{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:20:21Z","timestamp":1767313221808,"version":"3.48.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032068170","type":"print"},{"value":"9783032068187","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-06818-7_14","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:16:51Z","timestamp":1767313011000},"page":"252-273","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Runtime Management of\u00a0Artificial Intelligence Applications Through Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7581-5955","authenticated-orcid":false,"given":"Riccardo","family":"Cavadini","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6495-5717","authenticated-orcid":false,"given":"Hamta","family":"Sedghani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6549-924X","authenticated-orcid":false,"given":"Federica","family":"Filippini","sequence":"additional","affiliation":[]},{"given":"Danilo","family":"Ardagna","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"14_CR1","unstructured":"Argo Workflows \u2014 argoproj.github.io. https:\/\/argoproj.github.io\/workflows\/, Accessed 06 Sept 2024"},{"key":"14_CR2","unstructured":"Artificial Intelligence Market Size & Trends, Growth Analysis, Forecast [2030] \u2014 marketsandmarkets.com. https:\/\/www.marketsandmarkets.com\/Market-Reports\/artificial-intelligence-market-74851580.html, Accessed 11 Sept 2024"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Bai, H., Xu, M., Ye, K., Buyya, R., Xu, C.: Drpc: distributed reinforcement learning approach for scalable resource provisioning in container-based clusters. IEEE Trans. Serv. Comput. (2024)","DOI":"10.1109\/TSC.2024.3433388"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cao, B., Ye, H., Liu, J., Tang, B., Tao, Z., Deng, S.: Smart: cost-aware service migration path selection based on deep reinforcement learning. IEEE Trans. Intell. Transp. Syst. (2024)","DOI":"10.1109\/TITS.2024.3378920"},{"issue":"23","key":"14_CR5","doi-asserted-by":"publisher","first-page":"28832","DOI":"10.1007\/s10489-023-05065-7","volume":"53","author":"Z Chai","year":"2023","unstructured":"Chai, Z., Hou, H., Li, Y.: A dynamic queuing model based distributed task offloading algorithm using deep reinforcement learning in mobile edge computing. Appl. Intell. 53(23), 28832\u201328847 (2023)","journal-title":"Appl. Intell."},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xiong, B., Chen, X., Min, G., Li, J.: Joint computation offloading and resource allocation in multi-edge smart communities with personalized federated deep reinforcement learning. IEEE Trans. Mobile Comput. (2024)","DOI":"10.1109\/TMC.2024.3396511"},{"key":"14_CR7","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.future.2023.12.032","volume":"154","author":"N Filinis","year":"2024","unstructured":"Filinis, N., et al.: Intent-driven orchestration of serverless applications in the computing continuum. Future Generation Comput. Syst. 154, 72\u201386 (2024)","journal-title":"Future Generation Comput. Syst."},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Filippini, F., et al.: FIGARO: reinForcement learnInG mAnagement acRoss computing cOntinua. In: 3rd Workshop on Distributed Machine Learning for the Intelligence Computing Continuum at ACM\/IEEE UCC 2023 (to appear) (2023)","DOI":"10.1145\/3603166.3632565"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Giagkos, D., Tzenetopoulos, A., Masouros, D., Soudris, D., Xydis, S.: Darly: deep reinforcement learning for QOS-aware scheduling under resource heterogeneity optimizing serverless video analytics. In: 2023 IEEE 16th International Conference on Cloud Computing (CLOUD), pp.\u00a01\u20133. IEEE (2023)","DOI":"10.1109\/CLOUD60044.2023.00079"},{"key":"14_CR10","unstructured":"Graesser, L., Keng, W.L.: Foundations of deep reinforcement learning: theory and practice in python. Addison-Wesley Professional, 1st edn. (2019)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Jayanetti, A., Halgamuge, S., Buyya, R.: A deep reinforcement learning approach for cost optimized workflow scheduling in cloud computing environments. arXiv preprint arXiv:2408.02926 (2024)","DOI":"10.1145\/3685767.3685780"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Jayanetti, A., Halgamuge, S., Buyya, R.: Reinforcement learning based workflow scheduling in cloud and edge computing environments: a taxonomy, review and future directions. arXiv preprint arXiv:2408.02938 (2024)","DOI":"10.1145\/3685767.3685780"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Lackinger, A., et al.: Inference load-aware orchestration for hierarchical federated learning. arXiv preprint arXiv:2407.16836 (2024)","DOI":"10.1109\/LCN60385.2024.10639809"},{"key":"14_CR14","volume-title":"Quantitative system performance: computer system analysis using queueing network models","author":"ED Lazowska","year":"1984","unstructured":"Lazowska, E.D., Zahorjan, J., Graham, G.S., Sevcik, K.C.: Quantitative system performance: computer system analysis using queueing network models. Prentice-Hall, Inc (1984)"},{"key":"14_CR15","doi-asserted-by":"publisher","first-page":"112762","DOI":"10.1109\/ACCESS.2020.3002895","volume":"8","author":"S Li","year":"2020","unstructured":"Li, S., Li, B., Zhao, W.: Joint optimization of caching and computation in multi-server NOMA-MEC system via reinforcement learning. IEEE Access 8, 112762\u2013112771 (2020)","journal-title":"IEEE Access"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Task placement and resource allocation for edge machine learning: a GNN-based multi-agent reinforcement learning paradigm (2023)","DOI":"10.1109\/TPDS.2023.3313779"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhang, J., Cheng, X., Hong, Y., Chen, Z., Xing, X.: Computation offloading in resource-constrained edge computing systems based on deep reinforcement learning. IEEE Trans. Comput. (2023)","DOI":"10.1109\/TC.2023.3321938"},{"key":"14_CR18","unstructured":"Ray: RLLib: Industry-Grade Reinforcement Learning. https:\/\/docs.ray.io\/en\/latest\/rllib\/index.html, Accessed 17 Sept 2024"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection (2016). https:\/\/arxiv.org\/abs\/1506.02640","DOI":"10.1109\/CVPR.2016.91"},{"issue":"3","key":"14_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10723-021-09570-2","volume":"19","author":"S Risco","year":"2021","unstructured":"Risco, S., Molt\u00f3, G., Naranjo, D.M., Blanquer, I.: Serverless workflows for containerised applications in the cloud continuum. J. Grid Comput. 19(3), 1\u201318 (2021)","journal-title":"J. Grid Comput."},{"key":"14_CR21","unstructured":"Ross, S., Bagnell, D.: Efficient reductions for imitation learning. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol.\u00a09, pp. 661\u2013668. PMLR, Chia Laguna Resort, Sardinia (2010). https:\/\/proceedings.mlr.press\/v9\/ross10a.html"},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Rossi, F., Nardelli, M., Cardellini, V.: Horizontal and vertical scaling of container-based applications using reinforcement learning. In: IEEE CLOUD\u201919, pp. 329\u2013338 (2019). https:\/\/doi.org\/10.1109\/CLOUD.2019.00061","DOI":"10.1109\/CLOUD.2019.00061"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Sedghani, H., Filippini, F., Ardagna, D.: A random greedy based design time tool for AI applications component placement and resource selection in computing continua. In: IEEE EDGE\u201921, pp. 32\u201340 (2021)","DOI":"10.1109\/EDGE53862.2021.00014"},{"key":"14_CR24","unstructured":"Song, A., Lazarev, N., Gohil, V., Li, Y.: Scarlet: serverless container autoscaling with reinforcement learning environments"},{"issue":"3","key":"14_CR25","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1109\/TPDS.2022.3231981","volume":"34","author":"A Staffolani","year":"2023","unstructured":"Staffolani, A., Darvariu, V.A., Bellavista, P., Musolesi, M.: Rlq: Workload allocation with reinforcement learning in distributed queues. IEEE Transa. Parallel Distr. Syst. 34(3), 856\u2013868 (2023)","journal-title":"IEEE Transa. Parallel Distr. Syst."},{"issue":"3","key":"14_CR26","doi-asserted-by":"publisher","first-page":"3930","DOI":"10.1109\/TVT.2022.3219058","volume":"72","author":"Y Su","year":"2023","unstructured":"Su, Y., Fan, W., Gao, L., Qiao, L., Liu, Y., Wu, F.: Joint DNN partition and resource allocation optimization for energy-constrained hierarchical edge-cloud systems. IEEE Trans. Veh. Technol. 72(3), 3930\u20133944 (2023)","journal-title":"IEEE Trans. Veh. Technol."},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Valmari, A.: The state explosion problem. In: Advanced Course on Petri Nets, pp. 429\u2013528. Springer (1996)","DOI":"10.1007\/3-540-65306-6_21"},{"issue":"2","key":"14_CR28","doi-asserted-by":"publisher","first-page":"1817","DOI":"10.1109\/TNSM.2022.3213575","volume":"20","author":"W Wei","year":"2023","unstructured":"Wei, W., Gu, H., Wang, K., Li, J., Zhang, X., Wang, N.: Multi-dimensional resource allocation in distributed data centers using deep reinforcement learning. IEEE Trans. Netw. Service Manag. 20(2), 1817\u20131829 (2023)","journal-title":"IEEE Trans. Netw. Service Manag."},{"issue":"3","key":"14_CR29","doi-asserted-by":"publisher","first-page":"3323","DOI":"10.1007\/s10586-023-04143-2","volume":"27","author":"H Xiang","year":"2024","unstructured":"Xiang, H., Zhang, M., Jian, C.: Federated deep reinforcement learning-based online task offloading and resource allocation in harsh mobile edge computing environment. Cluster Comput. 27(3), 3323\u20133339 (2024)","journal-title":"Cluster Comput."}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Performance Evaluation Methodologies and Tools"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06818-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:16:53Z","timestamp":1767313013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06818-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032068170","9783032068187"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06818-7_14","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"value":"1867-8211","type":"print"},{"value":"1867-822X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Valuetools","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EAI International Conference on Performance Evaluation Methodologies and Tools","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17th","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"valuetools2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}