{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:35:11Z","timestamp":1772112911916,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010607","name":"Universit\u00e0 degli Studi di Perugia","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100010607","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Grid Computing"],"published-print":{"date-parts":[[2023,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The continuous growth of data production in almost all scientific areas raises new problems in data access and management, especially in a scenario where the end-users, as well as the resources that they can access, are worldwide distributed. This work is focused on the data caching management in a Data Lake infrastructure in the context of the High Energy Physics field. We are proposing an autonomous method, based on Reinforcement Learning techniques, to improve the user experience and to contain the maintenance costs of the infrastructure.<\/jats:p>","DOI":"10.1007\/s10723-023-09664-z","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T07:02:05Z","timestamp":1689145325000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Smart Caching in a Data Lake for High Energy Physics Analysis"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7125-2905","authenticated-orcid":false,"given":"Tommaso","family":"Tedeschi","sequence":"first","affiliation":[]},{"given":"Marco","family":"Baioletti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0843-4108","authenticated-orcid":false,"given":"Diego","family":"Ciangottini","sequence":"additional","affiliation":[]},{"given":"Valentina","family":"Poggioni","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2991-6384","authenticated-orcid":false,"given":"Daniele","family":"Spiga","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5021-7759","authenticated-orcid":false,"given":"Loriano","family":"Storchi","sequence":"additional","affiliation":[]},{"given":"Mirco","family":"Tracolli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"9664_CR1","unstructured":"Pettersson, T.S., Lef\u00e8vre, P.: The Large Hadron Collider: conceptual design. Technical report (Oct 1995). https:\/\/cds.cern.ch\/record\/291782"},{"key":"9664_CR2","doi-asserted-by":"publisher","first-page":"08003","DOI":"10.1088\/1748-0221\/3\/08\/S08003","volume":"3","author":"The ATLAS Collaboration","year":"2008","unstructured":"The ATLAS Collaboration: The ATLAS experiment at the CERN Large Hadron Collider. J. Instrum. 3, 08003 (2008)","journal-title":"J. Instrum."},{"issue":"08","key":"9664_CR3","doi-asserted-by":"publisher","first-page":"08004","DOI":"10.1088\/1748-0221\/3\/08\/S08004","volume":"3","author":"The CMS Collaboration","year":"2008","unstructured":"The CMS Collaboration: The CMS experiment at the CERN LHC. J. Instrum. 3(08), 08004\u201308004 (2008)","journal-title":"J. Instrum."},{"issue":"08","key":"9664_CR4","doi-asserted-by":"publisher","first-page":"08002","DOI":"10.1088\/1748-0221\/3\/08\/S08002","volume":"3","author":"The ALICE Collaboration","year":"2008","unstructured":"The ALICE Collaboration: The ALICE experiment at the CERN LHC. J. Instrum. 3(08), 08002 (2008)","journal-title":"J. Instrum."},{"issue":"08","key":"9664_CR5","doi-asserted-by":"publisher","first-page":"08005","DOI":"10.1088\/1748-0221\/3\/08\/S08005","volume":"3","author":"The LHCb Collaboration","year":"2008","unstructured":"The LHCb Collaboration: The LHCb detector at the LHC. J. instrum. 3(08), 08005 (2008)","journal-title":"J. instrum."