{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:44:04Z","timestamp":1772556244588,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030708658","type":"print"},{"value":"9783030708665","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-70866-5_13","type":"book-chapter","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T16:03:57Z","timestamp":1614701037000},"page":"204-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Enhanced Pub\/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Carlos E.","family":"Arruda","sequence":"first","affiliation":[]},{"given":"Pedro F.","family":"Moraes","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3461-4284","authenticated-orcid":false,"given":"Nazim","family":"Agoulmine","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1310-9366","authenticated-orcid":false,"given":"Joberto S. B.","family":"Martins","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","first-page":"54074","DOI":"10.1109\/ACCESS.2020.2981434","volume":"8","author":"T Alfakih","year":"2020","unstructured":"Alfakih, T., Hassan, M.M., Gumaei, A., Savaglio, C., Fortino, G.: Task offloading and resource allocation for mobile edge computing by deep reinforcement learning based on SARSA. IEEE Access 8, 54074\u201354084 (2020)","journal-title":"IEEE Access"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"An, K., Gokhale, A., Tambe, S., Kuroda, T.: Wide Area Network-Scale Discovery and Data Dissemination in Data-Centric Publish\/Subscribe Systems, ACM Press, pp. 1\u20132 (2015)","DOI":"10.1145\/2830894.2830900"},{"key":"13_CR3","doi-asserted-by":"publisher","unstructured":"Asghari, A., Sohrabi, M.K., Yaghmaee, F.: Task scheduling, resource provisioning, and load balancing on scientific workflows using parallel SARSA reinforcement learning agents and genetic algorithm. J. Supercomput. 77, 2800\u20132828 (2021). https:\/\/doi.org\/10.1007\/s11227-020-03364-1","DOI":"10.1007\/s11227-020-03364-1"},{"issue":"4","key":"13_CR4","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1007\/s11036-018-0996-0","volume":"24","author":"JV Bibal Benifa","year":"2018","unstructured":"Bibal Benifa, J.V., Dejey, D.: RLPAS: reinforcement learning-based proactive auto-scaler for resource provisioning in cloud environment. Mob. Netw. Appl. 24(4), 1348\u20131363 (2018). https:\/\/doi.org\/10.1007\/s11036-018-0996-0","journal-title":"Mob. Netw. Appl."},{"issue":"1","key":"13_CR5","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1186\/s13174-018-0087-2","volume":"9","author":"R Boutaba","year":"2018","unstructured":"Boutaba, R., et al.: A comprehensive survey on machine learning for networking: evolution, applications and research opportunities. J. Internet Serv. Appl. 9(1), 16 (2018)","journal-title":"J. Internet Serv. Appl."},{"key":"13_CR6","unstructured":"Ciosek, K., Vuong, Q., Loftin, R., Hofmann, K.: Better exploration with optimistic actor critic, pp. 1787\u20131798 (2019)"},{"issue":"10","key":"13_CR7","doi-asserted-by":"publisher","first-page":"D100","DOI":"10.1364\/JOCN.10.00D100","volume":"10","author":"D Cote","year":"2018","unstructured":"Cote, D.: Using machine learning in communication networks. IEEE\/OSA J. Opt. Commun. Networking 10(10), D100\u2013D109 (2018)","journal-title":"IEEE\/OSA J. Opt. Commun. Networking"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Dabbaghjamanesh, M., Moeini, A., Kavousi-Fard, A.: Reinforcement learning-based load forecasting of electric vehicle charging station using Q-learning technique. IEEE Trans. Indust. Inform. V1, 1\u20139 (2020)","DOI":"10.1109\/TII.2020.2990397"},{"key":"13_CR9","unstructured":"Defazio, A., Graepel, T.: A comparison of learning algorithms on the arcade learning environment. arXiv:1410.8620 [cs], October 2014"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Happ, D., Wolisz, A.: Limitations of the Pub\/Sub pattern for cloud based IoT and their implications. In: Cloudification of the Internet of Things (CIoT), Paris, pp. 1\u20136. IEEE, November 2016","DOI":"10.1109\/CIOT.2016.7872916"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Koo, J., Mendiratta, V.B., Rahman, M.R., Walid, A.: Deep reinforcement learning for network slicing with heterogeneous resource requirements and time varying traffic dynamics. In: 2019 