{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T05:08:58Z","timestamp":1779167338779,"version":"3.51.4"},"reference-count":59,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>AI infrastructure is entering a constraint-dominated regime in which power access, cooling, water conditions, reliability, and financing jointly shape cost, sustainability, and operational risk. Yet the metrics used to evaluate these systems remain fragmented across facility engineering, compute\/workload performance, and economic or risk analysis, with definitions that often sit at different layers and under different boundaries. This fragmentation weakens cross-layer reasoning and makes decision-traceable trade-off analysis difficult. This paper proposes a structured, decision-oriented measurement architecture for AI infrastructure metrics. The framework combines a 6 \u00d7 3 taxonomy, which organizes metrics across six layers and three semantic domains, with a procedural workflow built around a problem card, variable registry, minimality gate record, activated-cell map, boundary log, metric ledger, and a results sheet with case-pack manifest. Within this protocol, the Metric Propagation Graph is used as a case-specific dependency representation for tracing decision-facing metrics back to minimal boundary-consistent inputs. It is introduced as a traceability layer within the framework rather than as a stand-alone graph-theoretic method. The paper is illustrated through one fully worked case and one scoped portability illustration. The first is a fully worked large-load planning case for the Northern Virginia data-center corridor within PJM\u2019s Dominion zone, showing that a boundary-consistent integrated metric can reverse the ranking obtained under a simpler screening view. The second is a scoped portability illustration for hourly matching under dual Scope 2 boundaries. Its purpose is not to provide a second full empirical validation, but to show how the same dossier logic, boundary discipline, and traceable metric construction transfer to a distinct decision setting.<\/jats:p>","DOI":"10.3390\/info17050432","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T09:33:17Z","timestamp":1777627997000},"page":"432","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Unified Metric Architecture for AI Infrastructure: A Cross-Layer Taxonomy Integrating Performance, Efficiency, and Cost"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6258-5137","authenticated-orcid":false,"given":"Qi","family":"He","sequence":"first","affiliation":[{"name":"Google LLC, Austin, TX 78701, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2003-6401","authenticated-orcid":false,"given":"Wenjie","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Mechanical and Aerospace Engineering, Jilin University, Changchun 130012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1126\/science.aba3758","article-title":"Recalibrating global data center energy-use estimates","volume":"367","author":"Masanet","year":"2020","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101430","DOI":"10.1016\/j.patter.2025.101430","article-title":"The carbon and water footprints of data centers and what this could mean for artificial intelligence","volume":"7","year":"2026","journal-title":"Patterns"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"oiad014","DOI":"10.1093\/ooenergy\/oiad014","article-title":"Stretched grid? Managing data center energy demand and grid capacity","volume":"2","author":"Mytton","year":"2023","journal-title":"Oxf. Open Energy"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Safari, A., Sorouri, H., Rahimi, A., and Oshnoei, A. (2025). A systematic review of energy efficiency metrics for optimizing cloud data center operations and management. Electronics, 14.","DOI":"10.3390\/electronics14112214"},{"key":"ref_5","unstructured":"Mattson, P., Cheng, C., Coleman, C.A., Diamos, G.F., Micikevicius, P., Patterson, D.A., Tang, H., Wei, G.-Y., Bailis, P., and Bittorf, V. (2019). MLPerf training benchmark. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Cao, J.M., Guan, Y., Qian, K., Gao, J.Q., Xiao, W.C., Dong, J.B., Fu, B.Z., Cai, D., and Zhai, E.N. (2024, January 4\u20138). Crux: GPU-efficient communication scheduling for deep learning training. Proceedings of the 2024 ACM SIGCOMM 2024 Conference, Sydney, Australia.","DOI":"10.1145\/3651890.3672239"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/MM.2012.71","article-title":"Optimizing data-center TCO with scale-out processors","volume":"32","author":"Grot","year":"2012","journal-title":"IEEE Micro"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/3381831","article-title":"Green AI","volume":"63","author":"Schwartz","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"He, Q., and Qu, C. (2025). Waste-to-energy-coupled AI data centers: Cooling efficiency and grid resilience. arXiv.","DOI":"10.1109\/GreenTech68285.2026.11471545"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"He, Q. (2025). Location-robust cost-preserving blended pricing for multi-campus AI data centers. Symmetry, 18.","DOI":"10.2139\/ssrn.5931756"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"He, Q., and Qu, C. (2025). Modular landfill remediation for AI grid resilience. arXiv.","DOI":"10.1109\/SysCon66367.2026.11503598"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102098","DOI":"10.1016\/j.frl.2021.102098","article-title":"Impact of carbon tax on electricity prices and behaviour","volume":"44","author":"Wong","year":"2022","journal-title":"Financ. Res. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3529","DOI":"10.1016\/j.egyr.2025.10.012","article-title":"Energy solutions for data center: Comparative analysis of levelized cost of electricity (LCOE) and recent developments","volume":"14","author":"Uranbold","year":"2025","journal-title":"Energy Rep."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Pakbaznia, E., and Pedram, M. (2009, January 19\u201321). Minimizing data center cooling and server power costs. Proceedings of the 2009 ACM\/IEEE International Symposium on Low Power Electronics and Design, San Fancisco, CA, USA.","DOI":"10.1145\/1594233.1594268"},{"key":"ref_15","unstructured":"International Carbon Action Partnership (ICAP) (2024). Carbon Pricing in the Power Sector, The World Bank Group. Available online: https:\/\/icapcarbonaction.com\/system\/files\/document\/carbon-pricing-in-the-power-sector_final.pdf."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3440689","article-title":"AI tax: The hidden cost of AI data center applications","volume":"37","author":"Richins","year":"2021","journal-title":"ACM Trans. Comput. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Jian, X., Hanumolu, P.K., and Kumar, R. (2017, January 4\u20138). Understanding and optimizing power consumption in memory networks. Proceedings of the 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA), Austin, TX, USA.","DOI":"10.1109\/HPCA.2017.60"},{"key":"ref_18","unstructured":"(2016). Information Technology\u2014Data Centres\u2014Key Performance Indicators\u2014Part 1: Overview and General Requirements (Standard No. ISO\/IEC 30134-1:2016)."},{"key":"ref_19","unstructured":"ASHRAE (2021). 2021 Thermal Guidelines for Data Processing Environments, ASHRAE. [5th ed.]."},{"key":"ref_20","unstructured":"Google (2026, March 21). Data Center Efficiency. Available online: https:\/\/datacenters.google\/efficiency\/."},{"key":"ref_21","unstructured":"Google (2026, March 21). Google 2025 Environmental Report. Available online: https:\/\/sustainability.google\/reports\/google-2025-environmental-report\/."},{"key":"ref_22","unstructured":"Google (2026, March 21). Data Center Impact Report. Available online: https:\/\/static.googleusercontent.com\/media\/www.google.com\/en\/\/about\/datacenters\/static\/pdf\/google-va-impact-report.pdf."},{"key":"ref_23","unstructured":"Meta (2026, March 21). Meta Sustainability Report 2025. Available online: https:\/\/sustainability.atmeta.com\/2025-sustainability-report\/."},{"key":"ref_24","unstructured":"TOP500\/Green500 Consortium (2026, March 21). The Green500 List. Available online: https:\/\/www.top500.org\/lists\/green500\/."},{"key":"ref_25","unstructured":"NVIDIA (2026, March 21). DGX System Software Stack Installation Guide. Available online: https:\/\/docs.nvidia.com\/dgx\/dgx-software-stack-installation-guide\/."},{"key":"ref_26","unstructured":"NVIDIA (2026, March 21). DGX Solution Stack Whitepaper. Available online: https:\/\/www.scribd.com\/document\/797155222\/dgx-solution-stack-whitepaper."