Environmental Burden of United States Data Centers in the Artificial Intelligence Era

• URL: http://arxiv.org/abs/2411.09786v1
• Date: Thu, 14 Nov 2024 19:55:49 GMT
• Title: Environmental Burden of United States Data Centers in the Artificial Intelligence Era
• Authors: Gianluca Guidi, Francesca Dominici, Jonathan Gilmour, Kevin Butler, Eric Bell, Scott Delaney, Falco J. Bargagli-Stoffi,
• Abstract summary: Data centers generated more than 105 million tons of CO$_2$e (2.18% of US emissions in 2023) Data centers' carbon intensity - the amount of CO$_2$e emitted per unit of electricity consumed - exceeded the US average by 48%. Our data pipeline and visualization tools can be used to assess current and future environmental impacts of data centers.
• Score: 0.5025737475817937
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid proliferation of data centers in the US - driven partly by the adoption of artificial intelligence - has set off alarm bells about the industry's environmental impact. We compiled detailed information on 2,132 US data centers operating between September 2023 and August 2024 and determined their electricity consumption, electricity sources, and attributable CO$_{2}$e emissions. Our findings reveal that data centers accounted for more than 4% of total US electricity consumption - with 56% derived from fossil fuels - generating more than 105 million tons of CO$_{2}$e (2.18% of US emissions in 2023). Data centers' carbon intensity - the amount of CO$_{2}$e emitted per unit of electricity consumed - exceeded the US average by 48%. Our data pipeline and visualization tools can be used to assess current and future environmental impacts of data centers.

