GraphNET: Graph Neural Networks for routing optimization in Software Defined Networks
In this paper, a graph neural net-based routing algorithm is designed which leverages global information from controller of a software-defined network to predict optimal path with minimum average delay between source and destination nodes in software-defined networks. Graph nets are used because of...
Uloženo v:
| Vydáno v: | Computer communications Ročník 178; s. 169 - 182 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.10.2021
|
| Témata: | |
| ISSN: | 0140-3664, 1873-703X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In this paper, a graph neural net-based routing algorithm is designed which leverages global information from controller of a software-defined network to predict optimal path with minimum average delay between source and destination nodes in software-defined networks. Graph nets are used because of their generalization capability which allows the routing algorithm to scale across varying topologies, traffic schemes and changing conditions. A deep reinforcement learning framework is developed to train the Graph Neural Networks using prioritized experience replay from the experiences learnt by the controllers. The algorithm is tested on various small and large topologies in terms of packets successfully routed and average packet delay time. Experiments are performed to check robustness of routing algorithms to changes in network structure and effects of varying hyperparameters. The proposed algorithm shows impressive results when compared to q-routing and shortest path routing algorithm in terms of above experiments and is robust to varying graphical structure of the network. |
|---|---|
| AbstractList | In this paper, a graph neural net-based routing algorithm is designed which leverages global information from controller of a software-defined network to predict optimal path with minimum average delay between source and destination nodes in software-defined networks. Graph nets are used because of their generalization capability which allows the routing algorithm to scale across varying topologies, traffic schemes and changing conditions. A deep reinforcement learning framework is developed to train the Graph Neural Networks using prioritized experience replay from the experiences learnt by the controllers. The algorithm is tested on various small and large topologies in terms of packets successfully routed and average packet delay time. Experiments are performed to check robustness of routing algorithms to changes in network structure and effects of varying hyperparameters. The proposed algorithm shows impressive results when compared to q-routing and shortest path routing algorithm in terms of above experiments and is robust to varying graphical structure of the network. |
| Author | Swaminathan, Avinash Ghosh, Uttam Chaba, Mridul Sharma, Deepak Kumar |
| Author_xml | – sequence: 1 givenname: Avinash orcidid: 0000-0002-7319-3275 surname: Swaminathan fullname: Swaminathan, Avinash email: s.avinash.it.17@nsit.net.in organization: Department of Information Technology, Netaji Subhas University of Technology, New Delhi 110078, India – sequence: 2 givenname: Mridul surname: Chaba fullname: Chaba, Mridul email: mridulc.it.17@nsit.net.in organization: Department of Information Technology, Netaji Subhas University of Technology, New Delhi 110078, India – sequence: 3 givenname: Deepak Kumar orcidid: 0000-0001-6117-3464 surname: Sharma fullname: Sharma, Deepak Kumar email: dk.sharma1982@yahoo.com organization: Department of Information Technology, Netaji Subhas University of Technology, New Delhi 110078, India – sequence: 4 givenname: Uttam orcidid: 0000-0003-1698-8888 surname: Ghosh fullname: Ghosh, Uttam email: ghosh.uttam@ieee.org organization: Department of EECS, Vanderbilt University, Nashville TN, USA |