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Reddi, V.J., Cheng, C., Kanter, D., Mattson, P., Schmuelling, G., Wu, C.J., Anderson, B., Breughe, M., Charlebois, M., and Chou, W. (June, January 30). MLPerf Inference Benchmark. Proceedings of the 2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), Virtual.","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Huo, H., Li, P., Xin, C., Wang, Y., Zhou, Y., Li, W., Lu, Y., Chen, T., and Wang, J. (2025). Life Cycle Cost Modeling and Multi-Dimensional Decision-Making of Multi-Energy Storage System in Different Source-Grid-Load Scenarios. Processes, 13.","DOI":"10.3390\/pr13082400"},{"key":"ref_29","unstructured":"U.S. Department of Energy (2026, March 21). Levelized Cost of Energy (LCOE), Available online: https:\/\/www.energy.gov\/sites\/prod\/files\/2015\/08\/f25\/LCOE.pdf."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yuan, X., Chen, L., Sheng, X., Liu, M., Xu, Y., Tang, Y., Wang, Q., Ma, Q., and Zuo, J. (2021). Life cycle cost of electricity production: A comparative study of coal-fired, biomass, and wind power in China. Energies, 14.","DOI":"10.3390\/en14123463"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Curcio, E. (2025). Introducing LCOAI: A standardized economic metric for evaluating AI deployment costs. arXiv.","DOI":"10.2139\/ssrn.5377442"},{"key":"ref_32","unstructured":"Beyer, B., Jones, C., Petoff, J., and Murphy, N.R. (2016). Site Reliability Engineering: How Google Runs Production Systems, O\u2019Reilly Media."},{"key":"ref_33","unstructured":"U.S. Department of Energy (2026, March 21). Artificial Intelligence Strategy, Available online: https:\/\/www.energy.gov\/sites\/default\/files\/2025-09\/EXEC-2025-010630%20-%20250923_%20DOE%20AI%20Strategy%20VFinal.pdf."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1049\/iet-rpg.2015.0378","article-title":"Integration of renewable distributed generators into the distribution system: A review","volume":"10","author":"Adefarati","year":"2016","journal-title":"Iet Renew. Power Gener."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"973","DOI":"10.30574\/wjarr.2024.21.1.0112","article-title":"Microgrid systems in U.S. energy infrastructure: A comprehensive review: Exploring decentralized energy solutions, their benefits, and challenges in regional implementation","volume":"21","author":"Onyinyechukwu","year":"2024","journal-title":"World J. Adv. Res. Rev."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"106059","DOI":"10.1109\/ACCESS.2022.3211511","article-title":"Microgrids and Resilience: A Review","volume":"10","author":"Hamidieh","year":"2022","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, J.H., and Lin, J.H. (2025). Review of microgrids to enhance power system resilience. Eng. Proc., 92.","DOI":"10.3390\/engproc2025092082"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"107979","DOI":"10.1016\/j.eiar.2025.107979","article-title":"Impact of cropland use transformation on ecosystem carbon sinks in a typical agroforestry mixed region: An analysis from explicit and implicit perspectives","volume":"115","author":"Zhou","year":"2025","journal-title":"Environ. Impact Assess. Rev."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"105432","DOI":"10.1016\/j.tust.2023.105432","article-title":"Towards automated 3D evaluation of water leakage on a tunnel face via improved GAN and self-attention DL model","volume":"142","author":"Wu","year":"2023","journal-title":"Tunn. Undergr. Space Technol."},{"key":"ref_40","unstructured":"(2026, March 21). PJM Board Plan for Integrating Large Loads (Connect-and-Manage, BYOG)\u2014PJM Inside Lines. Available online: https:\/\/insidelines.pjm.com\/pjm-board-outlines-plans-to-integrate-large-loads-reliably\/."},{"key":"ref_41","unstructured":"(2026, March 21). FERC Directive to PJM on Rules for AI-Driven Data Centers\/Large Loads\u2014FERC, Available online: https:\/\/www.ferc.gov\/news-events\/news\/ferc-directs-nations-largest-grid-operator-create-new-rules-embrace-innovation-and."},{"key":"ref_42","unstructured":"(2026, March 21). Resource Adequacy Risks with Demand Growth Including Data Centers\u2014NERC Newsroom. Available online: https:\/\/www.nerc.com\/newsroom\/resource-adequacy-risks-intensify-across-north-america-as-demand-growth-surges."},{"key":"ref_43","unstructured":"(2026, March 21). Long-Term Reliability Assessment Referencing Data Center Growth and \u201cData Center Alley\u201d\u2014NERC LTRA 2024. Available online: https:\/\/www.nerc.com\/globalassets\/our-work\/assessments\/2024-ltra_corrected_july_2025.pdf."