{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:55:55Z","timestamp":1781870155888,"version":"3.54.5"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Two converging crises\u2014uncontrolled operational expenditure and significant environmental hazards\u2014have been aggravated by the exponential scaling of cloud infrastructure. This has led to a greater focus on the efficiency of Financial Operations (FinOps). Current monitoring methods exhibit a major flaw: passive dashboards require constant human monitoring and lead to alert fatigue, whereas deep learning models require substantial Graphics Processing Unit (GPU) resources and operate as opaque \u201cblack boxes.\u201d This lack of interpretability contradicts the sustainability goals these tools promise to support. This study proposes Eco-FinOps, a causal-agentic framework that autonomously and energy-efficiently optimizes cloud costs, designed strictly for commodity Central Processing Unit (CPU) environments without discrete GPU requirements. The system uses Polars-based telemetry ingestion, the Peter-Clark (Algorithm) (PC) algorithm for causal graph construction, and DoWhy for effect estimation to mathematically distinguish genuine workload fluctuations from inefficient resource usage. This study targets the \u201czombie\u201d resource pattern\u2014provisioned instances that utilize only 0.2%-5% CPU while maintaining 60%\u201390% memory consumption. Furthermore, a LangGraph-coordinated Retrieval-Augmented Generation (RAG) pipeline enables Small Language Models to generate auditable, human-verifiable remediation scripts. Evaluated on five fault-injection scenarios from the Alibaba Cluster Trace dataset, the framework achieves a Precision of 0.89, a recall of 0.86, and an F1-score of 0.87. Causal verification successfully eliminates 39% of false positive anomalies, raising Precision by 38 points over static threshold rules and outperforming neural autoencoder baselines by 15 F1 points.<\/jats:p>","DOI":"10.3389\/frai.2026.1861514","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:34:02Z","timestamp":1781868842000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Eco-FinOps: a causal-agentic framework for energy-efficient and explainable cloud cost optimization"],"prefix":"10.3389","volume":"9","author":[{"given":"P.","family":"Sreejindeth","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Padmavathy","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"101925","DOI":"10.1016\/j.phycom.2022.101925","article-title":"Autonomous drl-based energy efficient vm consolidation for cloud data centers","volume":"55","author":"Abbas","year":"2022","journal-title":"Phys. Commun"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.future.2015.01.007","article-title":"Cost-aware challenges for workflow scheduling approaches in cloud computing environments: taxonomy and opportunities","volume":"50","author":"Alkhanak","year":"2015","journal-title":"Fut. Gen. Comput. Syst"},{"key":"B3","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MC.2007.443","article-title":"The case for energy-proportional computing","volume":"40","author":"Barroso","year":"2007","journal-title":"Computer"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1887","DOI":"10.1109\/INFOCOM.2014.6848128","article-title":"\u201cCauseinfer: automatic and distributed performance diagnosis with hierarchical causality graph in large distributed systems,\u201d","author":"Chen","year":"2014","journal-title":"IEEE INFOCOM 2014"},{"key":"B5","doi-asserted-by":"publisher","first-page":"131961","DOI":"10.1016\/j.eswa.2026.131961","article-title":"Causalm-net: an llm-guided causal graph and state-space learning framework for fault diagnosis in cloud native 5g base stations","volume":"317","author":"Dui","year":"2026","journal-title":"Expert Syst. Appl"},{"key":"B6","doi-asserted-by":"publisher","first-page":"100528","DOI":"10.1016\/j.suscom.2021.100528","article-title":"Improving the cost efficiency of large-scale cloud systems running hybrid workloads - a case study of alibaba cluster traces","volume":"30","author":"Everman","year":"2021","journal-title":"Sustain. Comput.: Inform. Syst"},{"key":"B7","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/1273440.1250665","article-title":"\u201cPower provisioning for a warehouse-sized computer,\u201d","author":"Fan","year":"2007","journal-title":"Proceedings of the 34th annual international symposium on Computer architecture, SPAA07"},{"key":"B8","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1016\/j.future.2011.12.002","article-title":"Energy-efficient and multifaceted resource management for profit-driven virtualized data centers","volume":"28","author":"Goiri","year":"2012","journal-title":"Fut. Gen. Comput. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3071","DOI":"10.1109\/TSE.2023.3241299","article-title":"Trinityrcl: multi-granular and code-level root cause localization using multiple types of telemetry data in microservice systems","volume":"49","author":"Gu","year":"2023","journal-title":"IEEE Trans. Softw. Eng"},{"key":"B10","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.future.2012.05.018","article-title":"Enabling cost-aware and adaptive elasticity of multi-tier cloud applications","volume":"32","author":"Han","year":"2014","journal-title":"Fut. Gen. Comput. Syst"},{"key":"B11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3744556","article-title":"Monitoring data for anomaly detection in cloud-based systems: a systematic mapping study","volume":"35","author":"Hrusto","year":"2026","journal-title":"ACM Trans. Softw. Eng. Methodol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.jpdc.2019.12.014","article-title":"Utilization-prediction-aware virtual machine consolidation approach for energy-efficient cloud data centers","volume":"139","author":"Hsieh","year":"2020","journal-title":"J. Parallel Distrib. Comput"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2970","DOI":"10.1145\/3543507.3583338","article-title":"\u201cLook deep into the microservice system anomaly through very sparse logs,\u201d","author":"Jiang","year":"2023","journal-title":"Proceedings of the ACM Web Conference 2023, WWW 23"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-022-00296-4","article-title":"Anomaly detection in microservice environments using distributed tracing data analysis and nlp","author":"Kohyarnejadfard","year":"2022","journal-title":"J. Cloud Comput"},{"key":"B16","doi-asserted-by":"publisher","first-page":"103017","DOI":"10.1016\/j.jnca.2021.103017","article-title":"Cost-aware automatic scaling and workload-aware replica management for edge-cloud environment","volume":"180","author":"Li","year":"","journal-title":"J. Netw. Comput. Applic"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1109\/SRDS69199.2025.00024","article-title":"\u201cRootscan: unveiling microservice anomalies through fine-grained, interpretable root cause analysis,\u201d","volume-title":"2025 44th International Symposium on Reliable Distributed Systems (SRDS)","author":"Li","year":"2025"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IWQOS52092.2021.9521340","article-title":"\u201cPractical root cause localization for microservice systems via trace analysis,\u201d","author":"Li","year":"","journal-title":"2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1109\/ICDM.2008.17","article-title":"\u201cIsolation forest,\u201d","author":"Liu","year":"2008","journal-title":"2008 Eighth IEEE International Conference on Data Mining"},{"key":"B20","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1093\/comjnl\/bxt009","article-title":"Cost-aware cloud service request scheduling for saas providers","volume":"57","author":"Liu","year":"2013","journal-title":"Comput. J"},{"key":"B21","doi-asserted-by":"publisher","first-page":"77550","DOI":"10.1109\/ACCESS.2025.3565220","article-title":"Anomaly detection and root cause analysis in cloud-native environments using large language models and bayesian networks","volume":"13","author":"Pedroso","year":"2025","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","first-page":"103885","DOI":"10.1016\/j.jnca.2024.103885","article-title":"Efficient cloud data center: an adaptive framework for dynamic virtual machine consolidation","volume":"226","author":"Rozehkhani","year":"2024","journal-title":"J. Netw. Comput. Applic"},{"key":"B23","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.future.2014.06.008","article-title":"Towards high-available and energy-efficient virtual computing environments in the cloud","volume":"40","author":"Sampaio","year":"2014","journal-title":"Fut. Gen. Comput. Syst"},{"key":"B24","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.future.2020.03.059","article-title":"Detection of time series patterns and periodicity of cloud computing workloads","volume":"109","author":"St-Onge","year":"2020","journal-title":"Fut. Gen. Comput. Syst"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/TNET.2012.2188837","article-title":"G-rca: a generic root cause analysis platform for service quality management in large ip networks","volume":"20","author":"Yan","year":"2012","journal-title":"IEEE\/ACM Trans. Network"},{"key":"B26","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1109\/TASE.2015.2427234","article-title":"Cawsac: Cost-aware workload scheduling and admission control for distributed cloud data centers","volume":"13","author":"Yuan","year":"2016","journal-title":"IEEE Trans. Autom. Sci. Eng"},{"key":"B27","doi-asserted-by":"publisher","first-page":"107938","DOI":"10.1016\/j.infsof.2025.107938","article-title":"Mhp-rca: multivariate hawkes process-based root cause analysis in microservice systems","volume":"189","author":"Zhang","year":"2026","journal-title":"Inform. Softw. Technol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41019-025-00335-5","article-title":"Retrieval-augmented generation for ai-generated content: a survey","volume":"11","author":"Zhao","year":"2026","journal-title":"Data Sci. Eng"},{"key":"B29","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1109\/ISSRE59848.2023.00033","article-title":"\u201cTracestream: anomalous service localization based on trace stream clustering with online feedback,\u201d","author":"Zhou","year":"2023","journal-title":"2023 IEEE 34th International Symposium on Software Reliability Engineering (ISSRE)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"112145","DOI":"10.1016\/j.jss.2024.112145","article-title":"Microirc: instance-level root cause localization for microservice systems","volume":"216","author":"Zhu","year":"2024","journal-title":"J. Syst. Softw"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1861514\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:34:03Z","timestamp":1781868843000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1861514\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":30,"alternative-id":["10.3389\/frai.2026.1861514"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1861514","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]},"article-number":"1861514"}}