Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

The Growing Interdependence of the Internet and Climate Change


Published on

Distinguished Lecture
Scientific Computing and Imaging (SCI) Institute
University of Utah
Title: The Growing Interdependence of the Internet and Climate Change
Salt Lake City, UT

Published in: Education
  • Be the first to comment

The Growing Interdependence of the Internet and Climate Change

  1. 1. ―The Growing Interdependence of the Internet and Climate Change‖ Scientific Computing and Imaging (SCI) Institute Distinguished Lecture University of Utah April 30, 2010 Dr. Larry Smarr Director, California Institute for Telecommunications and Information Technology Harry E. Gruber Professor, Dept. of Computer Science and Engineering Jacobs School of Engineering, UCSD Twitter: lsmarr
  2. 2. Abstract Greenhouse gas (GHG) emissions continue their relentless rise, even though the global CO2 level is already considerably higher than it has been on earth for over two million years. The Information and Communication Technology (ICT) industry currently produces ~2-3 % of global GHG emissions and will nearly triple, in a business as usual scenario, from 2002 to 2020. On the other hand, the Climate Group estimates that transformative application of ICT to electricity grids, logistic chains, intelligent transportation and building infrastructure, and other social systems can reduce global GHG emissions by ~15%, five times ICT's own footprint! I will discuss three campus testbeds for exploring these complex tradeoffs. The first testbed is the NSF-funded GreenLight Project deployed at UCSD, which creates an instrumented data center that can guide users who wish to lower the energy cost of computation and storage. The second testbed is the campus itself, in which the move to centralized computing and storage can greatly reduce the GHG emissions of the current distributed set of clusters and storage. The third testbed is the global set of dedicated optical networks (operating at 10,000 Mbps), coupled to large tiled wall OptIPortals (with fractions of a billion pixels) and high definition (2 Mpixel/frame) or digital cinema (8Mpixel/frame), to create next generation "telepresence" systems for "sewing remote rooms together" as a way to reduce the need for transportation for national or global collaboration.
  3. 3. ICT Could be a Key Factor in Reducing the Rate of Climate Change Applications of ICT could enable emissions reductions of 15% of business-as-usual emissions. But it must keep its own growing footprint in check and overcome a number of hurdles if it expects to deliver on this potential.
  4. 4. Rapid Increase in the Greenhouse Gas CO2 Since Industrial Era Began Source: David JC MacKay, Sustainable Energy Without the Hot Air (2009) 388 ppm in 2010 Medieval Little Warm Ice Age 290 ppm in 1900 Period
  5. 5. Global Average Temperature Per Decade Over the Last 160 Years
  6. 6. Atmospheric CO2 Levels for 800,000 Years and Projections for the 21st Century Source: U.S. Global Change (MIT Study) Research Program Report (2009) (Shell Study) /us-impacts/download-the-report
  7. 7. Global Climatic Disruption Example: The Arctic Sea Ice ―A pervasive cooling of the Arctic in progress 2000 years ago continued through the Middle Ages and into the Little Ice Age. It was reversed during the 20th century, with four of the five warmest decades of our 2000-year-long reconstruction occurring between 1950 and 2000. The most recent 10-year interval (1999–2008) was the warmest of the past 200 decades.‖ Mean of all records transformed to summer temperature anomaly relative to the 1961–1990 reference period, with first-order linear trend for all records through 1900 with 2 standard deviations Science v. 325 pp 1236 (September 4, 2009)
  8. 8. Arctic Summer Ice Melting Accelerating Relative to IPCC 2007 Predictions Source:
  9. 9. Global Climatic Disruption Early Signs: Area of Arctic Summer Ice is Rapidly Decreasing "We are almost out of multiyear sea ice in the northern hemisphere-- I've never seen anything like this in my 30 years of working in the high Arctic.‖ --David Barber, Canada's Research Chair in Arctic System Science at the University of Manitoba October 29, 2009 sc_nm/us_climate_canada_arctic_1
  10. 10. Summer Arctic Sea Ice Volume Shows Even More Extreme Melting—Ice Free by 2015? Source: Wieslaw Maslowski Naval Postgraduate School, AAAS Talk 2010
  11. 11. The Latest Science on Global Climatic Disruption An Update to the 2007 IPCC Report
  12. 12. The Global ICT Carbon Footprint is Significant and Growing at 6% Annually! the assumptions behind the growth in emissions expected in 2020: • takes into account likely efficient technology developments that affect the power consumption of products and services • and their expected penetration in the market in 2020
  13. 13. Reduction of ICT Emissions is a Global Challenge – U.S. and Canada are Small Sources U.S. plus Canada Percentage Falls From 25% to 14% of Global ICT Emissions by 2020
  14. 14. The Global ICT Carbon Footprint by Subsector The Number of PCs (Desktops and Laptops) Globally is Expected to Increase from 592 Million in 2002 to More Than Four Billion in 2020 PCs Are Biggest Data Centers Are Problem Rapidly Improving
  15. 15. Making University Campuses Living Laboratories for the Greener Future
  16. 16. Increasing Laptop Energy Efficiency: Putting Machines To Sleep Transparently Rajesh Gupta, UCSD CSE; Calit2 Network interface Secondary Network processor interface Management software Low power domain Main processor, Peripheral RAM, etc IBM X60 Power Consumption Laptop Power Consumption (Watts) 20 16W 18 (4.1 Hrs) Somniloquy 16 11.05W Enables Servers 14 (5.9 Hrs) to Enter and Exit Sleep 12 10 While Maintaining 8 Their Network and 6 Application Level 0.74W 1.04W 4 (88 Hrs) (63 Hrs) Presence 2 0 Sleep (S3) Somniloquy Baseline (Low 16 Normal Power)
  17. 17. Desktops: Power Savings with SleepServer: A Networked Server-Based Energy Saving System State Power Normal Idle State 102.1W Lowest CPU Frequency 97.4W Disable Multiple Cores 93.1W Dell OptiPlex 745 “Base Power” 93.1W Desktop PC Sleep state (ACPI State S3) 2.3W Using SleepServers – Power Drops from 102W to < 2.5W – Assuming a 45 Hour Work Week – 620kWh Saved per Year, for Each PC – Additional Application Latency: 3s - 10s Across Applications – Not Significant as a Percentage of Resulting Session 17 Source: Rajesh Gupta, UCSD CSE, Calit2
  18. 18. PC: 68% Energy Saving Since SSR Deployment kW-Hours:488.77 kW-H Averge Watts:55.80 W Energy costs:$63.54 Estimated Energy Savings with Sleep Server: 32.62% Estimated Cost Savings with Sleep Server: $28.4
  19. 19. ―Blueprint for the Digital University‖--Report of the UCSD Research Cyberinfrastructure Design Team • Focus on Greener Data Storage and Data Curation – These Become the Centralized Components – Other Common Elements ―Plug In‖ April 24, 2009
  20. 20. Campus Preparations Needed to Accept CENIC CalREN Handoff to Campus Source: Jim Dolgonas, CENIC
  21. 21. Current UCSD Prototype Optical Core: Bridging End-Users to CENIC L1, L2, L3 Services Quartzite Communications To 10GigE cluster node interfaces Core Year 3 Enpoints: Quartzite Wavelength >= 60 endpoints at 10 GigE Core Selective ..... Switch >= 32 Packet switched Lucent To 10GigE cluster node interfaces and >= 32 Switched wavelengths other switches To cluster nodes ..... >= 300 Connected endpoints Glimmerglass To cluster nodes ..... Production GigE Switch with OOO Dual 10GigE Upliks Switch To cluster nodes Approximately 0.5 TBit/s 32 10GigE ..... Arrive at the ―Optical‖ GigE Switch with Force10 Dual 10GigE Upliks Center of Campus. ... GigE Switch with Switching is a Hybrid of: To Packet Switch CalREN-HPR Research Dual 10GigE Upliks Packet, Lambda, Circuit -- other nodes Cloud GigE OOO and Packet Switches 10GigE Campus Research 4 GigE 4 pair fiber Cloud Juniper T320 Source: Phil Papadopoulos, SDSC/Calit2 (Quartzite PI, OptIPuter co-PI) Quartzite Network MRI #CNS-0421555; OptIPuter #ANI-0225642
  22. 22. UCSD Campus Investment in Fiber Enables Consolidation of Energy Efficient Computing & Storage CENIC, NLR, I2DCN Nx 10Gbe Gordon – HPC System Cluster Condo DataOasis (Central) Storage Triton – Petadata Analysis Scientific Instruments Digital Data Campus Lab OptIPortal Collections Cluster Tile Display Wall Source: Philip Papadopoulos, SDSC, UCSD
  23. 23. The GreenLight Project: Instrumenting the Energy Cost of Computational Science • Focus on 5 Communities with At-Scale Computing Needs: – Metagenomics – Ocean Observing – Microscopy – Bioinformatics – Digital Media • Measure, Monitor, & Web Publish Real-Time Sensor Outputs – Via Service-oriented Architectures – Allow Researchers Anywhere To Study Computing Energy Cost – Enable Scientists To Explore Tactics For Maximizing Work/Watt • Develop Middleware that Automates Optimal Choice of Compute/RAM Power Strategies for Desired Greenness • Partnering With Minority-Serving Institutions Cyberinfrastructure Empowerment Coalition Source: Tom DeFanti, Calit2; GreenLight PI
  24. 24. GreenLight’s Data is Available Remotely: Virtual Version in Calit2 StarCAVE 30 HD Connected at Projectors! 50 Gb/s to Quartzite Source: Tom DeFanti, Greg Dawe, Jurgen Schulze, Calit2
  25. 25. Research Needed on How to Deploy a Green CI MRI • Computer Architecture – Rajesh Gupta/CSE • Software Architecture, Clouds – Amin Vahdat, Ingolf Kruger/CSE • CineGrid Exchange – Tom DeFanti/Calit2 • Visualization – Falko Kuster/Structural Engineering • Power and Thermal Management – Tajana Rosing/CSE • Analyzing Power Consumption Data – Jim Hollan/Cog Sci • Direct DC Datacenters – Tom Defanti, Greg Hidley
  26. 26. New Techniques for Dynamic Power and Thermal Management to Reduce Energy Requirements NSF Project Greenlight • Green Cyberinfrastructure in Energy-Efficient Modular Facilities • Closed-Loop Power &Thermal Management Dynamic Power Management (DPM) Dynamic Thermal Management (DTM) • Optimal DPM for a Class of Workloads • Workload Scheduling: • Machine Learning to Adapt • Machine learning for Dynamic • Select Among Specialized Policies Adaptation to get Best Temporal and • Use Sensors and Spatial Profiles with Closed-Loop Performance Counters to Monitor Sensing • Multitasking/Within Task Adaptation • Proactive Thermal Management of Voltage and Frequency • Reduces Thermal Hot Spots by Average • Measured Energy Savings of 60% with No Performance Overhead Up to 70% per Device CNS System Energy Efficiency Lab ( Prof. Tajana Šimunić Rosing, CSE, UCSD
  27. 27. Application of ICT Can Lead to a 5-Fold Greater Decrease in GHGs Than its Own Carbon Footprint While the sector plans to significantly step up the energy efficiency of its products and services, ICT’s largest influence will be by enabling energy efficiencies in other sectors, an opportunity that could deliver carbon savings five times larger than the total emissions from the entire ICT sector in 2020. --Smart 2020 Report Major Opportunities for the United States* – Smart Electrical Grids – Smart Transportation Systems – Smart Buildings – Virtual Meetings * Smart 2020 United States Report Addendum