15th International Conference on Network and Service Management, pp. 1\u20135, October 2019","DOI":"10.23919\/CNSM46954.2019.9012702"},{"issue":"1","key":"13_CR12","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/JPROC.2014.2371999","volume":"103","author":"D Kreutz","year":"2014","unstructured":"Kreutz, D., Ramos, F.M.V., Verissimo, P., Rothenberg, C.E., Azodolmolky, S., Uhlig, S.: Software-defined networking: a comprehensive survey. Proc. IEEE 103(1), 14\u201376 (2014)","journal-title":"Proc. IEEE"},{"issue":"2","key":"13_CR13","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1049\/iet-net.2018.5082","volume":"8","author":"M Latah","year":"2019","unstructured":"Latah, M., Toker, L.: Artificial intelligence enabled software-defined networking: a comprehensive overview. IET Netw. 8(2), 79\u201399 (2019)","journal-title":"IET Netw."},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Liao, X., Wu, D., Wang, Y.: Dynamic spectrum access based on improved SARSA algorithm. IOP Conf. Ser. Mater. Sci. Eng. 768(7), 072015 (2020)","DOI":"10.1088\/1757-899X\/768\/7\/072015"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1613\/jair.5699","volume":"61","author":"MC Machado","year":"2018","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M., Bowling, M.: Revisiting the arcade learning environment: evaluation protocols and open problems for general agents. J. Artif. Intell. Res. 61, 523\u2013562 (2018)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"13_CR16","first-page":"159","volume":"22","author":"S Mahadevan","year":"1996","unstructured":"Mahadevan, S.: Average reward reinforcement learning: foundations, algorithms, and empirical results. Mach. Learn. 22(1), 159\u2013195 (1996)","journal-title":"Mach. Learn."},{"issue":"2","key":"13_CR17","first-page":"1","volume":"8","author":"JSB Martins","year":"2018","unstructured":"Martins, J.S.B.: Towards smart city innovation under the perspective of software-defined networking, artificial intelligence and big data. Revista de Tecnologia da Informa\u00e7\u00e3o e Comunica\u00e7\u00e3o 8(2), 1\u20137 (2018)","journal-title":"Revista de Tecnologia da Informa\u00e7\u00e3o e Comunica\u00e7\u00e3o"},{"issue":"7540","key":"13_CR18","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"13_CR19","unstructured":"Moerland, T.M., Broekens, J., Jonker, C.M.: A framework for reinforcement learning and planning. Ph.D. thesis, TU Delft. June 2020"},{"issue":"2","key":"13_CR20","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/MCOM.2018.1700298","volume":"56","author":"M Mohammadi","year":"2018","unstructured":"Mohammadi, M., Al-Fuqaha, A.: Enabling cognitive smart cities using big data and machine learning: approaches and challenges. IEEE Commun. Mag. 56(2), 94\u2013101 (2018)","journal-title":"IEEE Commun. Mag."},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Moraes, P.F., Martins, J.S.B.: A Pub\/Sub SDN-integrated framework for IoT traffic orchestration. In: Proceedings of the 3rd International Conference on Future Networks and Distributed Systems, ICFNDS 2019, Paris, France, pp. 1\u20139 (2019)","DOI":"10.1145\/3341325.3342001"},{"key":"13_CR22","unstructured":"Moraes, P.F., Reale, R.F., Martins, J.S.B.: A publish\/subscribe QoS-aware framework for massive IoT traffic orchestration. In: Proceedings of the 6th International Workshop on ADVANCEs in ICT Infrastructures and Services (ADVANCE), Santiago, pp. 1\u201314, January 2018"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Mukherjee, M., Shu, L., Wang, D.: Survey of fog computing: fundamental, network applications, and research challenges. IEEE Commun. Surv. Tutorials 20(3), 1826\u20131857 (2018)","DOI":"10.1109\/COMST.2018.2814571"},{"key":"13_CR24","doi-asserted-by":"publisher","first-page":"128014","DOI":"10.1109\/ACCESS.2019.2939735","volume":"7","author":"A Nassar","year":"2019","unstructured":"Nassar, A., Yilmaz, Y.: Reinforcement learning for adaptive resource allocation in fog RAN for IoT with heterogeneous latency requirements. IEEE Access 7, 128014\u2013128025 (2019)","journal-title":"IEEE Access"},{"issue":"6","key":"13_CR25","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/MNET.2019.1800551","volume":"33","author":"B Nour","year":"2019","unstructured":"Nour, B., Sharif, K., Li, F., Yang, S., Moungla, H., Wang, Y.: ICN publisher-subscriber models: challenges and group-based communication. IEEE Netw. 33(6), 156\u2013163 (2019)","journal-title":"IEEE Netw."