Peter Xiang Gao
Srinivasan Keshav
ABSTRACT
Large-scale Internet applications, such as content distribution networks, are deployed across multiple datacenters and consume massive amounts of electricity. To provide uniformly low access latencies, these datacenters are geographically distributed and the deployment size at each location reflects the regional demand for the application. Consequently, an application's environmental impact can vary significantly depending on the geographical distribution of end-users, as electricity cost and carbon footprint per watt is location specific. In this paper, we describe FORTE: Flow Optimization based framework for request-Routing and Traffic Engineering. FORTE dynamically controls the fraction of user traffic directed to each datacenter in response to changes in both request workload and carbon footprint. It allows an operator to navigate the three-way tradeoff between access latency, carbon footprint, and electricity costs and to determine an optimal datacenter upgrade plan in response to increases in traffic load. We use FORTE to show that carbon taxes or credits are impractical in incentivizing carbon output reduction by providers of large-scale Internet applications. However, they can reduce carbon emissions by 10% without increasing the mean latency nor the electricity bill.
Supplemental Material
- Light-duty automotive technology, carbon dioxide emissions, and fuel economy trends: 1975 through 2011. U.S. Environmental Protection Agency.Google Scholar
- Akamai. Akamai reports fourth quarter 2010 and full-year 2010 financial results, 2011. http://tiny.cc/afyu9, Last visited Jan. 2012.Google Scholar
- H. Amur, J. Cipar, V. Gupta, G. R. Ganger, M. A. Kozuch, and K. Schwan. Robust and flexible power-proportional storage. In SoCC, 2010. Google ScholarDigital Library
- L. Barroso and U. Holzle. The case for energy-proportional computing. Computer, 40(12):33--37, dec. 2007. Google ScholarDigital Library
- California ISO. Renewables watch, 2011. http: //www.caiso.com/green/renewableswatch.html.Google Scholar
- J. Chang, J. Meza, P. Ranganathan, C. Bash, and A. Shah. Green server design: beyond operational energy to sustainability. In HotPower, 2010. Google ScholarDigital Library
- A. R. Curtis, S. Keshav, and A. López-Ortiz. LEGUP: Using heterogeneity to reduce the cost of data center network upgrades. In CoNEXT, 2010. Google ScholarDigital Library
- B. Dennis. Estimating a data center's electrical carbon footprint. Schneider Electric White Paper 66, 2011.Google Scholar
- J. Doyle, D. O'Mahony, and R. Shorten. Server selection for carbon emission control. In GreenNet, 2011. Google ScholarDigital Library
- EPA. EPA report to congress on server and data center energy efficiency. Technical report, U.S. Environmental Protection Agency, 2007.Google Scholar
- A. Feldmann, A. Gladisch, M. Kind, C. Lange, G. Smaragdakis, and F.-J. Westphal. Energy trade-offs among content delivery architectures. In CTTE, 2010.Google ScholarCross Ref
- I. Goiri, K. Le, J. Guitart, J. Torres, and R. Bianchini. Intelligent placement of datacenters for internet services. In ICDCS, 2011. Google ScholarDigital Library
- Google. Efficient computing-step 2: efficient datacenters. http://www.google.com/corporate/green/datacenters/step2.html.Google Scholar
- Google green. http://www.google.com/green/, Last visited Jan. 2012.Google Scholar
- Google's Data Center Efficiency. http://www.google.com/about/datacenters/inside/efficiency/power-usage.html, Last visited Jan. 2012.Google Scholar
- A. G. Greenberg, J. R. Hamilton, D. A. Maltz, and P. Patel. The cost of a cloud: research problems in data center networks. SIGCOMM CCR, 39(1):68--73, 2009. Google ScholarDigital Library
- K. Guan, G. Atkinson, D. Kilper, and E. Gulsen. On the energy efficiency of content delivery architectures. In ICC, 2011.Google ScholarCross Ref
- B. Heller, S. Seetharaman, P. Mahadevan, Y. Yiakoumis, P. Sharma, S. Banerjee, and N. McKeown. Elastictree: saving energy in data center networks. In NSDI, 2010. Google ScholarDigital Library
- B. H. Joseph V. Spadaro, Lucille Langlois. Greenhouse gas emissions of electricity generation chains: Assessing the difference. IAEA Bulletin, 2000.Google Scholar
- G. Jourjon, T. Rakotoarivelo, and M. Ott. Models for an energy-efficient p2p delivery service. In PDP, 2010. Google ScholarDigital Library
- J. Kanter. Europe considers new taxes to promote 'clean' energy, 2010. http://nyti.ms/xSlobE, Last visited Jan. 2012.Google Scholar
