{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T09:05:11Z","timestamp":1785143111648,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:00:00Z","timestamp":1778284800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":79,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"crossref","award":["62301596"],"award-info":[{"award-number":["62301596"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation","doi-asserted-by":"crossref","award":["U23B2064"],"award-info":[{"award-number":["U23B2064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s44443-026-00809-0","type":"journal-article","created":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T12:35:22Z","timestamp":1778330122000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep reinforcement learning for SDN routing optimization enhanced by graph multi-head attention"],"prefix":"10.1007","volume":"38","author":[{"given":"Chengjin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziang","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieling","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"cheng","family":"chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,9]]},"reference":[{"key":"809_CR1","unstructured":"Abilene (2004) [Online]. Available http:\/\/www.cs.utexas.edu\/yzhang\/research\/AbileneTM. Accessed 9 Mar 2025"},{"key":"809_CR2","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.comcom.2023.12.039","volume":"216","author":"J Bai","year":"2024","unstructured":"Bai J, Sun JC, Wang ZG et al (2024) An adaptive intelligent routing algorithm based on deep reinforcement learning. Comput Commun 216:195\u2013208. https:\/\/doi.org\/10.1016\/j.comcom.2023.12.039","journal-title":"Comput Commun"},{"issue":"9","key":"809_CR3","doi-asserted-by":"publisher","first-page":"14092","DOI":"10.1109\/tvt.2024.3397707","volume":"73","author":"M Bomin","year":"2024","unstructured":"Bomin M, Xueming Z, Jiajia L et al (2024) On a cooperative deep reinforcement learning-based multi-objective routing strategy for diversified 6G metaverse services[J]. IEEE Trans Veh Technol 73(9):14092\u201314096. https:\/\/doi.org\/10.1109\/tvt.2024.3397707","journal-title":"IEEE Trans Veh Technol"},{"issue":"4","key":"809_CR4","doi-asserted-by":"publisher","first-page":"3185","DOI":"10.1109\/TNSE.2020.3017751","volume":"7","author":"Y Chen","year":"2020","unstructured":"Chen Y, Amir R, Wen GT et al (2020) RL-routing: an SDN routing algorithm based on deep reinforcement learning. IEEE Trans Netw Sci Eng 7(4):3185\u20133199. https:\/\/doi.org\/10.1109\/TNSE.2020.3017751","journal-title":"IEEE Trans Netw Sci Eng"},{"issue":"10","key":"809_CR5","doi-asserted-by":"publisher","first-page":"10345","DOI":"10.1109\/tmc.2025.3568470","volume":"24","author":"L Chengjia","year":"2025","unstructured":"Chengjia L, Shaohua W, Yi Y et al (2025) Joint Partitioning, Allocation, and Transmission Optimization for Federated Learning in Satellite Constellations Via Multi-Task MARL[J]. IEEE Transact Mobile Comput 24(10):10345\u201310361. https:\/\/doi.org\/10.1109\/tmc.2025.3568470","journal-title":"IEEE Transact Mobile Comput"},{"issue":"4","key":"809_CR6","doi-asserted-by":"publisher","first-page":"5821","DOI":"10.1109\/jsyst.2022.3149990","volume":"16","author":"B Dai","year":"2022","unstructured":"Dai B, Cao YY, Wu ZL et al (2022) IQoR-LSE: an intelligent QoS on-demand routing algorithm with link state estimation. IEEE Syst J 16(4):5821\u20135830. https:\/\/doi.org\/10.1109\/jsyst.2022.3149990","journal-title":"IEEE Syst J"},{"issue":"4","key":"809_CR7","doi-asserted-by":"publisher","first-page":"4807","DOI":"10.1109\/tnsm.2021.3132491","volume":"19","author":"MC Daniela","year":"2022","unstructured":"Daniela MC, Oscar MCR, Nelson LSDA (2022) DRSIR: a deep reinforcement learning approach for routing in software-defined networking[J]. IEEE Trans Netw Serv Manag 19(4):4807\u20134820. https:\/\/doi.org\/10.1109\/tnsm.2021.3132491","journal-title":"IEEE Trans Netw Serv Manag"},{"issue":"4","key":"809_CR8","doi-asserted-by":"publisher","first-page":"2870","DOI":"10.1109\/tnse.2022.3172283","volume":"9","author":"YY Guo","year":"2022","unstructured":"Guo YY, Ma YL, Luo H et al (2022) Traffic engineering in a shared Inter-DC WAN via deep reinforcement learning. IEEE Trans Netw Sci Eng 9(4):2870\u20132881. https:\/\/doi.org\/10.1109\/tnse.2022.3172283","journal-title":"IEEE Trans Netw Sci Eng"},{"issue":"3","key":"809_CR9","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MNET.2016.7474344","volume":"30","author":"IF A","year":"2016","unstructured":"A IF, L A, W P, L M, C W et al (2016) Research challenges for traffic engineering in software defined networks. IEEE Network 30(3):52\u201358","journal-title":"IEEE Network"},{"key":"809_CR10","doi-asserted-by":"publisher","unstructured":"John S, Filip W, Prafulla D, Alec R, Oleg K et al (2017) Proximal Policy Optimization Algorithms.