},{"key":"ref_44","unstructured":"(2026, March 21). Texas SB 6 Bill Text (Large-Load Interconnection and Operation Framework)\u2013Texas Legislature, Available online: https:\/\/capitol.texas.gov\/tlodocs\/89R\/billtext\/pdf\/SB00006H.pdf."},{"key":"ref_45","unstructured":"(2026, March 21). PJM Filing and Description of Connect-and-Manage Curtailment Exposure Details\u2014PJM Inside Lines. Available online: https:\/\/insidelines.pjm.com\/pjm-files-price-collar-expedited-interconnection-as-part-of-large-load-plan\/."},{"key":"ref_46","unstructured":"(2026, March 21). PJM Data Miner 2, Day-Ahead Hourly LMPs Feed Definition. Available online: https:\/\/dataminer2.pjm.com\/feed\/da_hrl_lmps\/definition."},{"key":"ref_47","unstructured":"(2026, March 21). PJM Emergency Procedures Postings and Message Definitions. Available online: https:\/\/emergencyprocedures.pjm.com\/ep\/pages\/messagedefinitions.jsf."},{"key":"ref_48","unstructured":"(2026, March 21). NREL Cambium Documentation and Dataset Access (Hourly Emissions Metrics, Including LRMER), Available online: https:\/\/docs.nrel.gov\/docs\/fy24osti\/88507.pdf."},{"key":"ref_49","unstructured":"(2026, March 21). EPA eGRID Detailed Data and Summary Tables (Location-Based Emissions Factors Baseline), Available online: https:\/\/www.epa.gov\/egrid\/detailed-data."},{"key":"ref_50","unstructured":"(2026, March 21). GHG Protocol, Scope 2 Guidance (Location-Based and Market-Based Methods). Available online: https:\/\/ghgprotocol.org\/sites\/default\/files\/2023-03\/Scope%202%20Guidance.pdf."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"112780","DOI":"10.1016\/j.rser.2022.112780","article-title":"External carbon costs and internal carbon pricing","volume":"168","author":"Trinks","year":"2022","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"107187","DOI":"10.1016\/j.tej.2022.107187","article-title":"The quest to quantify the value of lost load: A critical review of the economics of power outages","volume":"35","author":"Gorman","year":"2022","journal-title":"Electr. J."},{"key":"ref_53","unstructured":"Viegand Maag\u00f8e (2026, March 21). Energy Efficiency Metrics for Data Centres: Final Report; Prepared for IEA 4E EDNA. Available online: https:\/\/www.iea-4e.org\/wp-content\/uploads\/2022\/10\/EDNA-Studies-Metrics-for-data-centre-efficiency-Final.pdf."},{"key":"ref_54","unstructured":"Google (2026, March 21). 24\/7 Carbon-Free Energy: Methodologies and Metrics. Available online: https:\/\/sustainability.google\/reports\/24x7-carbon-free-energy-methodologies-metrics\/."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"101808","DOI":"10.1016\/j.joule.2024.101808","article-title":"24\/7 carbon-free electricity matching accelerates adoption of advanced clean energy technologies","volume":"9","author":"Riepin","year":"2025","journal-title":"Joule"},{"key":"ref_56","unstructured":"Electric Power Research Institute (EPRI) (2022). 24\/7 Carbon-Free Energy, Electric Power Research Institute. Available online: https:\/\/restservice.epri.com\/publicattachment\/93073."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1002\/for.3198","article-title":"A multifrequency data fusion deep learning model for carbon price prediction","volume":"44","author":"Xiao","year":"2025","journal-title":"J. Forecast."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"2632","DOI":"10.1109\/TMECH.2024.3456250","article-title":"Embodied intelligence toward future smart manufacturing in the era of AI foundation model","volume":"30","author":"Ren","year":"2025","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Fan, D., Liu, M., Shao, Y., Yang, L., Liu, Y., Zhang, Y., Ren, Y., and Wang, Z. (Engineering, 2025). Domain-Specific Large Language Model for Maintenance Decision-Making on Wind Farms by Labeled-Data-Supervised Fine-Tuning, Engineering, in press.","DOI":"10.1016\/j.eng.2025.12.019"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/432\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T04:17:37Z","timestamp":1779164257000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/5\/432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,1]]},"references-count":59,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["info17050432"],"URL":"https:\/\/doi.org\/10.3390\/info17050432","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,1]]}}}