{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:12:00Z","timestamp":1769267520015,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["Peer-to-Peer Netw. Appl."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s12083-025-02066-w","type":"journal-article","created":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:24:31Z","timestamp":1751347471000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A hybrid reinforcement learning approach for multipath routing optimization in software-defined networks"],"prefix":"10.1007","volume":"18","author":[{"given":"Houda","family":"Hassen","sequence":"first","affiliation":[]},{"given":"Soumaya","family":"Meherzi","sequence":"additional","affiliation":[]},{"given":"Zouhair","family":"Ben\u00a0Jemaa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"key":"2066_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jnca.2016.03.016","volume":"67","author":"R Masoudi","year":"2016","unstructured":"Masoudi R, Ghaffari A (2016) Software defined networks: A survey. J. Netw. Comput. Appl. 67:1\u201325","journal-title":"J. Netw. Comput. Appl."},{"key":"2066_CR2","doi-asserted-by":"publisher","first-page":"5296","DOI":"10.1002\/dac.5296","volume":"38","author":"R Chaudhary","year":"2022","unstructured":"Chaudhary R, Aujla GS, Kumar N, Chouhan PK (2022) A comprehensive survey on software-defined networking for smart communities. Int. J. Commun Syst 38:5296","journal-title":"Int. J. Commun Syst"},{"issue":"2","key":"2066_CR3","doi-asserted-by":"publisher","first-page":"1507","DOI":"10.1007\/s11277-021-08100-3","volume":"118","author":"A Hodaei","year":"2021","unstructured":"Hodaei A, Babaie S (2021) A survey on traffic management in software-defined networks: challenges, effective approaches, and potential measures. Wireless Pers. Commun. 118(2):1507\u20131534","journal-title":"Wireless Pers. Commun."},{"issue":"9","key":"2066_CR4","doi-asserted-by":"publisher","first-page":"3643","DOI":"10.1002\/ett.3643","volume":"30","author":"A Rego","year":"2019","unstructured":"Rego A, Sendra S, Garcia L, Lloret J (2019) Adapting reinforcement learning for multimedia transmission on sdn. Transactions on Emerging Telecommunications Technologies. 30(9):3643","journal-title":"Transactions on Emerging Telecommunications Technologies."},{"key":"2066_CR5","doi-asserted-by":"publisher","first-page":"174773","DOI":"10.1109\/ACCESS.2020.3025432","volume":"8","author":"J Rischke","year":"2020","unstructured":"Rischke J, Sossalla P, Salah H, Fitzek FH, Reisslein M (2020) Qr-sdn: towards reinforcement learning states, actions, and rewards for direct flow routing in software-defined networks. IEEE Access. 8:174773\u2013174791","journal-title":"IEEE Access."},{"issue":"1","key":"2066_CR6","doi-asserted-by":"publisher","first-page":"870","DOI":"10.1109\/TNSM.2020.3036911","volume":"18","author":"DM Casas-Velasco","year":"2020","unstructured":"Casas-Velasco DM, Rendon OMC, Fonseca NL (2020) Intelligent routing based on reinforcement learning for software-defined networking. IEEE Trans. Netw. Serv. Manage. 18(1):870\u2013881","journal-title":"IEEE Trans. Netw. Serv. Manage."},{"key":"2066_CR7","doi-asserted-by":"crossref","unstructured":"Mahboob T, Jung YR, Chung MY (2019) Optimized routing in software defined networks\u2013a reinforcement learning approach. In: International Conference on Ubiquitous Information Management and Communication, pp. 267\u2013278. Springer","DOI":"10.1007\/978-3-030-19063-7_22"},{"issue":"5","key":"2066_CR8","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.icte.2022.10.007","volume":"9","author":"C-H Ke","year":"2022","unstructured":"Ke C-H, Tu Y-H, Ma Y-W (2022) A reinforcement learning approach for widest path routing in software-defined networks. ICT Express. 9(5):882\u2013889","journal-title":"ICT Express."},{"issue":"3","key":"2066_CR9","doi-asserted-by":"publisher","first-page":"3671","DOI":"10.32604\/cmc.2021.017475","volume":"68","author":"D Godfrey","year":"2021","unstructured":"Godfrey D, Kim BS, Miao H, Shah B, Hayat B, Khan I, Sung TE, Kim KI (2021) Q-learning based routing protocol for congestion avoidance. Computers, Materials and Continua. 68(3):3671","journal-title":"Computers, Materials and Continua."},{"issue":"2","key":"2066_CR10","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/s10922-024-09804-0","volume":"32","author":"H Hassen","year":"2024","unstructured":"Hassen H, Meherzi S, Jemaa ZB (2024) Improved exploration strategy for q-learning based multipath routing in sdn networks. J. Netw. Syst. Manage. 