[J], Comput Res Repositor, abs\/1707.06347. https:\/\/doi.org\/10.48550\/arxiv.1707.06347","DOI":"10.48550\/arxiv.1707.06347"},{"key":"809_CR11","unstructured":"Kostrikov I (2018) Pytorch implementations of reinforcement learning algorithms. [Online]. Available https:\/\/github.com\/ikostrikov\/Pytorcha2c-ppo-acktr-gail. Accessed 5 May 2025"},{"issue":"99","key":"809_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/MNET.2025.3548419","volume":"PP","author":"F Li","year":"2025","unstructured":"Li F, Renchao X, Qinqin T, Tao H, Zehui X, Tianjiao C, Ran Z, Sha T, Zeru F et al (2025) CaRCS: joint optimization of computing-aware routing and collaborative scheduling in computing power networks. IEEE Netw PP(99):1\u20138. https:\/\/doi.org\/10.1109\/MNET.2025.3548419","journal-title":"IEEE Netw"},{"key":"809_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2024.110514","volume":"249","author":"N Lin","year":"2024","unstructured":"Lin N, Huang JJ, Ammar H et al (2024) Joint routing and computation offloading based deep reinforcement learning for flying ad hoc networks. Comput Networks 249:110514. https:\/\/doi.org\/10.1016\/j.comnet.2024.110514","journal-title":"Comput Networks"},{"issue":"8","key":"809_CR14","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1109\/tpds.2023.3284651","volume":"34","author":"CY Liu","year":"2023","unstructured":"Liu CY, Wu PF, Xu MW et al (2023) Scalable deep reinforcement learning-based online routing for multi-type service requirements. IEEE Trans Parallel Distrib Syst 34(8):2337\u20132351. https:\/\/doi.org\/10.1109\/tpds.2023.3284651","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"809_CR15","doi-asserted-by":"publisher","unstructured":"Liu CY, Xu MW, Yang Y et al (2021) DRL-OR: deep reinforcement learning-based online routing for multi-type service requirements[C]\/\/Proc of The IEEE INFOCOM 2021-IEEE Conference on Computer Communications. Piscataway, NJ: IEEE, 1\u201310. https:\/\/doi.org\/10.1109\/infocom42981.2021.9488736","DOI":"10.1109\/infocom42981.2021.9488736"},{"key":"809_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2024.104851","volume":"188","author":"A Lizeth","year":"2024","unstructured":"Lizeth A, Shen YAO, Guo MY et al (2024) DQS: a QoS-driven routing optimization approach in SDN using deep reinforcement learning. J Parallel Distrib Comput 188:104851. https:\/\/doi.org\/10.1016\/j.jpdc.2024.104851","journal-title":"J Parallel Distrib Comput"},{"issue":"5","key":"809_CR17","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1109\/jsac.2024.3365869","volume":"42","author":"YF Lyu","year":"2024","unstructured":"Lyu YF, Hu H, Fan RF et al (2024) Dynamic routing for integrated satellite-terrestrial networks: a constrained multi-agent reinforcement learning approach. IEEE J Sel Areas Commun 42(5):1204\u20131218. https:\/\/doi.org\/10.1109\/jsac.2024.3365869","journal-title":"IEEE J Sel Areas Commun"},{"issue":"3","key":"809_CR18","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1109\/tmc.2024.3481276","volume":"24","author":"Y Meiyi","year":"2025","unstructured":"Meiyi Y, Deyun G, Weiting Z, Dong Y, Dusit N, Hongke Z, Victor CML et al (2025) Deep reinforcement learning-based joint caching and routing in AI-Driven networks. IEEE Trans Mob Comput 24(3):1322\u20131337. https:\/\/doi.org\/10.1109\/tmc.2024.3481276","journal-title":"IEEE Trans Mob Comput"},{"issue":"6","key":"809_CR19","doi-asserted-by":"publisher","first-page":"3080","DOI":"10.1109\/TNET.2023.3269983","volume":"31","author":"F Miquel","year":"2023","unstructured":"Miquel F, Jordi P, Jose S, Krzysztof R, Shihan X, Xiang S, Xiangle C, Pere B, Albert C et al (2023) RouteNet-Fermi: Network Modeling with Graph Neural Networks[J]. IEEE\/ACM Transact Network 