Multi-agent deep reinforcement learning algorithm with self-adaption division strategy for VNF-SC deployment in SDN/NFV-Enabled Networks
Network function virtualization can decouple the traditional network function from the dedicated hardware, abstracts the software-based virtual network function from the specialized network equipment, and promotes the fundamental transformation of network service deployment mode. However, the deploy...
Uloženo v:
| Vydáno v: | Applied soft computing Ročník 138; s. 110189 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.05.2023
|
| Témata: | |
| ISSN: | 1568-4946, 1872-9681 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Network function virtualization can decouple the traditional network function from the dedicated hardware, abstracts the software-based virtual network function from the specialized network equipment, and promotes the fundamental transformation of network service deployment mode. However, the deployment of virtual network function (VNF) service chain is an important and crucial problem and key technology faced and must be rescued. In this paper, the problem of VNF service chain deployment in SDN/NFV-Enabled Networks is investigated. The existing solution strategies based on optimization methods (dynamic programming, linear programming, etc.) and heuristic methods (genetic algorithm, particle swarm optimization, etc.) are only suitable for operation deployment in the case of predictable operations, and it is difficult to meet the real-time support operation scheduling requirements in high dynamic combat scenarios. A new real-time algorithm for VNF service chain deployment based on multi-agent deep reinforcement learning with self-adaption division strategy (MDRL-SaDS) to minimize energy consumption in a period of time is proposed. In proposed algorithm, an oriented self-adaptive strategy to determination the number of agents and the optimal division method of VNF service chain for the markov process modeling is designed. Constructing a new neural network model and design a training strategy of joint supervised and unsupervised learning. The global and long-term benefits are used to optimize the scheduling process, and the decision-making framework of offline learning and online deployment is used to solve the VNF service chain deployment problem. Finally, experimental results indicate that the MDRL-SaDS has more advantages and has higher convergence speed, average reward value and stability than compared algorithms, while decreasing the energy consumption in a period of time.
•An optimization model with the goal of minimizing energy consumption is formulated to determine a VNF service chain strategy.•A new real-time algorithm for VNF service chain deployment problem based on multi-agent deep reinforcement learning with self-adaption division strategy (MDRL-SaDS) is proposed.•To determine the optimal number of agents, a clustering method with a new weighted distance calculation is investigated. |
|---|---|
| AbstractList | Network function virtualization can decouple the traditional network function from the dedicated hardware, abstracts the software-based virtual network function from the specialized network equipment, and promotes the fundamental transformation of network service deployment mode. However, the deployment of virtual network function (VNF) service chain is an important and crucial problem and key technology faced and must be rescued. In this paper, the problem of VNF service chain deployment in SDN/NFV-Enabled Networks is investigated. The existing solution strategies based on optimization methods (dynamic programming, linear programming, etc.) and heuristic methods (genetic algorithm, particle swarm optimization, etc.) are only suitable for operation deployment in the case of predictable operations, and it is difficult to meet the real-time support operation scheduling requirements in high dynamic combat scenarios. A new real-time algorithm for VNF service chain deployment based on multi-agent deep reinforcement learning with self-adaption division strategy (MDRL-SaDS) to minimize energy consumption in a period of time is proposed. In proposed algorithm, an oriented self-adaptive strategy to determination the number of agents and the optimal division method of VNF service chain for the markov process modeling is designed. Constructing a new neural network model and design a training strategy of joint supervised and unsupervised learning. The global and long-term benefits are used to optimize the scheduling process, and the decision-making framework of offline learning and online deployment is used to solve the VNF service chain deployment problem. Finally, experimental results indicate that the MDRL-SaDS has more advantages and has higher convergence speed, average reward value and stability than compared algorithms, while decreasing the energy consumption in a period of time.
