Page 23 - ITU Journal Future and evolving technologies Volume 2 (2021), Issue 4 – AI and machine learning solutions in 5G and future networks

ITU Journal on Future and Evolving Technologies, Volume 2 (2021), Issue 4

REFERENCES [11] Fabien Geyer and Georg Carle. “Learning and Gen‑
erating Distributed Routing Protocols using Graph‑
[1] Franco Scarselli, Marco Gori, Ah Chung Tsoi, Based Deep Learning”. In: Proceedings of the Work‑
Markus Hagenbuchner, and Gabriele Monfardini. shop on Big Data Analytics and Machine Learning
“The Graph Neural Network Model”. In: IEEE Trans‑ for Data Communication Networks. 2018, pp. 40–
actions on Neural Networks 20.1 (2008), pp. 61–80.
45.
[2] Krzysztof Rusek and Piotr Chołda. “Message‑ [12] Miquel Ferriol‑Galmés, José Suárez‑Varela,
passing Neural Networks Learn Little’s Law”. In: Pere Barlet‑Ros, and Albert Cabellos‑Aparicio.
IEEE Communications Letters 23.2 (2018), pp. 274–
“Applying Graph‑Based Deep Learning to Re‑
277.
alistic Network Scenarios”. In: arXiv preprint
[3] Krzysztof Rusek, José Suárez‑Varela, Albert arXiv:2010.06686 (2020).
Mestres, Pere Barlet‑Ros, and Albert Cabellos‑
[13] Barcelona Neural Networking Center. GNN Chal‑
Aparicio. “Unveiling the Potential of Graph Neural
Networks for Network Modeling and Optimization lenge Website. https : / / bnn . upc . edu /
challenge2020/. Accessed: 2021‑01‑22.
in SDN”. In: Proceedings of the ACM Symposium on
SDN Research. 2019, pp. 140–151. [14] Xiaojun Hei, Jun Zhang, Brahim Bensaou, and Chi‑
Chung Cheung. “Wavelength Converter Placement
[4] Krzysztof Rusek, José Suárez‑Varela, Paul Almasan, in Least‑Load‑Routing‑Based Optical Networks Us‑
Pere Barlet‑Ros, and Albert Cabellos‑Aparicio. ing Genetic Algorithms”. In: Journal of Optical Net‑
“RouteNet: Leveraging Graph Neural Networks for working 3.5 (2004), pp. 363–378.
Network Modeling and Optimization in SDN”. In:
IEEE Journal on Selected Areas in Communications [15] Fernando Barreto, Emı́lio CG Wille, and Luiz Naca‑
38.10 (2020), pp. 2260–2270. mura Jr. “Fast Emergency Paths Schema to Over‑
come Transient Link Failures in OSPF Routing”. In:
[5] András Varga and Rudolf Hornig. “An Overview of arXiv preprint arXiv:1204.2465 (2012).
the OMNeT++ Simulation Environment”. In: Pro‑
ceedings of the 1st International Conference on Sim‑ [16] João Pedro, João Santos, and João Pires. “Perfor‑
ulation Tools and Techniques for Communications, mance Evaluation of Integrated OTN/DWDM Net‑
Networks and Systems & Workshops. 2008, p. 60. works with Single‑Stage Multiplexing of Optical
Channel Data Units”. In: 13th International Confer‑
[6] Robert B Cooper. “Queueing Theory”. In: Proceed‑ ence on Transparent Optical Networks. IEEE. 2011,
ings of the ACM’81 Conference. 1981, pp. 119–122.
pp. 1–4.
[7] Jean‑Yves Le Boudec and Patrick Thiran. Network
[17] J. Kurose and K. Ross. Computer Networking: A Top‑
Calculus: A Theory of Deterministic Queuing Systems
Down Approach, 7th Edition. Pearson Education
for the Internet. Vol. 2050. Springer Science & Busi‑
Limited, 2017. ISBN: 978‑0‑13‑359414‑0.
ness Media, 2001.
[18] Knowledge‑De ined Networking. RouteNet Chal‑
[8] Raouf Boutaba, Mohammad A Salahuddin, Noura lenge Github Repository. https : / / github .
Limam, Sara Ayoubi, Nashid Shahriar, Felipe com/knowledgedefinednetworking/RouteNet-
Estrada‑Solano, and Oscar M Caicedo. “A Com‑ challenge. Accessed: 2021‑02‑03.
prehensive Survey on Machine Learning for
Networking: Evolution, Applications and Research [19] Jorge Sola and Joaquin Sevilla. “Importance of In‑
Opportunities”. In: Journal of Internet Services and put Data Normalization for the Application of Neu‑
Applications 9.1 (2018), pp. 1–99. ral Networks to Complex Industrial Problems”. In:
IEEE Transactions on Nuclear Science 44.3 (1997),
[9] Albert Mestres, Eduard Alarcón, Yusheng Ji, and Al‑ pp. 1464–1468.
bert Cabellos‑Aparicio. “Understanding the Model‑
ing of Computer Network Delays Using Neural Net‑ [20] Yann A LeCun, Léon Bottou, Genevieve B Orr, and
works”. In: Proceedings of the Workshop on Big Data Klaus‑Robert Müller. “Ef icient Backprop”. In: Neu‑
Analytics and Machine Learning for Data Communi‑ ral Networks: Tricks of the Trade. Springer, 2012,
cation Networks. 2018, pp. 46–52. pp. 9–48.
[10] Justin Gilmer, Samuel S Schoenholz, Patrick F Ri‑ [21] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian
ley, Oriol Vinyals, and George E Dahl. “Neural Mes‑ Sun. “Deep Residual Learning for Image Recogni‑
sage Passing for Quantum Chemistry”. In: Inter‑ tion”. In: Proceedings of the IEEE conference on com‑
national Conference on Machine Learning. PMLR. puter vision and pattern recognition. 2016, pp. 770–
2017, pp. 1263–1272. 778.
[22] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and
Jian Sun. “Identity Mappings in Deep Residual Net‑
works”. In: Europeanconferenceon computervision.
Springer. 2016, pp. 630–645.

© International Telecommunication Union, 2021 7