| BookMark | eNqFkMFKAzEQhoMo2FbfwENeYNfJ7naT7UGQWqtQ6sEK3kKaTDS13ZRsatGnd9uKBw8KA_9cvp-Zr0uOa18jIRcMUgasvFyk2q_aSTPIWAo8hax_RDpM8DzhkD8fkw6wApK8LItT0m2aBQAUnOcd8jQOav06Hc0GdL_RKW6CWrYRtz68NdT6QIPfRFe_UL-ObuU-VXS-pq6mj97GrQpIb9C6Gs0PdUZOrFo2eP6dPTK7Hc2Gd8nkYXw_vJ4kOocyJllhCi5MYa3RQmWCKVUqy7KSVXNhKgUZ2qpSqAWg7c_7Yl4xnivkem4UE3mPDA61OvimCWildnF_XQzKLSUDufMjF_LgR-78SOCy9dPCxS94HdxKhY__sKsDhu1f7w6DbLTDWqNxAXWUxru_C74ACJ6F_g |
| CitedBy_id | crossref_primary_10_3390_su16219239 crossref_primary_10_1016_j_eswa_2024_125963 crossref_primary_10_1109_TNSE_2024_3495583 crossref_primary_10_1016_j_eswa_2025_128724 crossref_primary_10_3390_electronics14030476 crossref_primary_10_3390_electronics11203371 crossref_primary_10_1016_j_future_2023_09_017 crossref_primary_10_3390_electronics14051012 crossref_primary_10_3390_fi15120377 crossref_primary_10_1016_j_yofte_2024_104059 crossref_primary_10_1093_comjnl_bxae105 crossref_primary_10_3390_electronics13050994 crossref_primary_10_1007_s44443_025_00133_z crossref_primary_10_1016_j_jnca_2024_103927 crossref_primary_10_3390_telecom4030025 crossref_primary_10_1016_j_future_2022_04_006 crossref_primary_10_1016_j_comnet_2025_111175 crossref_primary_10_1287_ijoo_2023_0092 crossref_primary_10_1016_j_jmaa_2025_129509 |
| Cites_doi | 10.1109/ACCESS.2018.2877686 10.1002/dac.3879 10.1109/COMST.2018.2866942 10.37936/ecti-eec.2020182.240541 10.1090/qam/102435 10.1016/j.asoc.2021.107422 10.1109/JPROC.2019.2895553 10.1007/s11276-020-02331-1 10.1007/s11277-021-08072-4 10.1016/j.knosys.2020.106548 10.1117/12.472955 10.1016/j.jpdc.2020.03.021 10.1016/j.future.2020.10.007 10.1002/sec.1737 10.1109/JSYST.2016.2630923 10.1038/nature14236 10.1088/1742-6596/1284/1/012053 10.1109/TNSE.2020.2991106 10.1109/MCOM.2013.6553676 |
| ContentType | Journal Article |
| Copyright | 2021 Elsevier B.V. |
| Copyright_xml | – notice: 2021 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.comcom.2021.07.025 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1873-703X |
| EndPage | 182 |
| ExternalDocumentID | 10_1016_j_comcom_2021_07_025 S0140366421002887 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 77K 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABFNM ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG9 M41 MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ RXW SDF SDG SDP SES SPC SPCBC SST SSV SSZ T5K WH7 ZMT ~G- 07C 29F 77I 9DU AAQXK AATTM AAXKI AAYWO AAYXX ABJNI ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AI. AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD F0J FEDTE FGOYB HLZ HVGLF HZ~ R2- SBC SEW TAE UHS VH1 VOH WUQ XPP ZY4 ~HD |
| ID | FETCH-LOGICAL-c306t-24d478d4ffdc8a281aa6af12619b8d9a02ef99aec80ef5b58b9173ae7cbda183 |
| ISICitedReferencesCount | 28 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000703166900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0140-3664 |
| IngestDate | Sat Nov 29 07:24:13 EST 2025 Tue Nov 18 21:18:57 EST 2025 Fri Feb 23 02:44:01 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Q-table Routing algorithm Software-Defined Networking Deep Reinforcement Learning Routing optimization Deep Q-learning Graph Neural Networks |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c306t-24d478d4ffdc8a281aa6af12619b8d9a02ef99aec80ef5b58b9173ae7cbda183 |
| ORCID | 0000-0001-6117-3464 0000-0002-7319-3275 0000-0003-1698-8888 |
| PageCount | 14 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_comcom_2021_07_025 crossref_primary_10_1016_j_comcom_2021_07_025 elsevier_sciencedirect_doi_10_1016_j_comcom_2021_07_025 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-10-01 2021-10-00 |
| PublicationDateYYYYMMDD | 2021-10-01 |