•An optimization model with the goal of minimizing energy consumption is formulated to determine a VNF service chain strategy.•A new real-time algorithm for VNF service chain deployment problem based on multi-agent deep reinforcement learning with self-adaption division strategy (MDRL-SaDS) is proposed.•To determine the optimal number of agents, a clustering method with a new weighted distance calculation is investigated. |
| ArticleNumber | 110189 |
| Author | Xuan, Hejun Zhou, Yi Zhao, Xuelin Liu, Zhenghui |
| Author_xml | – sequence: 1 givenname: Hejun surname: Xuan fullname: Xuan, Hejun email: xuanhejun0896@xynu.edu.cn organization: School of Computer and Information Technology, Xinyang Normal University, Henan Xinyang, 464000, China – sequence: 2 givenname: Yi surname: Zhou fullname: Zhou, Yi organization: School of Artificial Intelligence, Henan University, Henan Zhengzhou, 450000, China – sequence: 3 givenname: Xuelin surname: Zhao fullname: Zhao, Xuelin organization: School of Computer and Information Technology, Xinyang Normal University, Henan Xinyang, 464000, China – sequence: 4 givenname: Zhenghui surname: Liu fullname: Liu, Zhenghui organization: School of Computer and Information Technology, Xinyang Normal University, Henan Xinyang, 464000, China |
| BookMark | eNp9kMFOGzEQhi1EpQLtC_TkF3DwepONV-KCAoFKND3QcrXG9jg4bOzINqC8AY-Nt-HUA5eZ0UjfL_3fKTkOMSAhPxo-aXjTnW8mkKOZCC7aSVM_sj8iJ42cC9Z3sjmu96yTbNpPu6_kNOcNr1Av5Al5-_U8FM9gjaFQi7ijCX1wMRncjq8BIQUf1hSGdUy-PG7pa5004-AYWNgVHwO1_sXn8cglQcH1ntYE-rBasvtFTd0Ncf8vzQd6f7U6Xy0f2HUAPaClKyyvMT3lb-SLgyHj9499Rv4ur_8sbtnd75ufi8s7ZlrOCxPGug6F1qJt5WzuQPYcpNZ9Zy00BiTMgGs-nRnXVgvYCau101rO-87hlLdnRBxyTYo5J3Rql_wW0l41XI0u1UaNLtXoUh1cVkj-BxlfYKxe-_rhc_TigGIt9eIxqWw8BoPWJzRF2eg_w98BgvaVJw |
| CitedBy_id | crossref_primary_10_1109_TWC_2024_3464639 crossref_primary_10_1109_TMC_2023_3301506 crossref_primary_10_1016_j_jocs_2024_102399 crossref_primary_10_1109_COMST_2024_3442149 |
| Cites_doi | 10.1109/MWC.2016.1600317WC 10.1109/TPDS.2018.2880992 10.1109/TNSM.2016.2569020 10.1109/TSC.2018.2849712 10.1016/j.comnet.2017.01.008 10.1016/j.media.2017.07.005 10.1287/moor.27.4.819.297 10.1016/j.future.2021.02.011 10.1109/JSAC.2020.2986592 10.1016/j.asoc.2018.01.028 10.1016/j.comnet.2015.09.015 10.1016/j.jnca.2021.103208 10.1109/TVT.2019.2952549 10.1109/TC.2017.2709742 10.1109/CC.2018.8387988 10.1109/JSAC.2017.2760158 10.1016/j.asoc.2018.12.037 10.1109/MNET.2018.1700394 10.1109/JSAC.2021.3087227 10.1109/TPDS.2018.2802518 10.1109/TNSM.2016.2598068 10.1109/TCC.2017.2780165 10.1109/COMST.2016.2586999 10.1016/j.asoc.2021.107798 10.1016/j.sysarc.2009.09.001 10.1109/TCC.2017.2721401 10.1016/j.jnca.2016.12.019 10.1109/TNET.2019.2959588 10.1109/TC.2020.2967661 10.1109/TMC.2013.39 10.1016/j.jnca.2016.09.001 10.1109/COMST.2017.2707140 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier B.V. |
| Copyright_xml | – notice: 2023 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2023.110189 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-9681 |
| ExternalDocumentID | 10_1016_j_asoc_2023_110189 S1568494623002077 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF HZ~ IHE J1W JJJVA KOM M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~G- 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c300t-2cdf6e2bb233857fa890a8bb96dda1ca8a5a0b045cf3189e62dbbfbb8796fe403 |
| ISICitedReferencesCount | 7 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001027291500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1568-4946 |
| IngestDate | Sat Nov 29 07:03:00 EST 2025 Tue Nov 18 20:54:00 EST 2025 Fri Feb 23 02:36:52 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep reinforcement learning SDN/NFV-Enabled Networks Network virtualization VNF-SC Self-adaption division strategy |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-2cdf6e2bb233857fa890a8bb96dda1ca8a5a0b045cf3189e62dbbfbb8796fe403 |
| ParticipantIDs | crossref_primary_10_1016_j_asoc_2023_110189 crossref_citationtrail_10_1016_j_asoc_2023_110189 elsevier_sciencedirect_doi_10_1016_j_asoc_2023_110189 |