},{"key":"9664_CR6","unstructured":"CMS Offline Software and Computing: CMS Phase-2 Computing Model: Update Document. CERN-CMS-NOTE-2022-008, available on the CERN Document Server as https:\/\/cds.cern.ch\/record\/2815292. (2022)"},{"key":"9664_CR7","doi-asserted-by":"crossref","unstructured":"Bird, I., Campana, S., Girone, M., Espinal, X., McCance, G., Schovancov\u00e1, J.: Architecture and prototype of a WLCG data lake for HL-LHC. In: EPJ Web of Conferences, vol. 214, p. 04024 (2019). EDP Sciences","DOI":"10.1051\/epjconf\/201921404024"},{"key":"9664_CR8","unstructured":"Kadochnikov, I., Bird, I., McCance, G., Schovancova, J., Girone, M., Campana, S., Currul, X.E.: WLCG data lake prototype for HL-LHC. Advisory committee, 127 (2018)"},{"key":"9664_CR9","doi-asserted-by":"crossref","unstructured":"Tedeschi, T., Tracolli, M., Ciangottini, D., Spiga, D., Storchi, L., Baioletti, M., Poggioni, V.: Reinforcement Learning for Smart Caching at the CMS experiment. In: Proceedings of International Symposium on Grids & Clouds 2021 PoS(ISGC2021), vol. 378, p. 009 (2021)","DOI":"10.22323\/1.378.0009"},{"key":"9664_CR10","unstructured":"Dixon, J.: Pentaho, Hadoop and Data Lakes. https:\/\/jamesdixon.wordpress.com\/2010\/10\/14\/pentaho-hadoop-and-data-lakes\/. Last check April 9, 2020 (2010)"},{"key":"9664_CR11","doi-asserted-by":"crossref","unstructured":"Adhikari, V.K., Guo, Y., Hao, F., Varvello, M., Hilt, V., Steiner, M., Zhang, Z.-L.: Unreeling netflix: Understanding and improving multi-CDN movie delivery. In: 2012 Proceedings IEEE INFOCOM, pp. 1620\u20131628 (2012). IEEE","DOI":"10.1109\/INFCOM.2012.6195531"},{"key":"9664_CR12","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (2018)"},{"key":"9664_CR13","first-page":"237","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intel. Res. 4, 237\u2013285 (1996)","journal-title":"J. Artif. Intel. Res."},{"key":"9664_CR14","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013)"},{"issue":"3","key":"9664_CR15","first-page":"729","volume":"12","author":"MA Wiering","year":"2012","unstructured":"Wiering, M.A., Van Otterlo, M.: Reinforcement learning. Adapt. Learn. Optim. 12(3), 729 (2012)","journal-title":"Reinforcement learning. Adapt. Learn. Optim."},{"key":"9664_CR16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"7540","key":"9664_CR17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature. 518(7540), 529\u2013533 (2015)","journal-title":"Nature."},{"issue":"3","key":"9664_CR18","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/COMST.2015.2420097","volume":"17","author":"M Zhang","year":"2015","unstructured":"Zhang, M., Luo, H., Zhang, H.: A survey of caching mechanisms in information-centric networking. IEEE Commun. Surv. Tutor. 17(3), 1473\u20131499 (2015)","journal-title":"IEEE Commun. Surv. Tutor."},{"issue":"4","key":"9664_CR19","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1145\/954339.954341","volume":"35","author":"S Podlipnig","year":"2003","unstructured":"Podlipnig, S., B\u00f6sz\u00f6rmenyi, L.: A survey of web cache replacement strategies. ACM Comput. Surv. (CSUR) 35(4), 374\u2013398 (2003)","journal-title":"ACM Comput. Surv. (CSUR)"},{"issue":"4","key":"9664_CR20","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/COMST.2020.3005361","volume":"22","author":"C Chen","year":"2020","unstructured":"Chen, C., Wang, C., Qiu, T., Atiquzzaman, M., Wu, D.O.: Caching in vehicular named data networking: Architecture, schemes and future directions. IEEE Commun. Surv. Tutor. 22(4), 2378\u20132407 (2020)","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"9664_CR21","doi-asserted-by":"crossref","unstructured":"Lei, L., You, L., Dai, G., Vu, T.X., Yuan, D., Chatzinotas, S.: A deep learning approach for optimizing content delivering in cache-enabled hetnet. In: 2017 International Symposium on Wireless Communication Systems (ISWCS), IEEE, pp. 449\u2013453 (2017)","DOI":"10.1109\/ISWCS.2017.8108157"},{"key":"9664_CR22","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Verma, S., Ramadan, E., Babaie, P., Zhang, Z.