32(2):25","journal-title":"J. Netw. Syst. Manage."},{"issue":"2","key":"2066_CR11","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1287\/ijoc.1080.0305","volume":"21","author":"A Gosavi","year":"2009","unstructured":"Gosavi A (2009) Reinforcement learning: A tutorial survey and recent advances. INFORMS J. Comput. 21(2):178\u2013192","journal-title":"INFORMS J. Comput."},{"issue":"4","key":"2066_CR12","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.3390\/s21041292","volume":"21","author":"N Akalin","year":"2021","unstructured":"Akalin N, Loutfi A (2021) Reinforcement learning approaches in social robotics. Sensors. 21(4):1292","journal-title":"Sensors."},{"issue":"1","key":"2066_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10922-020-09575-4","volume":"29","author":"S Ahmad","year":"2021","unstructured":"Ahmad S, Mir AH (2021) Scalability, consistency, reliability and security in sdn controllers: a survey of diverse sdn controllers. J. Netw. Syst. Manage. 29(1):1\u201359","journal-title":"J. Netw. Syst. Manage."},{"issue":"2","key":"2066_CR14","doi-asserted-by":"publisher","first-page":"302","DOI":"10.3390\/fi6020302","volume":"6","author":"W Braun","year":"2014","unstructured":"Braun W, Menth M (2014) Software-defined networking using openflow: Protocols, applications and architectural design choices. Future Internet. 6(2):302\u2013336","journal-title":"Future Internet."},{"issue":"3","key":"2066_CR15","doi-asserted-by":"publisher","first-page":"1631","DOI":"10.1007\/s11277-023-10516-y","volume":"131","author":"GS Let","year":"2023","unstructured":"Let GS, Pratap C, Jagannath D, Dolly D, Evangeline LD (2023) Software-defined networking routing algorithms: Issues, qos and models. Wireless Pers. Commun. 131(3):1631\u20131661","journal-title":"Wireless Pers. Commun."},{"issue":"1","key":"2066_CR16","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1186\/s40537-024-01029-x","volume":"11","author":"Y Wang","year":"2024","unstructured":"Wang Y, Othman M, Choo WO, Liu R, Wang X (2024) Dfrdrl: a dynamic fuzzy routing algorithm based on deep reinforcement learning with guaranteed latency and bandwidth for software-defined networks. Journal of Big Data. 11(1):150","journal-title":"Journal of Big Data."},{"key":"2066_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2024.104054","volume":"234","author":"Y Ma","year":"2025","unstructured":"Ma Y, Guo Y, Yang R, Luo H (2025) Frrl: A reinforcement learning approach for link failure recovery in a hybrid sdn. J. Netw. Comput. Appl. 234:104054","journal-title":"J. Netw. Comput. Appl."},{"issue":"3","key":"2066_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2024.102006","volume":"36","author":"C Jisi","year":"2024","unstructured":"Jisi C, Roh B-H, Ali J (2024) Reliable paths prediction with intelligent data plane monitoring enabled reinforcement learning in sd-iot. Journal of King Saud University-Computer and Information Sciences. 36(3):102006","journal-title":"Journal of King Saud University-Computer and Information Sciences."},{"issue":"15","key":"2066_CR19","doi-asserted-by":"publisher","first-page":"2441","DOI":"10.3390\/electronics11152441","volume":"11","author":"M Al Jameel","year":"2022","unstructured":"Al Jameel M, Kanakis T, Turner S, Al-Sherbaz A, Bhaya WS (2022) A reinforcement learning-based routing for real-time multimedia traffic transmission over software-defined networking. Electronics 11(15):2441","journal-title":"Electronics"},{"key":"2066_CR20","doi-asserted-by":"crossref","unstructured":"Le D-H, Tran H-A, Souihi S (2021) A reinforcement learning-based solution for intra-domain egress selection. In: 2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR), pp. 1\u20136. IEEE","DOI":"10.1109\/HPSR52026.2021.9481846"},{"issue":"4","key":"2066_CR21","doi-asserted-by":"publisher","first-page":"3185","DOI":"10.1109\/TNSE.2020.3017751","volume":"7","author":"Y-R Chen","year":"2020","unstructured":"Chen Y-R, Rezapour A, Tzeng W-G, Tsai S-C (2020) Rl-routing: An sdn routing algorithm based on deep reinforcement learning. IEEE Transactions on Network Science and Engineering. 7(4):3185\u20133199","journal-title":"IEEE Transactions on Network Science and Engineering."