{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T02:13:36Z","timestamp":1777428816033,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1145\/3644815.3644967","type":"proceedings-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T17:28:38Z","timestamp":1718126918000},"page":"134-139","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Green AI: a Preliminary Empirical Study on Energy Consumption in DL Models Across Different Runtime Infrastructures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8155-165X","authenticated-orcid":false,"given":"Negar","family":"Alizadeh","sequence":"first","affiliation":[{"name":"Utrecht University, Utrecht, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6389-3630","authenticated-orcid":false,"given":"Fernando","family":"Castor","sequence":"additional","affiliation":[{"name":"University of Twente, Enschede, Netherlands"},{"name":"Federal University of Pernambuco, Recife, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Carbontracker: Tracking and predicting the carbon footprint of training deep learning models. arXiv preprint arXiv:2007.03051","author":"Wolff Anthony Lasse F","year":"2020","unstructured":"Lasse F Wolff Anthony, Benjamin Kanding, and Raghavendra Selvan. 2020. Carbontracker: Tracking and predicting the carbon footprint of training deep learning models. arXiv preprint arXiv:2007.03051 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472","author":"Desislavov Radosvet","year":"2021","unstructured":"Radosvet Desislavov, Fernando Mart\u00ednez-Plumed, and Jos\u00e9 Hern\u00e1ndez-Orallo. 2021. Compute and energy consumption trends in deep learning inference. arXiv preprint arXiv:2109.05472 (2021)."},{"key":"e_1_3_2_1_3_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3350768.3353813"},{"key":"e_1_3_2_1_5_1","volume-title":"Energy Efficiency Considerations for Popular AI Benchmarks. arXiv preprint arXiv:2304.08359","author":"Fischer Raphael","year":"2023","unstructured":"Raphael Fischer, Matthias Jakobs, and Katharina Morik. 2023. Energy Efficiency Considerations for Popular AI Benchmarks. arXiv preprint arXiv:2304.08359 (2023)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.07.007"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510221"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICT4S55073.2022.00016"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455964"},{"key":"e_1_3_2_1_11_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861","author":"Howard Andrew G","year":"2017","unstructured":"Andrew G Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)."},{"key":"e_1_3_2_1_12_1","volume-title":"University of Lille","author":"INRIA","year":"2023","unstructured":"INRIA, University of Lille. 2023. Python Running Average Power Limit. https:\/\/pyrapl.readthedocs.io\/en\/latest\/index.html. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3647632.3647990"},{"key":"e_1_3_2_1_14_1","article-title":"RAPL in Action: Experiences in Using RAPL for Power Measurements","volume":"3","author":"Khan Kashif Nizam","year":"2018","unstructured":"Kashif Nizam Khan, Mikael Hirki, Tapio Niemi, Jukka K. Nurminen, and Zhonghong Ou. 2018. RAPL in Action: Experiences in Using RAPL for Power Measurements. ACM Trans. Model. Perform. Evaluation Comput. Syst. 3, 2 (2018), 9:1--9:26.","journal-title":"ACM Trans. Model. Perform. Evaluation Comput. Syst."},{"key":"e_1_3_2_1_15_1","unstructured":"Alexandre Lacoste Alexandra Luccioni Victor Schmidt and Thomas Dandres. 2019. Quantifying the Carbon Emissions of Machine Learning. arXiv:1910.09700 [cs.CY]"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2018.12.014"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 14th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2009","author":"Mytkowicz Todd","year":"2009","unstructured":"Todd Mytkowicz, Amer Diwan, Matthias Hauswirth, and Peter F. Sweeney. 2009. Producing wrong data without doing anything obviously wrong!. In Proceedings of the 14th International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2009, Washington, DC, USA, March 7--11, 2009, Mary Lou Soffa and Mary Jane Irwin (Eds.). ACM, 265--276."},{"key":"e_1_3_2_1_18_1","volume-title":"https:\/\/developer.nvidia.com\/cuda-zone. Last accessed November 20th","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. 2007. CUDA. https:\/\/developer.nvidia.com\/cuda-zone. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_19_1","volume-title":"https:\/\/developer.nvidia.com\/tensorrt. Last accessed November 20th","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. 2021. TensorRT. https:\/\/developer.nvidia.com\/tensorrt. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_20_1","volume-title":"System Management Interface SMI. https:\/\/developer.nvidia.com\/nvidia-system-management-interface. Last accessed November 20th","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation. 2023. System Management Interface SMI. https:\/\/developer.nvidia.com\/nvidia-system-management-interface. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_21_1","volume-title":"NVIDIA NCG Containers. https:\/\/catalog.ngc.nvidia.com\/orgs\/nvidia\/containers\/pytorch. Last accessed November 20th","author":"NVIDIA Corporation","year":"2023","unstructured":"NVIDIA Corporation, Facebook. 2023. NVIDIA NCG Containers. https:\/\/catalog.ngc.nvidia.com\/orgs\/nvidia\/containers\/pytorch. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-021-09950-y"},{"key":"e_1_3_2_1_23_1","volume-title":"AI And Energy Efficiency. In 2023 IEEE 20th International Conference on Software Architecture Companion (ICSA-C). IEEE, 141--144","author":"Omar Rafiullah","year":"2023","unstructured":"Rafiullah Omar. 2023. AI And Energy Efficiency. In 2023 IEEE 20th International Conference on Software Architecture Companion (ICSA-C). IEEE, 141--144."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME55016.2022.00010"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3154384"},{"key":"e_1_3_2_1_26_1","volume-title":"FECoM: A Step towards Fine-Grained Energy Measurement for Deep Learning. arXiv preprint arXiv:2308.12264","author":"Rajput Saurabhsingh","year":"2023","unstructured":"Saurabhsingh Rajput, Tim Widmayer, Ziyuan Shang, Maria Kechagia, Federica Sarro, and Tushar Sharma. 2023. FECoM: A Step towards Fine-Grained Energy Measurement for Deep Learning. arXiv preprint arXiv:2308.12264 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"arXiv preprint arXiv:1907.10597","author":"Schwartz Roy","year":"2019","unstructured":"Roy Schwartz, Jesse Dodge, Noah A Smith, and Oren Etzioni. 2019. Green AI; 2019. arXiv preprint arXiv:1907.10597 (2019)."},{"key":"e_1_3_2_1_28_1","volume-title":"An Approach Using Performance Models for Supporting Energy Analysis of Software Systems. In European Workshop on Performance Engineering. Springer, 249--263","author":"Stoico Vincenzo","year":"2023","unstructured":"Vincenzo Stoico, Vittorio Cortellessa, Ivano Malavolta, Daniele Di Pompeo, Luigi Pomante, and Patricia Lago. 2023. An Approach Using Performance Models for Supporting Energy Analysis of Software Systems. In European Workshop on Performance Engineering. Springer, 249--263."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Emma Strubell Ananya Ganesh and Andrew McCallum. 2019. Energy and Policy Considerations for Deep Learning in NLP. arXiv:1906.02243 [cs.CL]","DOI":"10.18653\/v1\/P19-1355"},{"key":"e_1_3_2_1_30_1","volume-title":"Open Neural Network Exchange. https:\/\/onnx.ai\/. Last accessed November 20th","author":"Foundation The Linux","year":"2023","unstructured":"The Linux Foundation. 2019. Open Neural Network Exchange. https:\/\/onnx.ai\/. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2013.01.005"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICT4S55073.2022.00015"},{"key":"e_1_3_2_1_33_1","volume-title":"MXNet - Deep Learning Framework of Choice at AWS. https:\/\/www.allthingsdistributed.com\/2016\/11\/mxnet-default-framework-deep-learning-aws.html. Last accessed November 20th","author":"Vogels Werner","year":"2023","unstructured":"Werner Vogels. 2016. MXNet - Deep Learning Framework of Choice at AWS. https:\/\/www.allthingsdistributed.com\/2016\/11\/mxnet-default-framework-deep-learning-aws.html. Last accessed November 20th, 2023.."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485275"},{"key":"e_1_3_2_1_35_1","volume-title":"Energy Efficiency of Training Neural Network Architectures: An Empirical Study. arXiv preprint arXiv:2302.00967","author":"Xu Yinlena","year":"2023","unstructured":"Yinlena Xu, Silverio Mart\u00ednez-Fern\u00e1ndez, Matias Martinez, and Xavier Franch. 2023. Energy Efficiency of Training Neural Network Architectures: An Empirical Study. arXiv preprint arXiv:2302.00967 (2023)."},{"key":"e_1_3_2_1_36_1","volume-title":"Batching for Green AI-An Exploratory Study on Inference. arXiv preprint arXiv:2307.11434","author":"Yarally Tim","year":"2023","unstructured":"Tim Yarally, Lu\u00eds Cruz, Daniel Feitosa, June Sallou, and Arie van Deursen. 2023. Batching for Green AI-An Exploratory Study on Inference. arXiv preprint arXiv:2307.11434 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI. In 2nd IEEE\/ACM International Conference on AI Engineering - Software Engineering for AI, CAIN 2023","author":"Yarally Tim","year":"2023","unstructured":"Tim Yarally, Luis Cruz, Daniel Feitosa, June Sallou, and Arie van Deursen. 2023. Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI. In 2nd IEEE\/ACM International Conference on AI Engineering - Software Engineering for AI, CAIN 2023, Melbourne, Australia, May 15--16, 2023. IEEE, 25--36."},{"key":"e_1_3_2_1_38_1","volume-title":"Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI. In 2023 IEEE\/ACM 2nd International Conference on AI Engineering-Software Engineering for AI (CAIN)","author":"Yarally Tim","unstructured":"Tim Yarally, Luis Cruz, Daniel Feitosa, June Sallou, and Arie Van Deursen. 2023. Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI. In 2023 IEEE\/ACM 2nd International Conference on AI Engineering-Software Engineering for AI (CAIN). IEEE, 25--36."}],"event":{"name":"CAIN 2024: IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI","location":"Lisbon Portugal","acronym":"CAIN 2024","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the IEEE\/ACM 3rd International Conference on AI Engineering - Software Engineering for AI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3644815.3644967","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3644815.3644967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:27Z","timestamp":1750291407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3644815.3644967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":38,"alternative-id":["10.1145\/3644815.3644967","10.1145\/3644815"],"URL":"https:\/\/doi.org\/10.1145\/3644815.3644967","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]},"assertion":[{"value":"2024-06-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}