| PublicationCentury | 2000 |
| PublicationDate | May 2023 2023-05-00 |
| PublicationDateYYYYMMDD | 2023-05-01 |
| PublicationDate_xml | – month: 05 year: 2023 text: May 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2023 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Mangat, Kaur, Saluja (b35) 2020; 38 Khatiria, Mirjalilya, Luo (b34) 2022; 203 Khebbache, Hadji, Zeghlache (b1) 2017; 114 Pei, Hong, Xue, Li (b38) 2019; 30 Bari, Chowdhury, Duarte (b7) 2016; 13 Karakus, Durresi (b10) 2017; 80 Kato, Fadlullah, Mao, Tang, Akashi, Inoue, Mizutani (b30) 2017; 43 Chao, Jw, Xw (b15) 2022; 120 Fadlullah, Tang, Mao, Kato, Akashi, Inoue, Mizutani (b17) 2017; 19 Litjens, Kooi, Bejnordi, Setio, Sánchez (b19) 2017; 42 Huang, Guo, Wu, Li (b23) 2017; 7 Ramaswamy, Wolf (b39) 2009; 55 Do, Gregory, Li (b16) 2021; 189 Bhamare, Jain, Samaka, Erbad (b29) 2016; 75 Nouar, Yangui, Faci, Drira, Tazi (b5) 2021; 195 Zahedi, Jamali, Bayat (b6) 2022 Huang, Zeng, Zhao, Min, Hu (b27) 2021; 39 Wang, Xing, Zhan, Luo, Dai, Iqbal (b32) 2021; 112 Huang, Yang, Wang, Ding, Sari, Adachi (b18) 2020; 69 Mechtri, Ghribi, Zeghlache (b21) 2016; 13 Bernstein, Givan, Immerman, Zilberstein (b36) 2002; 27 Cheng, Chen, Hu, Wang, Lan (b25) 2015; 92 Mercian, Mcgarry, Reisslein, Kellerer (b9) 2016; 18 Pei, Hong, Xue, Li (b26) 2018; 14 Yang, Yeung (b13) 2020; 28 Pajarinen, Hottinen, Peltonen (b37) 2014; 13 Haque, Saha (b11) 2021; 193 Li, Zhou, Feng, Li, Xu (b28) 2018; 15 Yu, Xue, Xiang (b22) 2017; 35 Huang, Li, Guo, Liang, Wang (b24) 2017; 8 Khan, Hussain, Hussain (b12) 2021; 119 Pei, Hong, Xue, Li, Wu (b40) 2020; 38 Shokouhifar (b4) 2021; 107 Li, Ota, Dong (b2) 2018; 33 Zou, Tang, Ni, Liu, Wang (b3) 2018; 66 Li, Hong, Xue, Pei (b14) 2018; 29 Kato, Fadlullah, Mao, Tang, Akashi, Inoue, Mizutani (b20) 2016; 24 Mao, Fadlullah, Tang, Kato, Osamu (b31) 2017; 66 Bao, Yuan, Zhou, Zomaya (b8) 2020; 69 Xing, Zhou, Wang, Luo, Dai, Li, Yang (b33) 2019; 76 Bernstein (10.1016/j.asoc.2023.110189_b36) 2002; 27 Fadlullah (10.1016/j.asoc.2023.110189_b17) 2017; 19 Pajarinen (10.1016/j.asoc.2023.110189_b37) 2014; 13 Chao (10.1016/j.asoc.2023.110189_b15) 2022; 120 Li (10.1016/j.asoc.2023.110189_b28) 2018; 15 Khan (10.1016/j.asoc.2023.110189_b12) 2021; 119 Zahedi (10.1016/j.asoc.2023.110189_b6) 2022 Ramaswamy (10.1016/j.asoc.2023.110189_b39) 2009; 55 Huang (10.1016/j.asoc.2023.110189_b23) 2017; 7 Li (10.1016/j.asoc.2023.110189_b14) 2018; 29 Mangat (10.1016/j.asoc.2023.110189_b35) 2020; 38 Khatiria (10.1016/j.asoc.2023.110189_b34) 2022; 203 Wang (10.1016/j.asoc.2023.110189_b32) 2021; 112 Do (10.1016/j.asoc.2023.110189_b16) 2021; 189 Pei (10.1016/j.asoc.2023.110189_b26) 2018; 14 Xing (10.1016/j.asoc.2023.110189_b33) 2019; 76 Huang (10.1016/j.asoc.2023.110189_b18) 2020; 69 Huang (10.1016/j.asoc.2023.110189_b24) 2017; 8 Bari (10.1016/j.asoc.2023.110189_b7) 2016; 13 Shokouhifar (10.1016/j.asoc.2023.110189_b4) 2021; 107 Nouar (10.1016/j.asoc.2023.110189_b5) 2021; 195 Kato (10.1016/j.asoc.2023.110189_b30) 2017; 43 Litjens (10.1016/j.asoc.2023.110189_b19) 2017; 42 Li (10.1016/j.asoc.2023.110189_b2) 2018; 33 Yang (10.1016/j.asoc.2023.110189_b13) 2020; 28 Pei (10.1016/j.asoc.2023.110189_b38) 2019; 30 Mechtri (10.1016/j.asoc.2023.110189_b21) 2016; 13 Pei (10.1016/j.asoc.2023.110189_b40) 2020; 38 Khebbache (10.1016/j.asoc.2023.110189_b1) 2017; 114 Bhamare (10.1016/j.asoc.2023.110189_b29) 2016; 75 Mao (10.1016/j.asoc.2023.110189_b31) 2017; 66 Yu (10.1016/j.asoc.2023.110189_b22) 2017; 35 Zou (10.1016/j.asoc.2023.110189_b3) 2018; 66 Huang (10.1016/j.asoc.2023.110189_b27) 2021; 39 Haque (10.1016/j.asoc.2023.110189_b11) 2021; 193 Karakus (10.1016/j.asoc.2023.110189_b10) 2017; 80 Kato (10.1016/j.asoc.2023.110189_b20) 2016; 24 Mercian (10.1016/j.asoc.2023.110189_b9) 2016; 18 Bao (10.1016/j.asoc.2023.110189_b8) 2020; 69 Cheng (10.1016/j.asoc.2023.110189_b25) 2015; 92 |