},{"key":"2066_CR22","doi-asserted-by":"crossref","unstructured":"Lin S-C, Akyildiz IF, Wang P, Luo M (2016) Qos-aware adaptive routing in multi-layer hierarchical software defined networks: A reinforcement learning approach. In: 2016 IEEE International Conference on Services Computing (SCC), pp. 25\u201333. IEEE","DOI":"10.1109\/SCC.2016.12"},{"issue":"17","key":"2066_CR23","doi-asserted-by":"publisher","first-page":"3802","DOI":"10.1002\/dac.3802","volume":"31","author":"R Jin","year":"2018","unstructured":"Jin R, Li J, Tuo X, Wang W, Li X (2018) A congestion control method of sdn data center based on reinforcement learning. Int. J. Commun Syst 31(17):3802","journal-title":"Int. J. Commun Syst"},{"issue":"4","key":"2066_CR24","doi-asserted-by":"publisher","first-page":"5064","DOI":"10.1109\/TNNLS.2022.3207346","volume":"35","author":"X Wang","year":"2022","unstructured":"Wang X, Wang S, Liang X, Zhao D, Huang J, Xu X, Dai B, Miao Q (2022) Deep reinforcement learning: A survey. IEEE Transactions on Neural Networks and Learning Systems. 35(4):5064\u20135078","journal-title":"IEEE Transactions on Neural Networks and Learning Systems."},{"issue":"1","key":"2066_CR25","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1186\/s13677-024-00603-1","volume":"13","author":"J Chen","year":"2024","unstructured":"Chen J, Xiao W, Zhang H, Zuo J, Li X (2024) Dynamic routing optimization in software-defined networking based on a metaheuristic algorithm. Journal of Cloud Computing. 13(1):41","journal-title":"Journal of Cloud Computing."},{"key":"2066_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2024.104082","volume":"235","author":"LPA Sanchez","year":"2025","unstructured":"Sanchez LPA, Shen Y, Guo M (2025) Mdq: A qos-congestion aware deep reinforcement learning approach for multi-path routing in sdn. J. Netw. Comput. Appl. 235:104082","journal-title":"J. Netw. Comput. Appl."},{"key":"2066_CR27","doi-asserted-by":"publisher","first-page":"18121","DOI":"10.1109\/ACCESS.2022.3151081","volume":"10","author":"G Kim","year":"2022","unstructured":"Kim G, Kim Y, Lim H (2022) Deep reinforcement learning-based routing on software-defined networks. IEEE Access. 10:18121\u201318133","journal-title":"IEEE Access."},{"issue":"3","key":"2066_CR28","doi-asserted-by":"publisher","first-page":"4015","DOI":"10.32604\/cmc.2024.058480","volume":"81","author":"J Ali","year":"2024","unstructured":"Ali J, Alenazi MJ (2024) Effective controller placement in software-defined internet-of-things leveraging deep q-learning (dql). Computers, Materials & Continua. 81(3):4015","journal-title":"Computers, Materials & Continua."},{"issue":"9","key":"2066_CR29","doi-asserted-by":"publisher","first-page":"9771","DOI":"10.1007\/s11227-022-04995-2","volume":"79","author":"TM Modi","year":"2023","unstructured":"Modi TM, Swain P (2023) Hybrid deep learning models and link probability based routing in software defined-dcn. J. Supercomput. 79(9):9771\u20139794","journal-title":"J. Supercomput."},{"key":"2066_CR30","doi-asserted-by":"crossref","unstructured":"Wu G (2024) Deep reinforcement learning based multi-layered traffic scheduling scheme in data center networks. Wireless Netw. 30(5):4133\u20134144","DOI":"10.1007\/s11276-021-02883-w"},{"issue":"5","key":"2066_CR31","doi-asserted-by":"publisher","first-page":"2039","DOI":"10.1007\/s12083-023-01489-7","volume":"16","author":"J Chen","year":"2023","unstructured":"Chen J, Huang X, Wang Y, Zhang H, Liao C, Xie X, Li X, Xiao W (2023) Astppo: A proximal policy optimization algorithm based on the attention mechanism and spatio-temporal correlation for routing optimization in software-defined networking. Peer-to-Peer Networking and Applications. 16(5):2039\u20132057","journal-title":"Peer-to-Peer Networking and Applications."