| PublicationDate_xml | – month: 10 year: 2021 text: 2021-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Computer communications |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Yazdinejad, Parizi, Dehghantanha, Srivastava, Mohan, Rababah (b11) 2020; 143 Benzekki, El Fergougui, Elbelrhiti Elalaoui (b7) 2016; 9 Shan, Mamoulis, Cheng, Li, Li, Qian (b4) 2020 Naeem, Gautam, Tariq (b14) 2020; 7 Mehra, Doja, Alam (b35) 2019; 32 Zhou, Cui, Zhang, Yang, Liu, Sun (b2) 2018 Mothukuri, Khare, Parizi, Pouriyeh, Dehghantanha, Srivastava (b34) 2021 Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare, Graves, Riedmiller, Fidjeland, Ostrovski, Petersen, Beattie, Sadik, Antonoglou, King, Kumaran, Wierstra, Legg, Hassabis (b6) 2015; 518 Maheswari, Sujitha, Kadiyala Ramana (b29) 2020; 10 Kumar, K, Singh (b18) 2020 Ranjan, Nguyen, Mekky, Zhang (b25) 2020 Sharma, Dhurandher, Woungang, Srivastava, Mohananey, Rodrigues (b13) 2018; 12 Boyan, Littman (b26) 1999; 6 Moravejosharieh, Ahmadi, Ahmad (b1) 2018 Lin, Shao, Youcef (b24) 2021; 212 Sharma, Rodrigues, Vashishth, Khanna, Chhabra (b17) 2020; 26 Lin, Djenouri, Srivastava, Yun, Fournier-Viger (b21) 2021; 108 Pasupuleti, Mathew, Shenoy, Dianat (b28) 2002; 4740 Sendra, Rego, Lloret, Jimenez, Romero (b30) 2017 Mnih, Kavukcuoglu, Silver, Graves, Antonoglou, Wierstra, Riedmiller (b5) 2013 Dwivedi, Sharma, Mehra (b12) 2020; 18 Gia Nguyen, Phan, Dinh Thai, Nguyen, So-In (b10) 2020 Fang, Cheng, Tang, Li (b16) 2019; 1284 Lin, Akyildiz, Wang, Luo (b22) 2016 Gilmer, Schoenholz, Riley, Vinyals, Dahl (b3) 2017 Xie, Yu, Huang, Xie, Liu, Wang, Liu (b9) 2019; 21 Maan, Chaba (b19) 2021; 118 Sharma, Manju, Singh, Mehra (b20) 2021 You, Li, Xu, Feng, Zhao (b33) 2019 Bellman (b27) 1958; 16 Yu, Lan, Guo, Hu (b32) 2018; 6 Mothukuri, Parizi, Pouriyeh, Huang, Dehghantanha, Gautam (b23) 2021; 115 Azzouni, Boutaba, Pujolle (b31) 2017 Sezer, Scott-Hayward, Chouhan, Fraser, Lake, Finnegan, Vilijoen, Miller, Rao (b8) 2013; 51 Kellerer, Kalmbach, Blenk, Basta, Reisslein, Schmid (b15) 2019; 107 Moravejosharieh (10.1016/j.comcom.2021.07.025_b1) 2018 Benzekki (10.1016/j.comcom.2021.07.025_b7) 2016; 9 Azzouni (10.1016/j.comcom.2021.07.025_b31) 2017 Ranjan (10.1016/j.comcom.2021.07.025_b25) 2020 Xie (10.1016/j.comcom.2021.07.025_b9) 2019; 21 Mnih (10.1016/j.comcom.2021.07.025_b5) 2013 Gilmer (10.1016/j.comcom.2021.07.025_b3) 2017 Sharma (10.1016/j.comcom.2021.07.025_b20) 2021 Kellerer (10.1016/j.comcom.2021.07.025_b15) 2019; 107 Naeem (10.1016/j.comcom.2021.07.025_b14) 2020; 7 Lin (10.1016/j.comcom.2021.07.025_b21) 2021; 108 Lin (10.1016/j.comcom.2021.07.025_b24) 2021; 212 Sezer (10.1016/j.comcom.2021.07.025_b8) 2013; 51 Boyan (10.1016/j.comcom.2021.07.025_b26) 1999; 6 Mehra (10.1016/j.comcom.2021.07.025_b35) 2019; 32 Mnih (10.1016/j.comcom.2021.07.025_b6) 2015; 518 Bellman (10.1016/j.comcom.2021.07.025_b27) 1958; 16 Sharma (10.1016/j.comcom.2021.07.025_b17) 2020; 26 Mothukuri (10.1016/j.comcom.2021.07.025_b34) 2021 Sendra (10.1016/j.comcom.2021.07.025_b30) 2017 Zhou (10.1016/j.comcom.2021.07.025_b2) 2018 Sharma (10.1016/j.comcom.2021.07.025_b13) 2018; 12 Mothukuri (10.1016/j.comcom.2021.07.025_b23) 2021; 115 Fang (10.1016/j.comcom.2021.07.025_b16) 2019; 1284 Lin (10.1016/j.comcom.2021.07.025_b22) 2016 Dwivedi (10.1016/j.comcom.2021.07.025_b12) 2020; 18 Pasupuleti (10.1016/j.comcom.2021.07.025_b28) 2002; 4740 You (10.1016/j.comcom.2021.07.025_b33) 2019 Maheswari (10.1016/j.comcom.2021.07.025_b29) 2020; 10 Kumar (10.1016/j.comcom.2021.07.025_b18) 2020 Shan (10.1016/j.comcom.2021.07.025_b4) 2020 Gia Nguyen (10.1016/j.comcom.2021.07.025_b10) 2020 Yu (10.1016/j.comcom.2021.07.025_b32) 2018; 6 Yazdinejad (10.1016/j.comcom.2021.07.025_b11) 2020; 143 Maan (10.1016/j.comcom.2021.07.025_b19) 2021; 118 |