| References_xml | – volume: 27 start-page: 819 year: 2002 end-page: 840 ident: b36 article-title: The complexity of decentralized control of Markov decision processes publication-title: Math. Oper. Res. – volume: 13 start-page: 533 year: 2016 end-page: 546 ident: b21 article-title: A scalable algorithm for the placement of service function chains publication-title: IEEE Trans. Netw. Serv. Manag. – volume: 193 year: 2021 ident: b11 article-title: SoftIoT: A resource-aware SDN/NFV-based IoT network publication-title: J. Netw. Comput. Appl. – volume: 92 start-page: 396 year: 2015 end-page: 407 ident: b25 article-title: Enabling network function combination via service chain instantiation publication-title: Comput. Netw. – volume: 24 start-page: 146 year: 2016 end-page: 153 ident: b20 article-title: The deep learning vision for heterogeneous network traffic control: Proposal, challenges, and future perspective publication-title: IEEE Wirel. Commun. – volume: 28 start-page: 312 year: 2020 end-page: 321 ident: b13 article-title: SDN candidate selection in hybrid IP/SDN networks for single link failure protection publication-title: IEEE/ACM Trans. Netw. – volume: 35 start-page: 2522 year: 2017 end-page: 2531 ident: b22 article-title: Qos-aware and reliable traffic steering for service function chaining in mobile networks publication-title: IEEE J. Sel. Areas Commun. – volume: 14 start-page: 985 year: 2018 end-page: 997 ident: b26 article-title: Resource aware routing for service function chains in SDN and NFV-enabled network publication-title: IEEE Trans. Serv. Comput. – volume: 30 start-page: 2179 year: 2019 end-page: 2192 ident: b38 article-title: Efficiently embedding service function chains with dynamic virtual network function placement in geo-distributed cloud system publication-title: IEEE Trans. Parallel Distrib. Syst. – volume: 7 start-page: 1082 year: 2017 end-page: 1094 ident: b23 article-title: Service chaining for hybrid network function publication-title: IEEE Trans. Cloud Comput. – volume: 69 start-page: 800 year: 2020 end-page: 811 ident: b8 article-title: Prune and plant: Efficient placement and parallelism of virtual network functions publication-title: IEEE Trans. Comput. – volume: 15 start-page: 77 year: 2018 end-page: 91 ident: b28 article-title: Horizontal-based orchestration for multi-domain SFC in SDN/NFV-enabled satellite/terrestrial networks publication-title: China Commun. – volume: 66 start-page: 1946 year: 2017 end-page: 1960 ident: b31 article-title: Routing or computing? The paradigm shift towards intelligent computer network packet transmission based on deep learning publication-title: IEEE Trans. Comput. – volume: 38 start-page: 1102 year: 2020 end-page: 1117 ident: b40 article-title: Two-phase virtual network function selection and chaining algorithm based on deep learning in SDN/NFV-enabled networks publication-title: IEEE J. Sel. Areas Commun. – volume: 33 start-page: 136 year: 2018 end-page: 141 ident: b2 article-title: DeepNFV: A light-weight framework for intelligent edge network functions virtualization publication-title: IEEE Netw. – volume: 114 start-page: 95 year: 2017 end-page: 110 ident: b1 article-title: Virtualized network functions chaining and routing algorithms publication-title: Comput. Netw. – volume: 203 year: 2022 ident: b34 article-title: Balanced resource allocation for VNF service chain provisioning in inter-datacenter elastic optical networks publication-title: Appl. Soft Comput. – volume: 18 start-page: 2738 year: 2016 end-page: 2786 ident: b9 article-title: Software defined optical networks (SDONs): A comprehensive survey publication-title: IEEE Commun. Surv. Tutor. – volume: 39 start-page: 2558 year: 2021 end-page: 2571 ident: b27 article-title: Scalable service function chain orchestration in NFV-enabled networks: A federated reinforcement learning approach publication-title: IEEE J. Sel. Areas Commun. – volume: 13 start-page: 725 year: 2016 end-page: 739 ident: b7 article-title: Orchestrating virtualized network functions publication-title: IEEE Trans. Netw. Serv. Manag. – volume: 8 start-page: 585 year: 2017 end-page: 596 ident: b24 article-title: Near-optimal deployment of service chains by exploiting correlations between network functions publication-title: IEEE Trans. Cloud Comput. – volume: 107 year: 2021 ident: b4 article-title: FH-ACO: Fuzzy heuristic-based ant colony optimization for joint virtual network function placement and routing publication-title: Appl. Soft Comput. – volume: 29 start-page: 1664 year: 2018 end-page: 1677 ident: b14 article-title: Virtual network function placement considering resource optimization and SFC requests in cloud datacenter publication-title: IEEE Trans. Parallel Distrib. Syst. – volume: 69 start-page: 1117 year: 2020 end-page: 1121 ident: b18 article-title: Deep reinforcement learning for UAV navigation through massive MIMO technique publication-title: IEEE Trans. Veh. Technol. – volume: 42 start-page: 60 year: 2017 end-page: 88 ident: b19 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. – volume: 75 start-page: 138 year: 2016 end-page: 155 ident: b29 article-title: A survey on service function chaining publication-title: J. Netw. Comput. Appl. – volume: 195 year: 2021 ident: b5 article-title: A semantic virtualized network functions description and discovery model publication-title: Comput. Netw. – volume: 120 year: 2022 ident: b15 article-title: Towards delay-optimized and resource-efficient network function dynamic deployment for VNF service chaining publication-title: Appl. Soft Comput. – volume: 38 year: 2020 ident: b35 article-title: A comprehensive survey of service function chain provisioning approaches in SDN and NFV architecture publication-title: Comp. Sci. Rev. – year: 2022 ident: b6 article-title: EmcFIS: Evolutionary multi-criteria fuzzy inference system for virtual network function placement and routing publication-title: Appl. Soft Comput. – volume: 76 start-page: 575 year: 2019 end-page: 594 ident: b33 article-title: An integer encoding grey wolf optimizer for virtual network function placement publication-title: Appl. Soft Comput. – volume: 19 start-page: 2432 year: 2017 end-page: 2455 ident: b17 article-title: State-of-the-art deep learning: Evolving machine intelligence toward tomorrow’s intelligent network traffic control systems publication-title: IEEE Commun. Surv. Tutor. – volume: 43 start-page: 146 year: 2017 end-page: 153 ident: b30 article-title: The deep learning vision for heterogeneous network traffic control: Proposal, challenges, and future perspective publication-title: IEEE Wirel. Commun. – volume: 13 start-page: 866 year: 2014 end-page: 879 ident: b37 article-title: Optimizing spatial and temporal reuse in wireless networks by decentralized partially observable Markov decision processes publication-title: IEEE Trans. Mob. Comput. – volume: 55 start-page: 421 year: 2009 end-page: 433 ident: b39 article-title: Analysis of network processing workloads publication-title: J. Syst. Archit. – volume: 66 start-page: 220 year: 2018 end-page: 231 ident: b3 article-title: Resource multi-objective mapping algorithm based on virtualized network functions: RMMA publication-title: Appl. Soft Comput. – volume: 112 year: 2021 ident: b32 article-title: A two-stage approach for multicast-oriented virtual network function placement publication-title: Appl. Soft Comput. – volume: 189 year: 2021 ident: b16 article-title: SDN-based wireless mobile backhaul architecture: Review and challenges publication-title: J. Netw. Comput. Appl. – volume: 80 start-page: 200 year: 2017 end-page: 218 ident: b10 article-title: Quality of service (QoS) in software defined networking (SDN): A survey publication-title: J. Netw. Comput. Appl. – volume: 119 start-page: 176 year: 2021 end-page: 187 ident: b12 article-title: Guaranteeing end-to-end QoS provisioning in SOA based SDN architecture: A survey and open issues publication-title: Future Gener. Comput. Syst. – volume: 107 issue: 2 year: 2021 ident: 10.1016/j.asoc.2023.110189_b4 article-title: FH-ACO: Fuzzy heuristic-based ant colony optimization for joint virtual network function