- J. Koomey. Growth in data center electricity use 2005 to 2010. Analytics Press, Aug. 2011.Google Scholar
- J. G. Koomey. Worldwide electricity used in data centers. Environmental Research Letters, 3(3):034008, 2008.Google ScholarCross Ref
- A. Krioukov, P. Mohan, S. Alspaugh, L. Keys, D. Culler, and R. H. Katz. Napsac: design and implementation of a power-proportional web cluster. In GreenNet, 2010. Google ScholarDigital Library
- C. Labovitz, S. Iekel-Johnson, D. McPherson, J. Oberheide, and F. Jahanian. Internet inter-domain traffic. In SIGCOMM, 2010. Google ScholarDigital Library
- K. Le, R. Bianchini, T. Nguyen, O. Bilgir, and M. Martonosi. Capping the brown energy consumption of internet services at low cost. In IGCC, 2010. Google ScholarDigital Library
- U. Lee, I. Rimac, and V. Hilt. Greening the internet with content-centric networking. In e-Energy, 2010. Google ScholarDigital Library
- M. Lin, A. Wierman, L. L. H. Andrew, and E. Thereska. Dynamic right-sizing for power-proportional data centers. In INFOCOM, 2011.Google ScholarCross Ref
- Z. Liu, M. Lin, A. Wierman, S. H. Low, and L. L. Andrew. Greening geographical load balancing. In SIGMETRICS, 2011. Google ScholarDigital Library
- V. Mathew, R. Sitaraman, and P. Shenoy. Energy-aware load balancing in content delivery networks. In INFOCOM, 2012.Google ScholarCross Ref
- R. Miller. Report: Google Uses About 900,000 Servers. Data Center Knowledge, http://tiny.cc/gservers, 2011. Last visited Jan 2012.Google Scholar
- A. Mohsenian-Rad and A. Leon-Garcia. Coordination of cloud computing and smart power grids. In SmartGridComm, 2010.Google ScholarCross Ref
- E. Nygren, R. K. Sitaraman, and J. Sun. The akamai network: a platform for high-performance internet applications. SIGOPS OSR, 44:2--19, August 2010. Google ScholarDigital Library
- J. Park. Designing a Very Efficient Data Center. Facebook.com, http://tiny.cc/fbservers, 2011. Last visited Jan 2012.Google Scholar
- A. Qureshi, R. Weber, H. Balakrishnan, J. Guttag, and B. Maggs. Cutting the electric bill for Internet-scale systems. In SIGCOMM, 2009. Google ScholarDigital Library
- B. Raghavan and J. Ma. The Energy and Emergy of the Internet. In HotNets, 2011. Google ScholarDigital Library
- L. Rao, X. Liu, L. Xie, and W. Liu. Minimizing electricity cost: optimization of distributed internet data centers in a multi-electricity-market environment. In INFOCOM, 2010. Google ScholarDigital Library
- J. Rath. Data center site selection. In Rath Consulting White Paper, 2007.Google Scholar
- E. Schurman and J. Brutlag. The user and business impact of server delays, additional bytes, and HTTP chunking in web search. Presentation at the O'Reilly Velocity Web Performance and Operations Conference, 2009.Google Scholar
- A. Sullivan. ENERGY STAR for Data Centers. Technical report, U.S. Environmental Protection Agency, 2009.Google Scholar
- U.S. Energy Information Administration. http://www.eia.gov, Last visited Jan. 2012.Google Scholar
- V. Valancius, N. Laoutaris, L. Massoulié, C. Diot, and P. Rodriguez. Greening the internet with nano data centers. In CoNEXT, 2009. Google ScholarDigital Library
- E. Williams. Energy intensity of computer manufacturing: hybrid assessment combining process and economic input-output methods. Environ. Sci. Technol., 38(22), Nov 2004.Google Scholar
Index Terms
- It's not easy being green
Recommendations
It's not easy being green
Special october issue SIGCOMM '12Large-scale Internet applications, such as content distribution networks, are deployed across multiple datacenters and consume massive amounts of electricity. To provide uniformly low access latencies, these datacenters are geographically distributed ...
Impact of Virtualization on Cloud Computing Energy Consumption: Empirical Study
ISCSIC '18: Proceedings of the 2nd International Symposium on Computer Science and Intelligent ControlGlobal warming, which is currently one of the greatest environmental challenges, is caused by carbon emissions. A report from the Energy Information Administration indicates that approximately 98% of CO2 emissions can be attributed to energy ...
Carbon Capture by Fossil Fuel Power Plants: An Economic Analysis
For fossil fuel power plants to be built in the future, carbon capture and storage (CCS) technologies offer the potential for significant reductions in carbon dioxide (CO2) emissions. We examine the break-even value for CCS adoptions, that is, the ...
Comments