| References_xml | – year: 2020 ident: b18 article-title: Energy-aware routing protocols for wireless sensor network based on fuzzy logic: A 10-years analytical review publication-title: EAI Endorsed Trans. Energy Web: Online First – volume: 118 year: 2021 ident: b19 article-title: Accurate cluster head selection technique for software defined network in 5G VANET publication-title: Wirel. Pers. Commun. – volume: 16 year: 1958 ident: b27 article-title: On a routing problem publication-title: Quart. Appl. Math. – volume: 1284 year: 2019 ident: b16 article-title: Research on routing algorithm based on reinforcement learning in SDN publication-title: J. Phys. Conf. Ser. – volume: 6 start-page: 64533 year: 2018 end-page: 64539 ident: b32 article-title: DROM: Optimizing the routing in software-defined networks with deep reinforcement learning publication-title: IEEE Access – volume: 12 start-page: 2207 year: 2018 end-page: 2213 ident: b13 article-title: A machine learning-based protocol for efficient routing in opportunistic networks publication-title: IEEE Syst. J. – volume: 51 start-page: 36 year: 2013 end-page: 43 ident: b8 article-title: Are we ready for SDN? Implementation challenges for software-defined networks publication-title: IEEE Commun. Mag. – volume: 32 year: 2019 ident: b35 article-title: Codeword authenticated key exchange (CAKE) light weight secure routing protocol for WSN publication-title: Int. J. Commun. Syst. – volume: 107 start-page: 711 year: 2019 end-page: 731 ident: b15 article-title: Adaptable and data-driven softwarized networks: Review, opportunities, and challenges publication-title: Proc. IEEE – year: 2013 ident: b5 article-title: Playing atari with deep reinforcement learning – volume: 518 start-page: 529 year: 2015 end-page: 533 ident: b6 article-title: Human-level control through deep reinforcement learning publication-title: Nature – volume: 108 year: 2021 ident: b21 article-title: A predictive GA-based model for closed high-utility itemset mining publication-title: Appl. Soft Comput. – start-page: 68 year: 2018 end-page: 73 ident: b1 article-title: A fuzzy logic approach to increase quality of service in software defined networking publication-title: 2018 International Conference on Advances in Computing, Communication Control and Networking – start-page: 26 year: 2020 end-page: 38 ident: b10 article-title: Efficient SDN-based traffic monitoring in IoT networks with double deep Q-network – start-page: 49 year: 2020 end-page: 60 ident: b4 article-title: An end-to-end deep RL framework for task arrangement in crowdsourcing platforms publication-title: 2020 IEEE 36th International Conference on Data Engineering – volume: 212 year: 2021 ident: b24 article-title: ASRNN: A recurrent neural network with an attention model for sequence labeling publication-title: Knowl.-Based Syst. – start-page: 1 year: 2017 end-page: 6 ident: b31 article-title: NeuRoute: Predictive dynamic routing for software-defined networks publication-title: 2017 13th International Conference on Network and Service Management – start-page: 1 year: 2021 ident: b34 article-title: Federated learning-based anomaly detection for IoT security attacks publication-title: IEEE Internet Things J. – start-page: 139 year: 2021 end-page: 149 ident: b20 article-title: SCSZB: Sensor congregate stable zonal-based routing protocol designed for optimal WSN – volume: 26 start-page: 4319 year: 2020 end-page: 4338 ident: b17 article-title: RLProph: a dynamic programming based reinforcement learning approach for optimal routing in opportunistic IoT networks publication-title: Wirel. Netw. – volume: 21 start-page: 393 year: 2019 end-page: 430 ident: b9 article-title: A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges publication-title: IEEE Commun. Surv. Tutor. – volume: 115 start-page: 619 year: 2021 end-page: 640 ident: b23 article-title: A survey on security and privacy of federated learning publication-title: Future Gener. Comput. Syst. – start-page: 1 year: 2019 end-page: 8 ident: b33 article-title: Toward packet routing with