31(6):3080\u20133095","journal-title":"IEEE\/ACM Transact Network"},{"issue":"2","key":"809_CR20","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1145\/1355734.1355746","volume":"38","author":"M Nick","year":"2008","unstructured":"Nick M, Tom A, Hari B, Guru P, Larry P, Jennifer R, Scott S, Jonathan T (2008) OpenFlow: enabling innovation in campus networks. Comput Commun Rev 38(2):69\u201374. https:\/\/doi.org\/10.1145\/1355734.1355746","journal-title":"Comput Commun Rev"},{"key":"809_CR21","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.future.2023.08.006","volume":"149","author":"M Noureddine","year":"2023","unstructured":"Noureddine M, Edmond N, Kebira A et al (2023) A reinforcement learning based routing protocol for software-defined networking enabled wireless sensor network forest fire detection[J]. Future Gen Comput Syst Int J eSci 149:478\u2013493. https:\/\/doi.org\/10.1016\/j.future.2023.08.006","journal-title":"Future Gen Comput Syst Int J eSci"},{"key":"809_CR22","unstructured":"NSF network topology n.d. https:\/\/www.internet-topology-zoo.org\/. Accessed 5 Mar 2026"},{"issue":"1","key":"809_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2024.111557","volume":"163","author":"M Park","year":"2024","unstructured":"Park M, Shin J, Yang I (2024) Anderson acceleration for partially observable Markov decision processes: a maximum entropy approach. Automatica 163(1):111557","journal-title":"Automatica"},{"key":"809_CR24","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.comcom.2022.09.029","volume":"196","author":"A Paul","year":"2022","unstructured":"Paul A, Jose S, Krzysztof R, Pere B, Albert C et al (2022) Deep Reinforcement Learning Meets Graph Neural Networks: Exploring a Routing Optimization Use Case[J]. Comput Commun 196:184\u2013194","journal-title":"Comput Commun"},{"key":"809_CR25","unstructured":"Shi Z (2024) Research on intelligent routing algorithms for multiple QoS requirements[D]. Beijing Univ Posts Telecommun, pp 30\u201337"},{"issue":"9","key":"809_CR26","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1109\/JSAC.2011.111002","volume":"29","author":"K Simon","year":"2011","unstructured":"Simon K, Hung XN, Nickolas F, Rhys B, Matthew R et al (2011) The Internet Topology Zoo[J]. IEEE J Select Areas Commun 29(9):1765\u201317755","journal-title":"IEEE J Select Areas Commun"},{"issue":"03","key":"809_CR27","first-page":"591","volume":"64","author":"J Tai","year":"2024","unstructured":"Tai J, Liu CY, Yang Y et al (2024) Low-cost traffic engineering for large-scale live streaming [J]. J Tsinghua Univ 64(03):591\u2013600","journal-title":"J Tsinghua Univ"},{"issue":"1","key":"809_CR28","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1145\/1111322.1111341","volume":"36","author":"S Uhlig","year":"2006","unstructured":"Uhlig S, Quoitin B, Lepropre J, Balon S et al (2006) Providing Public Intradomain Traffic Matrices to the Research Community[J]. Computer Communication Review 36(1):83\u201386. https:\/\/doi.org\/10.1145\/1111322.1111341","journal-title":"Computer Communication Review"},{"issue":"07","key":"809_CR29","first-page":"110","volume":"47","author":"K Wang","year":"2024","unstructured":"Wang K, Lv GH, Xu L et al (2024) Routing optimization method for multi-domain traffic engineering in distributed software-defined networking[J]. Journal of Chongqing University 47(07):110\u2013124","journal-title":"Journal of Chongqing University"},{"issue":"4","key":"809_CR30","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1145\/2534169.2486020","volume":"43","author":"K Winstein","year":"2013","unstructured":"Winstein K, Balakrishnan H (2013) TCP Ex Machina: computer-generated congestion control. ACM SIGCOMM Comput Commun Rev 43(4):123\u2013134. https:\/\/doi.org\/10.1145\/2534169.2486020","journal-title":"ACM SIGCOMM Comput Commun Rev"},{"key":"809_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2025.104249","author":"J Wu","year":"2025","unstructured":"Wu J, Zhu Z (2025) Intelligent routing optimization for SDN based on PPO and GNN. J Netw Comput Appl. https:\/\/doi.org\/10.1016\/j.jnca.2025.104249","journal-title":"J Netw Comput Appl"},{"issue":"4","key":"809_CR32","doi-asserted-by":"publisher","first-page":"4058","DOI":"10.1109\/tnsm.2022.3208342","volume":"19","author":"D Xia","year":"2022","unstructured":"Xia D, Wan JFUXUPP et al (2022) Deep reinforcement learning-based QoS optimization for software-defined factory heterogeneous networks. IEEE Trans Netw Serv Manag 19(4):4058\u20134068. https:\/\/doi.org\/10.1109\/tnsm.2022.3208342","journal-title":"IEEE Trans Netw Serv Manag"},{"key":"809_CR33","unstructured":"Xiao Y (2024) Research and application of key technologies for autonomous networks based on deep reinforcement learning[D]. Beijing University of Posts and Telecommunications, pp 104\u2013110"},{"issue":"11","key":"809_CR34","doi-asserted-by":"publisher","first-page":"15748","DOI":"10.1109\/jiot.2025.3530919","volume":"12","author":"C Xiao","year":"2025","unstructured":"Xiao C, Zhe J, Sheng W, Haoge J, Ailing X, Chunxiao J et al (2025) A distributed routing algorithm for LEO satellite networks: a multi-agent Transformer-MIX learning approach. IEEE Internet Things J 12(11):15748\u201315763. https:\/\/doi.org\/10.1109\/jiot.2025.3530919","journal-title":"IEEE Internet Things J"},{"issue":"2","key":"809_CR35","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/jiot.2024.3468642","volume":"12","author":"L Xiaoyu","year":"2025","unstructured":"Xiaoyu L, Haibo Z, Zitian Z, Qiangzhou G, Ting M et al (2025) Multipath Cooperative Routing in Ultra-Dense LEO Satellite Networks: A Deep Reinforcement Learning-Based Approach[J]. IEEE Inter Things J 12(2):1789\u20131804. https:\/\/doi.org\/10.1109\/jiot.2024.3468642","journal-title":"IEEE Inter Things J"},{"issue":"07","key":"809_CR36","first-page":"2228","volume":"52","author":"SY Xu","year":"2024","unstructured":"Xu SY, Guo JH (2024) Dual-layer federated learning based edge collaborative computing mechanism for high dynamic internet of vehicle businesses. Acta Electron Sin 52(07):2228\u20132241","journal-title":"Acta Electron Sin"},{"issue":"10","key":"809_CR37","doi-asserted-by":"publisher","first-page":"17402","DOI":"10.1109\/jiot.2024.3358403","volume":"11","author":"SJ Yang","year":"2024","unstructured":"Yang SJ, Zhuang L, Zhang JH et al (2024) A multi-policy deep reinforcement learning approach for multi-objective joint routing and scheduling in deterministic networks. IEEE Int Things J 11(10):17402\u201317418. https:\/\/doi.org\/10.1109\/jiot.2024.3358403","journal-title":"IEEE Int Things J"},{"issue":"1","key":"809_CR38","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1109\/tnsm.2023.3287601","volume":"21","author":"JM Yao","year":"2024","unstructured":"Yao JM, Yan CG, Wang JL et al (2024) Stable QoE-aware multi-SFCs cooperative routing mechanism based on deep reinforcement learning. IEEE Trans Netw Serv Manag 21(1):120\u2013131. https:\/\/doi.org\/10.1109\/tnsm.2023.3287601","journal-title":"IEEE Trans Netw Serv Manag"},{"issue":"3","key":"809_CR39","first-page":"7","volume":"48","author":"S Yuan","year":"2024","unstructured":"Yuan S, Zhang H, Cai AL et al (2024) Specific flow routing selection algorithm based on Self-Attention deep reinforcement learning[J]. Optic Commun Technol 48(3):7\u201312","journal-title":"Optic Commun Technol"},{"key":"809_CR40","unstructured":"Yuanfeng L (2025) Research on intelligent routing and resource management technologies for satellite networks[D]. Beijing University of Posts and Telecommunications, pp 54\u201377"},{"key":"809_CR41","doi-asserted-by":"publisher","unstructured":"Zhiyuan X, Jian T, Jingsong M, Weiyi Z, Yanzhi W, Chi H L, Dejun Y et al (2018) Experience-driven networking: a deep reinforcement learning based approach[C]. IEEE Conf\u00a0 Comp Commun, pp 1880\u20131888. https:\/\/doi.org\/10.1109\/infocom.2018.8485853","DOI":"10.1109\/infocom.2018.8485853"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-00809-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00809-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-00809-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T08:19:49Z","timestamp":1785140389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-00809-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,9]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["809"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-00809-0","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,9]]},"assertion":[{"value":"27 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Conflict of interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"404"}}