},{"key":"2066_CR32","doi-asserted-by":"crossref","unstructured":"Liao L, Leung VC (2016) Lldp based link latency monitoring in software defined networks. In: 2016 12th International Conference on Network and Service Management (CNSM), pp. 330\u2013335. IEEE","DOI":"10.1109\/CNSM.2016.7818442"},{"key":"2066_CR33","doi-asserted-by":"crossref","unstructured":"Bouzidi EH, Outtagarts A, Langar R (2019) Deep reinforcement learning application for network latency management in software defined networks. In: 2019 IEEE Global Communications Conference (GLOBECOM), pp. 1\u20136. IEEE","DOI":"10.1109\/GLOBECOM38437.2019.9013221"},{"key":"2066_CR34","doi-asserted-by":"crossref","unstructured":"Phemius K, Bouet M (2013) Monitoring latency with openflow. In: Proceedings of the 9th International Conference on Network and Service Management (CNSM 2013), pp. 122\u2013125. IEEE","DOI":"10.1109\/CNSM.2013.6727820"},{"key":"2066_CR35","unstructured":"Amin S, Gomrokchi M, Satija H, Hoof H, Precup D (2021) A survey of exploration methods in reinforcement learning. arXiv preprint arXiv:2109.00157"},{"key":"2066_CR36","doi-asserted-by":"publisher","first-page":"133653","DOI":"10.1109\/ACCESS.2019.2941229","volume":"7","author":"B Jang","year":"2019","unstructured":"Jang B, Kim M, Harerimana G, Kim JW (2019) Q-learning algorithms: A comprehensive classification and applications. IEEE access. 7:133653\u2013133667","journal-title":"IEEE access."},{"key":"2066_CR37","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.comcom.2021.07.014","volume":"178","author":"MS Frikha","year":"2021","unstructured":"Frikha MS, Gammar SM, Lahmadi A, Andrey L (2021) Reinforcement and deep reinforcement learning for wireless internet of things: A survey. Comput. Commun. 178:98\u2013113","journal-title":"Comput. Commun."},{"issue":"9","key":"2066_CR38","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1016\/j.engappai.2013.06.016","volume":"26","author":"Y-H Wang","year":"2013","unstructured":"Wang Y-H, Li T-HS, Lin C-J (2013) Backward q-learning: The combination of sarsa algorithm and q-learning. Eng. Appl. Artif. Intell. 26(9):2184\u20132193","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"2","key":"2066_CR39","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1109\/TNSE.2022.3219417","volume":"10","author":"P Kamboj","year":"2022","unstructured":"Kamboj P, Pal S, Bera S, Misra S (2022) Qos-aware multipath routing in software-defined networks. IEEE Transactions on Network Science and Engineering. 10(2):723\u2013732","journal-title":"IEEE Transactions on Network Science and Engineering."},{"key":"2066_CR40","unstructured":"Wiering M (1999) Explorations in efficient reinforcement learning (Doctoral Dissertation, University of Amsterdam)"},{"key":"2066_CR41","doi-asserted-by":"crossref","unstructured":"Dholakiya D, Kshirsagar T, Nayak A (2020) Survey of mininet challenges, opportunities, and application in software-defined network (sdn). In: International Conference on Information and Communication Technology for Intelligent Systems, pp. 213\u2013221. Springer","DOI":"10.1007\/978-981-15-7062-9_21"},{"issue":"1","key":"2066_CR42","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/s11277-021-08920-3","volume":"122","author":"S Bhardwaj","year":"2022","unstructured":"Bhardwaj S, Panda SN (2022) Performance evaluation using ryu sdn controller in software-defined networking environment. Wireless Pers. Commun. 122(1):701\u2013723","journal-title":"Wireless Pers. Commun."},{"key":"2066_CR43","doi-asserted-by":"crossref","unstructured":"Srivastava S, Anmulwar S, Sapkal A, Batra T, Gupta AK, Kumar V (2014) Comparative study of various traffic generator tools. In: 2014 Recent Advances in Engineering and Computational Sciences (RAECS), pp. 1\u20136. IEEE","DOI":"10.1109\/RAECS.2014.6799557"},{"issue":"1","key":"2066_CR44","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s10922-021-09627-3","volume":"30","author":"DP Isravel","year":"2022","unstructured":"Isravel DP, Silas S, Rajsingh EB (2022) Centrality based congestion detection using reinforcement learning approach for traffic engineering in hybrid sdn. J. Netw. Syst. Manage. 30(1):2","journal-title":"J. Netw. Syst. Manage."},{"key":"2066_CR45","unstructured":"Zhang Y (2014) Abilene Traffic Matrices. [Online] Available. http:\/\/www.cs.utexas.edu\/~yzhang\/research\/AbileneTM\/"}],"container-title":["Peer-to-Peer Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-025-02066-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12083-025-02066-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12083-025-02066-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T15:22:32Z","timestamp":1758986552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12083-025-02066-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["2066"],"URL":"https:\/\/doi.org\/10.1007\/s12083-025-02066-w","relation":{},"ISSN":["1936-6442","1936-6450"],"issn-type":[{"value":"1936-6442","type":"print"},{"value":"1936-6450","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"226"}}