fully-distributed multi-agent deep reinforcement learning publication-title: 2019 International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks – year: 2018 ident: b2 article-title: Graph neural networks: A review of methods and applications – volume: 9 start-page: 5803 year: 2016 end-page: 5833 ident: b7 article-title: Software-defined networking (SDN): a survey publication-title: Secur. Commun. Netw. – start-page: 670 year: 2017 end-page: 674 ident: b30 article-title: Including artificial intelligence in a routing protocol using software defined networks publication-title: 2017 IEEE International Conference on Communications Workshops – volume: 6 year: 1999 ident: b26 article-title: Packet routing in dynamically changing networks: A reinforcement learning approach publication-title: Adv. Neural Inf. Process. Syst. – volume: 10 year: 2020 ident: b29 article-title: Routing optimization in sdn using deep reinforcement learning publication-title: J. Eng. Comput. Archit. – volume: 18 start-page: 158 year: 2020 end-page: 169 ident: b12 article-title: Energy efficient sensor node deployment scheme for two stage routing protocol of wireless sensor networks assisted IoT publication-title: ECTI Trans. Electr. Eng. Electron. Commun. – start-page: 1 year: 2020 end-page: 6 ident: b25 article-title: On virtual id assignment in networks for high resilience routing: A theoretical framework publication-title: 2020 IEEE Global Communications Conference – volume: 143 start-page: 36 year: 2020 end-page: 46 ident: b11 article-title: Cost optimization of secure routing with untrusted devices in software defined networking publication-title: J. Parallel Distrib. Comput. – start-page: 25 year: 2016 end-page: 33 ident: b22 article-title: QoS-aware adaptive routing in multi-layer hierarchical software defined networks: A reinforcement learning approach publication-title: 2016 IEEE International Conference on Services Computing – year: 2017 ident: b3 article-title: Neural message passing for quantum chemistry – volume: 7 start-page: 2155 year: 2020 end-page: 2164 ident: b14 article-title: A software defined network based fuzzy normalized neural adaptive multipath congestion control for the internet of things publication-title: IEEE Trans. Netw. Sci. Eng. – volume: 4740 year: 2002 ident: b28 article-title: Fuzzy system for adaptive network routing publication-title: Proc. SPIE – volume: 6 start-page: 64533 year: 2018 ident: 10.1016/j.comcom.2021.07.025_b32 article-title: DROM: Optimizing the routing in software-defined networks with deep reinforcement learning publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2877686 – volume: 32 issue: 3 year: 2019 ident: 10.1016/j.comcom.2021.07.025_b35 article-title: Codeword authenticated key exchange (CAKE) light weight secure routing protocol for WSN publication-title: Int. J. Commun. Syst. doi: 10.1002/dac.3879 – start-page: 1 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b25 article-title: On virtual id assignment in networks for high resilience routing: A theoretical framework – volume: 21 start-page: 393 issue: 1 year: 2019 ident: 10.1016/j.comcom.2021.07.025_b9 article-title: A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges publication-title: IEEE Commun. Surv. Tutor. doi: 10.1109/COMST.2018.2866942 – volume: 18 start-page: 158 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b12 article-title: Energy efficient sensor node deployment scheme for two stage routing protocol of wireless sensor networks assisted IoT publication-title: ECTI Trans. Electr. Eng. Electron. Commun. doi: 10.37936/ecti-eec.2020182.240541 – volume: 16 year: 1958 ident: 10.1016/j.comcom.2021.07.025_b27 article-title: On a routing problem publication-title: Quart. Appl. Math. doi: 10.1090/qam/102435 – start-page: 670 year: 2017 ident: 10.1016/j.comcom.2021.07.025_b30 