Related papers

• The Environmental Impact of AI Servers and Sustainable Solutions [0.0]
  This study evaluates the environmental footprint of AI server operations.<n>Projections indicate that global data center electricity demand may increase from approximately 415 TWh in 2024 to nearly 945 TWh by 2030.<n>In the United States alone, AI servers are expected to drive annual increases in water consumption of 200--300 billion gallons and add 24--44 million metric tons of CO2 quivalent emissions by 2030.
  arXiv  Detail & Related papers  (2025-12-24T01:09:06Z)
• Environmental Impact of CI/CD Pipelines [45.02374935546107]
  GitHub Actions ecosystem results in a substantial carbon and water footprint.<n>To provide perspective, the carbon footprint in the most likely scenario is equivalent to the carbon captured by 7,615 urban trees in a year.<n>Key recommendations include deploying runners in regions whose energy production has a low environmental impact.
  arXiv  Detail & Related papers  (2025-10-30T12:02:09Z)
• Towards Autonomous Sustainability Assessment via Multimodal AI Agents [46.77807327332175]
  We introduce multimodal AI agents to calculate cradle-to-gate carbon emissions of electronic devices.<n>The approach reduces weeks or months of expert time to under one minute and closes data availability gaps.<n>It yields carbon footprint estimates within 19% of expert LCAs with zero proprietary data.
  arXiv  Detail & Related papers  (2025-07-22T20:49:25Z)
• HEAPO -- An Open Dataset for Heat Pump Optimization with Smart Electricity Meter Data and On-Site Inspection Protocols [1.6419846488719232]
  Heat pumps are essential for decarbonizing residential heating but consume substantial electrical energy impacting operational costs and grid demand. We present an open-source dataset of electricity consumption from 1,408 households with heat pumps and smart electricity meters in the canton of Zurich, Switzerland.
  arXiv  Detail & Related papers  (2025-03-21T09:58:01Z)
• Holistically Evaluating the Environmental Impact of Creating Language Models [26.846990296567267]
  We estimate the real-world environmental impact of developing a series of language models, ranging from 20 million to 13 billion active parameters, trained on up to 5.6 trillion tokens each. We find that our series of models released 493 metric tons of carbon emissions, equivalent to powering about 98 homes in the United States for one year. We also find that power usage throughout training is not consistent, fluctuating between 15% and 85% of our hardware's maximum power draw.
  arXiv  Detail & Related papers  (2025-03-03T22:16:15Z)
• Software Frugality in an Accelerating World: the Case of Continuous Integration [2.73028688816111]
  We conduct the first large-scale analysis of the energy footprint of Continuous Integration pipelines implemented with GitHub. We observe that the average unitary energy cost of a pipeline is relatively low, at 10 Wh. When evaluating CO2 emissions based on regional Wh-to-CO2 estimates, we observe that the average aggregated CO2 emissions are significant, averaging 10.5 kg.
  arXiv  Detail & Related papers  (2024-10-21T09:29:50Z)
• Data Contamination Report from the 2024 CONDA Shared Task [78.50743680642405]
  This first compilation paper is based on 566 reported entries over 91 contaminated sources from a total of 23 contributors. The goal of the shared task and associated database is to assist the community in understanding the extent of the problem and to assist researchers in avoiding reporting evaluation results on known contaminated resources.
  arXiv  Detail & Related papers  (2024-07-31T11:26:57Z)
• Forecasting Imports in OECD Member Countries and Iran by Using Neural Network Algorithms of LSTM [0.0]
  This study aims at forecasting imports in OECD member selected countries and Iran for 20 seasons from 2021 to 2025 by means of ANN. Data related to the imports of such countries collected over 50 years from 1970 to 2019 from valid resources including World Bank, WTO, IFM. This study has used LSTM to analyse data in Pycharm. 75% of data considered as training data and 25% considered as test data and the results of the analysis were forecasted with 99% accuracy.
  arXiv  Detail & Related papers  (2024-01-06T17:34:26Z)
• Compute at Scale: A Broad Investigation into the Data Center Industry [0.8547032097715571]
  The global industry is valued at approximately $250B and is expected to double over the next seven years. There are likely about 500 large (above 10 MW) data centers globally, with the US, Europe, and China constituting the most important markets.
  arXiv  Detail & Related papers  (2023-11-05T13:39:59Z)
• Benchmarks and Custom Package for Energy Forecasting [55.460452605056894]
  Energy forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch. In this paper, we collected large-scale load datasets and released a new renewable energy dataset. We conducted extensive experiments with 21 forecasting methods in these energy datasets at different levels under 11 evaluation metrics.
  arXiv  Detail & Related papers  (2023-07-14T06:50:02Z)
• Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model [72.65502770895417]
  We quantify the carbon footprint of BLOOM, a 176-billion parameter language model, across its life cycle. We estimate that BLOOM's final training emitted approximately 24.7 tonnes ofcarboneqif we consider only the dynamic power consumption. We conclude with a discussion regarding the difficulty of precisely estimating the carbon footprint of machine learning models.
  arXiv  Detail & Related papers  (2022-11-03T17:13:48Z)
• Measuring the Carbon Intensity of AI in Cloud Instances [91.28501520271972]
  We provide a framework for measuring software carbon intensity, and propose to measure operational carbon emissions. We evaluate a suite of approaches for reducing emissions on the Microsoft Azure cloud compute platform.
  arXiv  Detail & Related papers  (2022-06-10T17:04:04Z)
• Towards Sustainable Energy-Efficient Data Centers in Africa [0.0]
  By 2040, 14 percent of global emissions will come from data centers. This paper presents early findings in the use AI and digital twins to model and optimize data center operations.
  arXiv  Detail & Related papers  (2021-09-09T07:18:21Z)
• A Framework for Energy and Carbon Footprint Analysis of Distributed and Federated Edge Learning [48.63610479916003]
  This article breaks down and analyzes the main factors that influence the environmental footprint of distributed learning policies. It models both vanilla and decentralized FL policies driven by consensus. Results show that FL allows remarkable end-to-end energy savings (30%-40%) for wireless systems characterized by low bit/Joule efficiency.
  arXiv  Detail & Related papers  (2021-03-18T16:04:42Z)
• Investigation of the Impacts of COVID-19 on the Electricity Consumption of a University Dormitory Using Weather Normalization [2.5352713493505785]
  The study investigated the impacts of the COVID-19 pandemic on the electricity consumption of a university dormitory building in the southern U.S. The results suggested that the total electricity consumption of the objective building decreased by nearly 41% (about 276,000 kWh (942 MMBtu)) compared with the prediction value during the campus shutdown due to the COVID-19.
  arXiv  Detail & Related papers  (2020-12-04T20:54:03Z)
• Averaging Atmospheric Gas Concentration Data using Wasserstein Barycenters [68.978070616775]
  Hyperspectral satellite images report greenhouse gas concentrations worldwide on a daily basis. We propose using Wasserstein barycenters coupled with weather data to average gas concentration data sets and better concentrate the mass around significant sources.
  arXiv  Detail & Related papers  (2020-10-06T14:31:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.