-L.: Deepcache: A deep learning based framework for content caching. In: Proceedings of the 2018 Workshop on Network Meets AI & ML, pp. 48\u201353 (2018)","DOI":"10.1145\/3229543.3229555"},{"key":"9664_CR23","unstructured":"Lykouris, T., Vassilvitskii, S.: Competitive caching with machine learned advice. arXiv:1802.05399 (2018)"},{"key":"9664_CR24","doi-asserted-by":"crossref","unstructured":"Herodotou, H.: Autocache: Employing machine learning to automate caching in distributed file systems. International Conference on Data Engineering Workshops (ICDEW), IEEE, pp. 133\u2013139 (2019)","DOI":"10.1109\/ICDEW.2019.00-21"},{"key":"9664_CR25","doi-asserted-by":"crossref","unstructured":"Sadeghi, A., Wang, G., Giannakis, G.B.: Deep reinforcement learning for adaptive caching in hierarchical content delivery\u00a0networks. IEEE Trans. Cogn. Commun. Netw. 5(4), 1024\u20131033 (2019)","DOI":"10.1109\/TCCN.2019.2936193"},{"key":"9664_CR26","unstructured":"Dulac-Arnold, G., Evans, R., van\u00a0Hasselt, H., Sunehag, P., Lillicrap, T., Hunt, J., Mann, T., Weber, T., Degris, T., Coppin, B.: Deep reinforcement learning in large discrete action spaces. arXiv:1512.07679 (2015)"},{"key":"9664_CR27","doi-asserted-by":"crossref","unstructured":"Zhong, C., Gursoy, M.C., Velipasalar, S.: A deep reinforcement learning-based framework for content caching. In: 2018 52nd Annual Conference on Information Sciences and Systems (CISS), IEEE, pp. 1\u20136 (2018)","DOI":"10.1109\/CISS.2018.8362276"},{"key":"9664_CR28","unstructured":"Alabed, S.: RLCache: automated cache management using reinforcement learning. arXiv:1909.13839. (2019)"},{"key":"9664_CR29","doi-asserted-by":"crossref","unstructured":"Tracolli, M., Baioletti, M., Ciangottini, D., Poggioni, V., Spiga, D.: An intelligent cache management for data analysis at cms. In: International conference on computational science and its applications, Springer, pp. 320\u2013332 (2020)","DOI":"10.1007\/978-3-030-58802-1_24"},{"key":"9664_CR30","unstructured":"Tracolli, M.: Open Source code. Available at https:\/\/github.com\/Cloud-PG\/smart-cache\/tree\/master (2022)"},{"key":"9664_CR31","unstructured":"Tedeschi, T.: Open Source code. Available at https:\/\/github.com\/Cloud-PG\/smart-cache\/tree\/dQl_add_evic_no_gym (2022)"},{"key":"9664_CR32","doi-asserted-by":"crossref","unstructured":"Kuznetsov, V., Li, T., Giommi, L., Bonacorsi, D., Wildish, T.: Predicting dataset popularity for the CMS experiment. arXiv:1602.07226arXiv:1602.07226. (2016)","DOI":"10.1088\/1742-6596\/762\/1\/012048"},{"issue":"2","key":"9664_CR33","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s10723-018-9436-4","volume":"16","author":"M Meoni","year":"2018","unstructured":"Meoni, M., Perego, R., Tonellotto, N.: Dataset popularity prediction for caching of CMS big data. J. Grid Comput. 16(2), 211\u2013228 (2018)","journal-title":"J. Grid Comput."},{"key":"9664_CR34","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-Scale machine learning on heterogeneous systems. Softw. available from tensorflow.org. (2015). https:\/\/www.tensorflow.org\/"},{"key":"9664_CR35","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980. (2014). https:\/\/doi.org\/10.48550\/ARXIV.1412.6980","DOI":"10.48550\/ARXIV.1412.6980"},{"issue":"1","key":"9664_CR36","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","volume":"35","author":"PJ Huber","year":"1964","unstructured":"Huber, P.J.: Robust Estimation of a Location Parameter. Ann. Math. Stat. 35(1), 73\u2013101 (1964). https:\/\/doi.org\/10.1214\/aoms\/1177703732","journal-title":"Ann. Math. Stat."}],"container-title":["Journal of Grid Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-023-09664-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10723-023-09664-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-023-09664-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,3]],"date-time":"2023-10-03T08:08:32Z","timestamp":1696320512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10723-023-09664-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["9664"],"URL":"https:\/\/doi.org\/10.1007\/s10723-023-09664-z","relation":{},"ISSN":["1570-7873","1572-9184"],"issn-type":[{"value":"1570-7873","type":"print"},{"value":"1572-9184","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"23 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no potential conflicts of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"42"}}