article-title: Including artificial intelligence in a routing protocol using software defined networks – volume: 108 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b21 article-title: A predictive GA-based model for closed high-utility itemset mining publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2021.107422 – volume: 6 year: 1999 ident: 10.1016/j.comcom.2021.07.025_b26 article-title: Packet routing in dynamically changing networks: A reinforcement learning approach publication-title: Adv. Neural Inf. Process. Syst. – year: 2020 ident: 10.1016/j.comcom.2021.07.025_b18 article-title: Energy-aware routing protocols for wireless sensor network based on fuzzy logic: A 10-years analytical review publication-title: EAI Endorsed Trans. Energy Web: Online First – start-page: 49 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b4 article-title: An end-to-end deep RL framework for task arrangement in crowdsourcing platforms – volume: 107 start-page: 711 issue: 4 year: 2019 ident: 10.1016/j.comcom.2021.07.025_b15 article-title: Adaptable and data-driven softwarized networks: Review, opportunities, and challenges publication-title: Proc. IEEE doi: 10.1109/JPROC.2019.2895553 – volume: 26 start-page: 4319 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b17 article-title: RLProph: a dynamic programming based reinforcement learning approach for optimal routing in opportunistic IoT networks publication-title: Wirel. Netw. doi: 10.1007/s11276-020-02331-1 – volume: 118 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b19 article-title: Accurate cluster head selection technique for software defined network in 5G VANET publication-title: Wirel. Pers. Commun. doi: 10.1007/s11277-021-08072-4 – start-page: 1 year: 2017 ident: 10.1016/j.comcom.2021.07.025_b31 article-title: NeuRoute: Predictive dynamic routing for software-defined networks – volume: 212 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b24 article-title: ASRNN: A recurrent neural network with an attention model for sequence labeling publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2020.106548 – start-page: 68 year: 2018 ident: 10.1016/j.comcom.2021.07.025_b1 article-title: A fuzzy logic approach to increase quality of service in software defined networking – volume: 4740 year: 2002 ident: 10.1016/j.comcom.2021.07.025_b28 article-title: Fuzzy system for adaptive network routing publication-title: Proc. SPIE doi: 10.1117/12.472955 – volume: 143 start-page: 36 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b11 article-title: Cost optimization of secure routing with untrusted devices in software defined networking publication-title: J. Parallel Distrib. Comput. doi: 10.1016/j.jpdc.2020.03.021 – start-page: 1 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b34 article-title: Federated learning-based anomaly detection for IoT security attacks publication-title: IEEE Internet Things J. – start-page: 25 year: 2016 ident: 10.1016/j.comcom.2021.07.025_b22 article-title: QoS-aware adaptive routing in multi-layer hierarchical software defined networks: A reinforcement learning approach – volume: 115 start-page: 619 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b23 article-title: A survey on security and privacy of federated learning publication-title: Future Gener. Comput. Syst. doi: 10.1016/j.future.2020.10.007 – year: 2017 ident: 10.1016/j.comcom.2021.07.025_b3 – volume: 9 start-page: 5803 issue: 18 year: 2016 ident: 10.1016/j.comcom.2021.07.025_b7 article-title: Software-defined networking (SDN): a survey publication-title: Secur. Commun. Netw. doi: 10.1002/sec.1737 – year: 2013 ident: 10.1016/j.comcom.2021.07.025_b5 – volume: 12 start-page: 2207 issue: 3 year: 2018 ident: 10.1016/j.comcom.2021.07.025_b13 article-title: A machine learning-based protocol for efficient routing in