},{"key":"13_CR26","unstructured":"Ramani, D.: A short survey on memory based reinforcement learning. arXiv:1904.06736 [cs], April 2019"},{"key":"13_CR27","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.comnet.2015.12.023","volume":"101","author":"MM Rathore","year":"2016","unstructured":"Rathore, M.M., Ahmad, A., Paul, A., Rho, S.: Urban planning and building smart cities based on the Internet of Things using big data analytics. Comput. Netw. 101, 63\u201380 (2016)","journal-title":"Comput. Netw."},{"key":"13_CR28","unstructured":"Rendon, O.M.C., et al.: Machine learning for cognitive network management. IEEE Commun. Mag. 1\u20139 (2018)"},{"key":"13_CR29","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical report, TR 166, Cambridge University Engineering Department, Cambridge, England (1994)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Sampaio, L.S.R., Faustini, P.H.A., Silva, A.S., Granville, L.Z., Schaeffer-Filho, A.: Using NFV and reinforcement learning for anomalies detection and mitigation in SDN. In: 2018 IEEE Symposium on Computers and Communications (ISCC), pp. 00432\u201300437, June 2018","DOI":"10.1109\/ISCC.2018.8538614"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Santos, J., Wauters, T., Volckaert, B., De Turck, F.: Resource provisioning in fog computing: from theory to practice. Sensors (Basel, Switzerland) 19(10), 2238 (2019)","DOI":"10.3390\/s19102238"},{"issue":"7676","key":"13_CR32","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"13_CR33","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning, 1st edn. MIT Press, Cambridge (1998)","edition":"1"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J.H., Lu, P.E., Chang, C.S., Lee, D.S.: A reinforcement learning approach for the multichannel rendezvous problem. In: 2019 IEEE Globecom Workshops (GC Wkshps), pp. 1\u20135, December 2019","DOI":"10.1109\/GCWkshps45667.2019.9024429"},{"key":"13_CR35","unstructured":"Wang, Y., Zou, S.: Finite-sample analysis of Greedy-GQ with linear function approximation under Markovian noise. In: Proceedings of Machine Learning Research. Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), vol. 124, pp. 1\u201326 (2020)"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Xie, J., et al.: A survey of machine learning techniques applied to software defined networking (SDN): research issues and challenges. IEEE Commun. Surv. Tutorials 21(1), 393\u2013430 (2019)","DOI":"10.1109\/COMST.2018.2866942"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, X., Wang, Y., Lu, S., Liu, L., Xu, L., Shi, W.: OpenEI: an open framework for edge intelligence. In: 39th IEEE International Conference on Distributed Computing Systems (ICDCS), Dallas, US, pp. 1\u201312, July 2019","DOI":"10.1109\/ICDCS.2019.00182"},{"issue":"4","key":"13_CR38","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1109\/MCOM.2019.1800603","volume":"57","author":"L Zhao","year":"2019","unstructured":"Zhao, L., Wang, J., Liu, J., Kato, N.: Routing for crowd management in smart cities: a deep reinforcement learning perspective. IEEE Commun. Mag. 57(4), 88\u201393 (2019)","journal-title":"IEEE Commun. Mag."}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Networking"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-70866-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T16:10:12Z","timestamp":1614701412000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-70866-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030708658","9783030708665"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-70866-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"3 March 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning for Networking","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mln2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adda-association.org\/mln-2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"50","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"44% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the Corona pandemic this event was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}