placement and routing publication-title: Appl. Soft Comput. – volume: 43 start-page: 146 issue: 3 year: 2017 ident: 10.1016/j.asoc.2023.110189_b30 article-title: The deep learning vision for heterogeneous network traffic control: Proposal, challenges, and future perspective publication-title: IEEE Wirel. Commun. doi: 10.1109/MWC.2016.1600317WC – volume: 30 start-page: 2179 issue: 99 year: 2019 ident: 10.1016/j.asoc.2023.110189_b38 article-title: Efficiently embedding service function chains with dynamic virtual network function placement in geo-distributed cloud system publication-title: IEEE Trans. Parallel Distrib. Syst. doi: 10.1109/TPDS.2018.2880992 – volume: 13 start-page: 725 issue: 4 year: 2016 ident: 10.1016/j.asoc.2023.110189_b7 article-title: Orchestrating virtualized network functions publication-title: IEEE Trans. Netw. Serv. Manag. doi: 10.1109/TNSM.2016.2569020 – volume: 14 start-page: 985 issue: 4 year: 2018 ident: 10.1016/j.asoc.2023.110189_b26 article-title: Resource aware routing for service function chains in SDN and NFV-enabled network publication-title: IEEE Trans. Serv. Comput. doi: 10.1109/TSC.2018.2849712 – volume: 203 year: 2022 ident: 10.1016/j.asoc.2023.110189_b34 article-title: Balanced resource allocation for VNF service chain provisioning in inter-datacenter elastic optical networks publication-title: Appl. Soft Comput. – volume: 114 start-page: 95 year: 2017 ident: 10.1016/j.asoc.2023.110189_b1 article-title: Virtualized network functions chaining and routing algorithms publication-title: Comput. Netw. doi: 10.1016/j.comnet.2017.01.008 – volume: 42 start-page: 60 issue: 9 year: 2017 ident: 10.1016/j.asoc.2023.110189_b19 article-title: A survey on deep learning in medical image analysis publication-title: Med. Image Anal. doi: 10.1016/j.media.2017.07.005 – volume: 27 start-page: 819 issue: 4 year: 2002 ident: 10.1016/j.asoc.2023.110189_b36 article-title: The complexity of decentralized control of Markov decision processes publication-title: Math. Oper. Res. doi: 10.1287/moor.27.4.819.297 – volume: 119 start-page: 176 year: 2021 ident: 10.1016/j.asoc.2023.110189_b12 article-title: Guaranteeing end-to-end QoS provisioning in SOA based SDN architecture: A survey and open issues publication-title: Future Gener. Comput. Syst. doi: 10.1016/j.future.2021.02.011 – volume: 195 issue: 5 year: 2021 ident: 10.1016/j.asoc.2023.110189_b5 article-title: A semantic virtualized network functions description and discovery model publication-title: Comput. Netw. – volume: 38 start-page: 1102 issue: 6 year: 2020 ident: 10.1016/j.asoc.2023.110189_b40 article-title: Two-phase virtual network function selection and chaining algorithm based on deep learning in SDN/NFV-enabled networks publication-title: IEEE J. Sel. Areas Commun. doi: 10.1109/JSAC.2020.2986592 – volume: 66 start-page: 220 issue: 1 year: 2018 ident: 10.1016/j.asoc.2023.110189_b3 article-title: Resource multi-objective mapping algorithm based on virtualized network functions: RMMA publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.01.028 – issue: 117 year: 2022 ident: 10.1016/j.asoc.2023.110189_b6 article-title: EmcFIS: Evolutionary multi-criteria fuzzy inference system for virtual network function placement and routing publication-title: Appl. Soft Comput. – volume: 189 issue: 3 year: 2021 ident: 10.1016/j.asoc.2023.110189_b16 article-title: SDN-based wireless mobile backhaul architecture: Review and challenges publication-title: J. Netw. Comput. Appl. – volume: 92 start-page: 396 issue: 9 year: 2015 ident: 10.1016/j.asoc.2023.110189_b25 article-title: Enabling network function combination via service chain instantiation publication-title: Comput. Netw. doi: 10.1016/j.comnet.2015.09.015 – volume: 120 year: 2022 ident: 10.1016/j.asoc.2023.110189_b15 article-title: Towards delay-optimized and resource-efficient network function dynamic deployment for VNF service chaining publication-title: Appl. Soft Comput. – volume: 38 year: 2020 ident: 10.1016/j.asoc.2023.110189_b35 article-title: A comprehensive survey of service function chain provisioning approaches in SDN and NFV architecture publication-title: Comp. Sci. Rev. – volume: 193 year: 2021 ident: 10.1016/j.asoc.2023.110189_b11 article-title: SoftIoT: A resource-aware SDN/NFV-based IoT network publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2021.103208 – volume: 69 start-page: 1117 issue: 1 year: 2020 ident: 10.1016/j.asoc.2023.110189_b18 article-title: Deep reinforcement learning for UAV navigation through massive MIMO technique publication-title: IEEE Trans. Veh. Technol. doi: 10.1109/TVT.2019.2952549 – volume: 24 start-page: 146 issue: 3 year: 2016 ident: 10.1016/j.asoc.2023.110189_b20 article-title: The deep learning vision for heterogeneous network traffic control: Proposal, challenges, and future perspective publication-title: IEEE Wirel. Commun. doi: 10.1109/MWC.2016.1600317WC – volume: 66 start-page: 1946 issue: 11 year: 2017 ident: 10.1016/j.asoc.2023.110189_b31 article-title: Routing or computing? The paradigm shift towards intelligent computer network packet transmission based on deep learning publication-title: IEEE Trans. Comput. doi: 10.1109/TC.2017.2709742 – volume: 15 start-page: 77 issue: 005 year: 2018 ident: 10.1016/j.asoc.2023.110189_b28 article-title: Horizontal-based orchestration for multi-domain SFC in SDN/NFV-enabled satellite/terrestrial networks publication-title: China Commun. doi: 10.1109/CC.2018.8387988 – volume: 35 start-page: 2522 issue: 11 year: 2017 ident: 10.1016/j.asoc.2023.110189_b22 article-title: Qos-aware and reliable traffic steering for service function chaining in mobile networks publication-title: IEEE J. Sel. Areas Commun. doi: 10.1109/JSAC.2017.2760158 – volume: 76 start-page: 575 year: 2019 ident: 10.1016/j.asoc.2023.110189_b33 article-title: An integer encoding grey wolf optimizer for virtual network function placement publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.12.037 – volume: 33 start-page: 136 issue: 1 year: 2018 ident: 10.1016/j.asoc.2023.110189_b2 article-title: DeepNFV: A light-weight framework for intelligent edge network functions virtualization publication-title: IEEE Netw. doi: 10.1109/MNET.2018.1700394 – volume: 39 start-page: 2558 issue: 8 year: 2021 ident: 10.1016/j.asoc.2023.110189_b27 article-title: Scalable service function chain orchestration in NFV-enabled networks: A federated reinforcement learning approach publication-title: IEEE J. Sel. Areas Commun. doi: 10.1109/JSAC.2021.3087227 – volume: 29 start-page: 1664 issue: 7 year: 2018 ident: 10.1016/j.asoc.2023.110189_b14 article-title: Virtual network function placement considering resource optimization and SFC requests in cloud datacenter publication-title: IEEE Trans. Parallel Distrib. Syst. doi: 10.1109/TPDS.2018.2802518 – volume: 13 start-page: 533 issue: 3 year: 2016 ident: 10.1016/j.asoc.2023.110189_b21 article-title: A scalable algorithm for the placement of service function chains publication-title: IEEE Trans. Netw. Serv. Manag. doi: 10.1109/TNSM.2016.2598068 – volume: 8 start-page: 585 issue: 2 year: 2017 ident: 10.1016/j.asoc.2023.110189_b24 article-title: Near-optimal deployment of service chains by exploiting correlations between network functions publication-title: IEEE Trans. Cloud Comput. doi: 10.1109/TCC.2017.2780165 – volume: 18 start-page: 2738 issue: 4 year: 2016 ident: 10.1016/j.asoc.2023.110189_b9 article-title: Software defined optical networks (SDONs): A comprehensive survey publication-title: IEEE Commun. Surv. Tutor. doi: 10.1109/COMST.2016.2586999 – volume: 112 year: 2021 ident: 10.1016/j.asoc.2023.110189_b32 article-title: A two-stage approach for multicast-oriented virtual network function placement publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2021.107798 – volume: 55 start-page: 421 issue: 10 year: 2009 ident: 10.1016/j.asoc.2023.110189_b39 article-title: Analysis of network processing workloads publication-title: J. Syst. Archit. doi: 10.1016/j.sysarc.2009.09.001 – volume: 7 start-page: 1082 issue: 