43

Energy Consumption in Buildings (US 1997) End Use Space heating Space cooling Water heating Energy Consumption in Buildings (US 1997) End Use Space heating Space cooling Water heating Refrigerator/Freezer Lighting Cooking Clothes dryers Color TVs Ventilation/Furnace fans Office equipment Miscellaneous Total Residential 6. 7 1. 5 2. 7 1. 1 0. 6 0. 8 0. 4 3. 0 19. 0 (Units: quads per year = 1. 05 EJ y-1) Source: Interlaboratory Working Group, 2000 Commercial 2. 0 1. 1 0. 9 0. 6 3. 8 0. 6 1. 4 4. 9 15. 2 44

A Three-Phase Approach u Phase 1: Passive Monitoring v The availability of cheap, connected A Three-Phase Approach u Phase 1: Passive Monitoring v The availability of cheap, connected (wired or wireless) sensors makes it possible for the end-user to monitor energyusage of buildings and individual appliances and act there-on. v Primary feedback on usage v Monitor health of the system (30% inefficiency!) u Phase 2: Quasi-Active Monitoring and Control v Combining the monitoring information with instantaneous feedback on the cost of usage closes the feedback loop between end-user and supplier. u Phase 3: Active Energy-Management through Feedback and Control—Smart Buildings and Intelligent Appliances v Adding instantaneous and distributed control functionality to the sensoring and monitoring functions increases energy 45 efficiency and user comfort

Smart Buildings Dense wireless network of sensor, control, and actuator nodes • Task/ambient conditioning Smart Buildings Dense wireless network of sensor, control, and actuator nodes • Task/ambient conditioning systems allow conditioning in small, localized zones, to be individually controlled by building occupants and environmental conditions • Joined projects between BWRC/BSAC, School of Architecture (CBE), Civil Engineering, and IEOR with 46 Berkeley and Santa Cruz

A Proof-of-Concept: A six month demonstration, already underway! Leaders: Pister, Culler, Trent, Sastry, Rabaey A Proof-of-Concept: A six month demonstration, already underway! Leaders: Pister, Culler, Trent, Sastry, Rabaey u “Easy”: v Fully instrument a number of buildings on campus with networked light and temperature sensors in every room, and make the data available on a centralized web-site. u “Medium”: v Make a wireless power monitor with a standard 3 -prong feedthrough receptacle so that people can monitor power consumption of electronic devices as a function of time. v Similar device, but passively coupled to high-power wiring to monitor total power consumption through breaker boxes. This would give us a much finer granularity of power-consumption details, and let us look at clusters of rooms, floors, etc. v Fully instrument the campus power distribution system u “Hard”: v Real-time monitoring and control of hundreds of power systems on campus. Enforce compliance with load reduction. Charge/reward departments according to their use during peak 47 times.

Energy References uwww. citris. berkeley. edu, v. Click on Smart Energy u. Severin Borenstein’s Energy References uwww. citris. berkeley. edu, v. Click on Smart Energy u. Severin Borenstein’s paper on California’s electricity deregulation disaster vhaas. berkeley. edu/~borenste/CATrouble. pd f

Next Steps Next Steps

How to participate u You probably are already (in technology) u Get the big How to participate u You probably are already (in technology) u Get the big picture v Application motivation important v Participate in interdisciplinary collaborations u On-line material v www. citris. berkeley. edu v www. cs. berkeley. edu/~demmel/ITR_CITRIS v www. cs. berkeley. edu/~demmel/Commerce. Net v Other faculty pages u Workshops v Mote Boot Camp by Culler on Oct 17 l webs. cs. berkeley. edu/bootcamp. html v More being planned on applications and technology u What is the future of information technology? v Increasingly, symbiosis with other fields, impact on society 50