  28. 28. Real-Time Monitoring of Building Energy Usage: UCSD Has 34 Buildings On-Line
  29. 29. Comparision Between UCSD Buildings: kW/sqFt Year Since 1/1/09 Calit2 and CSE are Very Energy Intensive Buildings
  30. 30. Power Management in Mixed Use Buildings: The UCSD CSE Building is Energy Instrumented • 500 Occupants, 750 Computers • Detailed Instrumentation to Measure Macro and Micro-Scale Power Use – 39 Sensor Pods, 156 Radios, 70 Circuits – Subsystems: Air Conditioning & Lighting • Conclusions: – Peak Load is Twice Base Load – 70% of Base Load is PCs and Servers – 90% of That Could Be Avoided! Source: Rajesh Gupta, CSE, Calit2
  31. 31. Contributors to the CSE Base Load • IT loads account for 50% (peak) to 80% (off-peak)! – Includes machine room + plug loads • IT equipment, even when idle, not put to sleep • Duty-Cycling IT loads essential to reduce baseline 31 Source: Rajesh Gupta, UCSD CSE, Calit2
  32. 32. HD Talk to Australia’s Monash University from Calit2: Reducing International Travel July 31, 2008 Qvidium Compressed HD ~140 mbps Source: David Abramson, Monash Univ
  33. 33. Linking the Calit2 Auditoriums at UCSD and UCI with LifeSize HD for Shared Seminars Sept. 8, 2009 2009 September 8, Photo by Erik Jepsen, UC San Diego
  34. 34. First Tri-Continental Premier of a Streamed 4K Feature Film With Global HD Discussion 4K Film Director, Beto Souza Keio Univ., Japan Calit2@UCSD Source: Sheldon Brown, San Paulo, Brazil Auditorium CRCA, Calit2 4K Transmission Over 10Gbps-- 4 HD Projections from One 4K Projector
  35. 35. The OptIPuter Project: Creating High Resolution Portals Over Dedicated Optical Channels to Global Science Data Scalable Adaptive Graphics Environment (SAGE) Picture Source: Mark Ellisman, David Lee, Jason Leigh Calit2 (UCSD, UCI), SDSC, and UIC Leads—Larry Smarr PI Univ. Partners: NCSA, USC, SDSU, NW, TA&M, UvA, SARA, KISTI, AIST Industry: IBM, Sun, Telcordia, Chiaro, Calient, Glimmerglass, Lucent
  36. 36. On-Line Resources Help You Build Your Own OptIPortal OptIPortals Are Built From Commodity PC Clusters and LCDs To Create a 10Gbps Scalable Termination Device
  37. 37. the AESOP Nearly Seamless OptIPortal 46‖ NEC Ultra-Narrow Bezel 720p LCD Monitors Source: Tom DeFanti, Calit2@UCSD;
  38. 38. High Definition Video Connected OptIPortals: Virtual Working Spaces for Data Intensive Research NASA Ames Mountain View, CA NASA Interest in Supporting Virtual Institutes LifeSize HD Calit2@UC San Diego Enables Collaboration Without Travel Source: Falko Kuester, Kai Doerr Calit2; Michael Sims, NASA
  39. 39. Providing End-to-End CI for Petascale End Users Two 64K Mike Norman, SDSC Images October 10, 2008 From a Cosmological Simulation log of gas temperature log of gas density of Galaxy Cluster Formation
  40. 40. 3D Stereo Head Tracked OptIPortal: NexCAVE Array of JVC HDTV 3D LCD Screens KAUST NexCAVE = 22.5MPixels Source: Tom DeFanti, Calit2@UCSD
  41. 41. 3D CAVE to CAVE Collaboration with HD Video Photo: Tom DeFanti Calit2’s Jurgen Schulze in San Diego in StarCAVE and Kara Gribskov at SC’09 in Portland, OR with NextCAVE
  42. 42. For Technical Details On OptIPuter Project and OptIPortals “OptIPlanet: The OptIPuter Global Collaboratory” – Special Section of Future Generations Computer Systems, Volume 25, Issue 2, February 2009
  43. 43. Follow My Talks and Tweets at