4 year: 2017 ident: 10.1016/j.asoc.2023.110189_b23 article-title: Service chaining for hybrid network function publication-title: IEEE Trans. Cloud Comput. doi: 10.1109/TCC.2017.2721401 – volume: 80 start-page: 200 year: 2017 ident: 10.1016/j.asoc.2023.110189_b10 article-title: Quality of service (QoS) in software defined networking (SDN): A survey publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2016.12.019 – volume: 28 start-page: 312 issue: 1 year: 2020 ident: 10.1016/j.asoc.2023.110189_b13 article-title: SDN candidate selection in hybrid IP/SDN networks for single link failure protection publication-title: IEEE/ACM Trans. Netw. doi: 10.1109/TNET.2019.2959588 – volume: 69 start-page: 800 issue: 6 year: 2020 ident: 10.1016/j.asoc.2023.110189_b8 article-title: Prune and plant: Efficient placement and parallelism of virtual network functions publication-title: IEEE Trans. Comput. doi: 10.1109/TC.2020.2967661 – volume: 13 start-page: 866 issue: 4 year: 2014 ident: 10.1016/j.asoc.2023.110189_b37 article-title: Optimizing spatial and temporal reuse in wireless networks by decentralized partially observable Markov decision processes publication-title: IEEE Trans. Mob. Comput. doi: 10.1109/TMC.2013.39 – volume: 75 start-page: 138 year: 2016 ident: 10.1016/j.asoc.2023.110189_b29 article-title: A survey on service function chaining publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2016.09.001 – volume: 19 start-page: 2432 issue: 4 year: 2017 ident: 10.1016/j.asoc.2023.110189_b17 article-title: State-of-the-art deep learning: Evolving machine intelligence toward tomorrow’s intelligent network traffic control systems publication-title: IEEE Commun. Surv. Tutor. doi: 10.1109/COMST.2017.2707140 |
| SSID | ssj0016928 |
| Score | 2.4164343 |
| Snippet | Network function virtualization can decouple the traditional network function from the dedicated hardware, abstracts the software-based virtual network... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 110189 |
| SubjectTerms | Deep reinforcement learning Network virtualization SDN/NFV-Enabled Networks Self-adaption division strategy VNF-SC |
| Title | Multi-agent deep reinforcement learning algorithm with self-adaption division strategy for VNF-SC deployment in SDN/NFV-Enabled Networks |
| URI | https://dx.doi.org/10.1016/j.asoc.2023.110189 |
| Volume | 138 |
| WOSCitedRecordID | wos001027291500001&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: 1872-9681 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016928 issn: 1568-4946 databaseCode: AIEXJ dateStart: 20010601 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1fb9MwELdKxwMv_EcbA-QH3iqPJmkS-3EarQZCFdLGVO0lsmOnTRXSqk2m8Q32AfjAnO04yzY0ARIvUWXFdpT79e58ud8dQu9lxn0qeEbSULcwk8ojjEYeSSnzVQw2LfK4aTYRT6d0NmNfe72fjgtzUcRlSS8v2fq_ihrGQNiaOvsX4m4XhQH4DUKHK4gdrn8keEOpJVxTpgZSqfVgo0x11NQEAl2biPmAF_PVJq8W35s0dVVkhEtuVYhmaek42mBrq9fatM6z6YScHOns2WL1w6yWg3b4OIWHnU7OyNjwsKQmEet0r23X8XXe7hbUvsljrytnNEHcs9rGYY_Vsm7Rer5Y1cZC5J3otonszmrNonejX3Jz2_lClfNFnXfjGH4na9AG1-4QbKw-jigZsSZKqewYjX3CItvppVXitkbMHYNgYxPLAw5YP9Dbat6DZ7sW3Sq0faI303vBqQyc6Dh-gHb8OGS0j3YOP41nn9uvUxEzPXvbh2vIWDZv8PZOv3d4Ok7M6VP0uDl94EOLmmeop8rn6Inr7IEbRf8CXXVAhDWI8A0QYQci3IIIaxDhGyDCDkTYgQjDCtiCCF-DCOclBhB96EAIOwi9RN8m49OjY9L07CApvLWK-KnMIuUL4QcBDeOMUzbkVAgWScm9lFMe8qGAc0SagTVhKvKlEJkQNGZRpkbD4BXql6tS7SIMvmng8YCKKPZGIedUwtkYdAi49KBf5GgPee7FJmlT0F73VSkSl7m4TLQwEi2MxApjDw3aOWtbzuXeu0Mnr6RxSK2jmQC87pn3-h_n7aNH1_-MN6hfbWr1Fj1ML6p8u3nXoPAXitSzYw |
| 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=Multi-agent+deep+reinforcement+learning+algorithm+with+self-adaption+division+strategy+for+VNF-SC+deployment+in+SDN%2FNFV-Enabled+Networks&rft.jtitle=Applied+soft+computing&rft.au=Xuan%2C+Hejun&rft.au=Zhou%2C+Yi&rft.au=Zhao%2C+Xuelin&rft.au=Liu%2C+Zhenghui&rft.date=2023-05-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.eissn=1872-9681&rft.volume=138&rft_id=info:doi/10.1016%2Fj.asoc.2023.110189&rft.externalDocID=S1568494623002077 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |