{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:22:37Z","timestamp":1763922157146,"version":"3.45.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076113","type":"print"},{"value":"9783032076120","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-07612-0_2","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:18Z","timestamp":1763920638000},"page":"15-27","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Monitoring Energy Consumption of\u00a0Workloads on\u00a0HPC Vega"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7629-5605","authenticated-orcid":false,"given":"Teo","family":"Prica","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3340-5624","authenticated-orcid":false,"given":"Ale\u0161","family":"Zamuda","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"2_CR1","unstructured":"EuroHPC Vega Documentation. https:\/\/doc.vega.izum.si\/. Accessed 25 July 2024"},{"key":"2_CR2","unstructured":"Node Health Check (NHC). https:\/\/github.com\/mej\/nhc. Accessed 25 Oct 2024"},{"key":"2_CR3","unstructured":"TOP500 Methodology 2.0rc1 (2025). https:\/\/www.top500.org\/static\/media\/ uploads\/methodology-2.0rc1.pdf. Accessed 19 Jan 2024"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Aaen\u00a0Springborg, A., Albano, M., Xavier-de Souza, S.: Automatic energy-efficient job scheduling in HPC: a novel SLURM plugin approach. In: SC-W \u201923: Proceedings of the SC \u201923 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, pp. 1831\u20131838. ACM (2023)","DOI":"10.1145\/3624062.3624265"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Angelelli, L., Carastan-Santos, D., Dutot, P.F.: Run your HPC jobs in eco-mode: revealing the potential of user-assisted power capping in supercomputing systems. In: Workshop on Job Scheduling Strategies for Parallel Processing, pp. 181\u2013196. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-74430-3_10","DOI":"10.1007\/978-3-031-74430-3_10"},{"key":"2_CR6","doi-asserted-by":"publisher","unstructured":"Blomer, J., et\u00a0al.: New directions in the CernVM file system. In: Journal of Physics: Conference Series, vol. 898 (2017). https:\/\/doi.org\/10.1088\/1742-6596\/898\/6\/062031","DOI":"10.1088\/1742-6596\/898\/6\/062031"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1007\/s10586-023-04151-2","volume":"27","author":"A Cabrera","year":"2023","unstructured":"Cabrera, A., Almeida, F., Castellanos-Nieves, D., Oleksiak, A., Blanco, V.: Energy efficient power cap configurations through Pareto front analysis and machine learning categorization. Clust. Comput. 27, 3433\u20133449 (2023)","journal-title":"Clust. Comput."},{"key":"2_CR8","unstructured":"Chapman, R., et\u00a0al.: Observability with Grafana: Monitor, control, and visualize your Kubernetes and cloud platforms. Packt Publishing Ltd. (2024)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Corbalan, J., et\u00a0al.: Energy optimization and analysis with EAR. In: 2020 IEEE International Conference on Cluster Computing, pp. 464\u2013472. IEEE (2020)","DOI":"10.1109\/CLUSTER49012.2020.00067"},{"key":"2_CR10","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/8348791","author":"P Czarnul","year":"2019","unstructured":"Czarnul, P., Proficz, J., Krzywaniak, A.: Energy-aware high-performance computing: survey of state-of-the-art tools, techniques, and environments. Sci. Program. (2019). https:\/\/doi.org\/10.1155\/2019\/8348791","journal-title":"Sci. Program."},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"David, H., et\u00a0al.: RAPL: memory power estimation and capping. In: 2010 ACM International Symposium on Low-Power Electronics and Design, pp. 189\u2013194 (2010). https:\/\/doi.org\/10.1145\/1840845.1840883","DOI":"10.1145\/1840845.1840883"},{"issue":"3","key":"2_CR12","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1007\/s11227-013-0884-0","volume":"65","author":"IP Egwutuoha","year":"2013","unstructured":"Egwutuoha, I.P., Levy, D., Selic, B., Chen, S.: A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems. J. Supercomput. 65(3), 1302\u20131326 (2013). https:\/\/doi.org\/10.1007\/s11227-013-0884-0","journal-title":"J. Supercomput."},{"key":"2_CR13","doi-asserted-by":"publisher","unstructured":"Huang, Z., et\u00a0al.: A concurrent OS-level GPU checkpoint and restore system using validated speculation (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.12079","DOI":"10.48550\/arXiv.2405.12079"},{"key":"2_CR14","doi-asserted-by":"publisher","unstructured":"Iakymchuk, R., et al.: Best Practice Guide - Harvesting energy consumption on European HPC systems: Sharing Experience from the CEEC project (2024). https:\/\/doi.org\/10.5281\/zenodo.13306639","DOI":"10.5281\/zenodo.13306639"},{"key":"2_CR15","unstructured":"IPMI\u00a0Working\u00a0Group: IPMI Specification (2006). Accessed 25 Oct 2024"},{"key":"2_CR16","doi-asserted-by":"publisher","unstructured":"Jette, M.A., et\u00a0al.: SLURM: simple linux utility for resource management. In: Proceedings of the 9th International Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP) (2002). https:\/\/doi.org\/10.1007\/10968987_3","DOI":"10.1007\/10968987_3"},{"key":"2_CR17","doi-asserted-by":"publisher","unstructured":"Jiao, Y., et\u00a0al.: Power and performance characterization of computational kernels on the GPU. In: International Conference on Green Computing and Communications, pp. 221\u2013228 (2010). https:\/\/doi.org\/10.1109\/GreenCom-CPSCom.2010.143","DOI":"10.1109\/GreenCom-CPSCom.2010.143"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Kra\u0161ovec, B., Prica, T.: Secure usage of containers in the HPC environment. In: Nordic e-Infrastructure Tomorrow, pp. 96\u2013112. Springer, Heidelberg (2025)","DOI":"10.1007\/978-3-031-86240-3_7"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.jpdc.2021.03.001","volume":"153","author":"M Kumar","year":"2021","unstructured":"Kumar, M., et al.: Study of interconnect errors, network congestion, and applications characteristics for throttle prediction on a large scale HPC system. J. Parallel Distrib. Comput. 153, 29\u201343 (2021)","journal-title":"J. Parallel Distrib. Comput."},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Liu, C., Chakraborty, A., Chawla, N., Roggel, N.: Frequency throttling side-channel attack. In: Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pp. 1977\u20131991. ACM (2022)","DOI":"10.1145\/3548606.3560682"},{"key":"2_CR21","doi-asserted-by":"publisher","unstructured":"Liu, Y., et\u00a0al.: Energy consumption and emission mitigation prediction based on data center traffic and PUE for global data centers. In: Global Energy Interconnection, pp. 272\u2013282 (2020). https:\/\/doi.org\/10.1016\/j.gloei.2020.07.008","DOI":"10.1016\/j.gloei.2020.07.008"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Ma, K., Bai, Y., Wang, X., Chen, W., Li, X.: Energy conservation for GPU\u2013CPU architectures with dynamic workload division and frequency scaling. In: Sustainable Computing: Informatics and Systems, pp. 21\u201333 (2016)","DOI":"10.1016\/j.suscom.2016.05.002"},{"key":"2_CR23","volume-title":"Ansible: Up and Running","author":"B Meijer","year":"2022","unstructured":"Meijer, B., et al.: Ansible: Up and Running. O\u2019Reilly Media, Inc., Newton (2022)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Mujkanovic, N., Durillo, J.J., Hammer, N., M\u00fcller, T.: Survey of adaptive containerization architectures for HPC. In: Proceedings of the SC \u201923 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, pp. 165\u2013176 (2023)","DOI":"10.1145\/3624062.3624588"},{"key":"2_CR25","doi-asserted-by":"publisher","unstructured":"Narasimhamurthy, S., et\u00a0al.: ETP4HPC\u2019s SRA 6 - Strategic Research Agenda for High Performance Computing in Europe. ETP4HPC Strategic Research Agenda, Zenodo (2024). https:\/\/doi.org\/10.5281\/zenodo.14268783","DOI":"10.5281\/zenodo.14268783"},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10462-018-09679-z","volume":"52","author":"G Nguyen","year":"2019","unstructured":"Nguyen, G., et al.: Machine learning and deep learning frameworks and libraries for large-scale data mining: a survey. Artif. Intell. Rev. 52(1), 77\u2013124 (2019). https:\/\/doi.org\/10.1007\/s10462-018-09679-z","journal-title":"Artif. Intell. Rev."},{"key":"2_CR27","unstructured":"Nortamo, H.: EuroHPC FP: A Federated Platform for HPC Infrastructure in Europe (2025). https:\/\/fosdem.org\/"},{"key":"2_CR28","doi-asserted-by":"publisher","unstructured":"Popescu, V.F., et\u00a0al.: Supervisory control and data acquisition (SCADA) traffic simulation for controlling industrial processes and infrastructures. Land Forces Acad. Rev. 27 (2022). https:\/\/doi.org\/10.1007\/978-3-030-92188-0_16","DOI":"10.1007\/978-3-030-92188-0_16"},{"key":"2_CR29","unstructured":"Prica, T.: Development and supporting activities on EuroHPC Vega. In: Austrian-Slovenian HPC Meeting 2024 \u2014 ASHPC24, p.\u00a014 (2024)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Santos, E.A., et\u00a0al.: How does Docker affect energy consumption? Evaluating workloads in and out of Docker containers. J. Syst. Softw. 146","DOI":"10.1016\/j.jss.2018.07.077"},{"key":"2_CR31","unstructured":"Sauge, L.: PRACE at SC17: Bull Energy Optimizer (2017). https:\/\/prace-ri.eu\/wp-content\/uploads\/PRACE-at-SC17-Ludovic-Sauge.pdf. Accessed 25 Oct 2024"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Silva, C., Vila\u00e7a, R., Pereira, A., Bessa, R.: A review on the decarbonization of high-performance computing centers. Renew. Sustain. Energy 189 (2024)","DOI":"10.1016\/j.rser.2023.114019"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Simsek, O.S., Piccinali, J.G., Ciorba, F.M.: Accurate measurement of application-level energy consumption for energy-aware large-scale simulations. In: Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis (SC-W 2023), Denver, CO, USA, 12\u201317 November 2023, pp. 1881\u20131884. ACM, New York (2023)","DOI":"10.1145\/3624062.3624272"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Sundriyal, V., et\u00a0al.: Automatic runtime frequency-scaling system for energy savings in parallel applications. J. Supercomput. 68, 777\u2013797 (2013)","DOI":"10.1007\/s11227-013-1062-0"},{"key":"2_CR35","unstructured":"Super Micro Computer, Inc.: BMC: Baseboard Management Controller, Revision 1.0a, p. 270 (2022)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Terai, M., et\u00a0al.: An operational data collecting and monitoring platform for fugaku: system overviews and case studies in the prelaunch service period. In: High Performance Computing, pp. 365\u2013377 (2021)","DOI":"10.1007\/978-3-030-90539-2_24"},{"key":"2_CR37","doi-asserted-by":"publisher","unstructured":"Timalsina, M., et\u00a0al.: Optimizing Checkpoint-Restart Mechanisms for HPC with DMTCP in Containers at NERSC (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.19117","DOI":"10.48550\/arXiv.2407.19117"},{"key":"2_CR38","doi-asserted-by":"publisher","unstructured":"Vamja, T., Ray, K., George, F., Devi, U.C.: On the Partitioning of GPU Power among Multi-Instances (2025). https:\/\/doi.org\/10.48550\/arXiv.2501.17752","DOI":"10.48550\/arXiv.2501.17752"},{"key":"2_CR39","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et\u00a0al.: Attention is all you need (2023). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"White, J.P., et\u00a0al.: Monitoring and analysis of power consumption on HPC clusters using XDMoD. In: PEARC \u201920 (2020). https:\/\/doi.org\/10.1145\/3311790.3396624","DOI":"10.1145\/3311790.3396624"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Wilde, T., Auweter, A., Shoukourian, H.: The 4 Pillar Framework for energy efficient HPC data centers. In: Computer Science - Research and Development, vol. 29 (2013)","DOI":"10.1007\/s00450-013-0244-6"},{"key":"2_CR42","doi-asserted-by":"publisher","unstructured":"Wolf, T., et\u00a0al.: HuggingFace\u2019s Transformers: State-of-the-art Natural Language Processing (2020). https:\/\/doi.org\/10.48550\/arXiv.1910.03771","DOI":"10.48550\/arXiv.1910.03771"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zhao, D., et al.: Sustainable supercomputing for AI: GPU power capping at HPC scale. In: 2023 ACM Symposium on Cloud Computing. ACM (2024)","DOI":"10.1145\/3620678.3624793"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07612-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:23Z","timestamp":1763920643000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07612-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076113","9783032076120"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07612-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}