opportunistic networks publication-title: IEEE Syst. J. doi: 10.1109/JSYST.2016.2630923 – year: 2018 ident: 10.1016/j.comcom.2021.07.025_b2 – volume: 518 start-page: 529 year: 2015 ident: 10.1016/j.comcom.2021.07.025_b6 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236 – volume: 1284 year: 2019 ident: 10.1016/j.comcom.2021.07.025_b16 article-title: Research on routing algorithm based on reinforcement learning in SDN publication-title: J. Phys. Conf. Ser. doi: 10.1088/1742-6596/1284/1/012053 – start-page: 139 year: 2021 ident: 10.1016/j.comcom.2021.07.025_b20 – volume: 10 issue: 5 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b29 article-title: Routing optimization in sdn using deep reinforcement learning publication-title: J. Eng. Comput. Archit. – start-page: 1 year: 2019 ident: 10.1016/j.comcom.2021.07.025_b33 article-title: Toward packet routing with fully-distributed multi-agent deep reinforcement learning – start-page: 26 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b10 – volume: 7 start-page: 2155 issue: 4 year: 2020 ident: 10.1016/j.comcom.2021.07.025_b14 article-title: A software defined network based fuzzy normalized neural adaptive multipath congestion control for the internet of things publication-title: IEEE Trans. Netw. Sci. Eng. doi: 10.1109/TNSE.2020.2991106 – volume: 51 start-page: 36 issue: 7 year: 2013 ident: 10.1016/j.comcom.2021.07.025_b8 article-title: Are we ready for SDN? Implementation challenges for software-defined networks publication-title: IEEE Commun. Mag. doi: 10.1109/MCOM.2013.6553676 |
| SSID | ssj0004773 |
| Score | 2.5058713 |
| Snippet | In this paper, a graph neural net-based routing algorithm is designed which leverages global information from controller of a software-defined network to... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 169 |
| SubjectTerms | Deep Q-learning Deep Reinforcement Learning Graph Neural Networks Q-table Routing algorithm Routing optimization Software-Defined Networking |
| Title | GraphNET: Graph Neural Networks for routing optimization in Software Defined Networks |
| URI | https://dx.doi.org/10.1016/j.comcom.2021.07.025 |
| Volume | 178 |
| WOSCitedRecordID | wos000703166900002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-703X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004773 issn: 0140-3664 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JbtswECXcpIf2UHRFky7goTdDgHZSvQWpuwE1CtgBfBNIikScJnJgK06-It_c4Sq1KdLm0ItACSYla55mhoM3Mwi9K0WaN1lZRVw1WZRTnkdMJHkkiZJgkljBS26aTZDplC4W1ffR6NrnwmxPSdvSq6vq_L-KGq6BsHXq7B3EHRaFCzAGocMRxA7HfxL8J12CejqZ672-GY91AQ6QxNQyvk0BhvF6dWEJz6Ayzlwupo59zEAtX2o22AepwAFtwqyhF-tbQWhCep9eErzz2SXTBBsdlDeqZwsnmxB2Pjxm3His39bLpqclzkwNbasCwUT-GBvyd6AHHa82JgB01HXsbBiqSJNAeuujl6D0S1u2PKhf28LHKdDENm5xtjixjYluqHkbcTjRUtKcH30vU4LV5lD_WlX7N2sXOIie3nZS21VqvUodkxpWuYd2U1JUoOh3D75MFl_7TFtiOQv-j_hkTMMYvPk0f3Z2Bg7M_DF65HYe-MAi5gkayfYpejioR_kMHXnsvMdmhC1ysMcABuRghxw8RA5ettgjBzvkhFnP0fzjZH74OXJ9NyIBG8gugq83J7TJlWoEZSlNGCuZSvRem9OmYnEqVVUxKWgsVcELymHPnzFJBG8YmIgXaKddtfIlwiqFFcHlVkUhcqIaHitSxhkYWRILmtE9lPn3UwtXk163Rjmtb5POHorCrHNbk-Uvvyf-1dfOr7T-Yg14unXm_h3v9Ao96HH_Gu106wv5Bt0X2265Wb91YPoJLGielw |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=GraphNET%3A+Graph+Neural+Networks+for+routing+optimization+in+Software+Defined+Networks&rft.jtitle=Computer+communications&rft.au=Swaminathan%2C+Avinash&rft.au=Chaba%2C+Mridul&rft.au=Sharma%2C+Deepak+Kumar&rft.au=Ghosh%2C+Uttam&rft.date=2021-10-01&rft.issn=0140-3664&rft.volume=178&rft.spage=169&rft.epage=182&rft_id=info:doi/10.1016%2Fj.comcom.2021.07.025&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_comcom_2021_07_025 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0140-3664&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0140-3664&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0140-3664&client=summon |