Tytuł artykułu
Autorzy
Identyfikatory
Warianty tytułu
Flow table occupancy reduction based on machine learning elephant flow detection
Konferencja
Konferencja Radiokomunikacji i Teleinformatyki (20-22.09.2023 ; Kraków, Polska)
Języki publikacji
Abstrakty
Liczba jednoczesnych przepływów w sieciach nadal przekracza pojemność tablic przepływów. W celu zmniejszenia zajętości tablic przeanalizowano wybrane modele uczenia maszynowego, wytrenowane na replikowalnych, rzeczywistych modelach ruchu, aby klasyfikować przepływy już od pierwszego pakietu. Jak pokazano w tej pracy, możliwe jest zmniejszenie liczby wpisów w tablicach 30-50 krotnie, przy jednoczesnym zachowaniu 80% pokrycia ruchu.
The number of simultaneous flows in networks still overwhelms the capacities of the flow tables. Selected machine learning models trained on the reproducible, real traffic models to classify flows since the first packet were analyzed in order to reduce the flow table occupancy. As it is shown in this paper it is possible to reduce the number of flow entries by a factor up to 30-50, still covering 80% of the traffic using out-of-the-box models.
Wydawca
Rocznik
Tom
Strony
403--406
Opis fizyczny
Bibliogr. 18 poz., rys.
Twórcy
autor
- AGH Akademia Górniczo-Hutnicza, Kraków
autor
- AGH Akademia Górniczo-Hutnicza, Kraków
Bibliografia
- [1] M. Al-Fares, S. Radhakrishnan, B. Raghavan, N. Huang, A. Vahdat et al., “Hedera: dynamic flow scheduling for data center networks.” in Nsdi, vol. 10, no. 8. San Jose, USA, 2010, pp. 89–92.
- [2] A. R. Curtis, J. C. Mogul, J. Tourrilhes, P. Yalagandula, P. Sharma, and S. Banerjee, “Devoflow: Scaling flow management for high-performance networks,” in Proceedings of the ACM SIGCOMM 2011 Conference, 2011, pp. 254–265.
- [3] M. V. B. da Silva, A. S. Jacobs, R. J. Pfitscher, and L. Z. Granville, “Predicting elephant flows in internet exchange point programmable networks,” in Advanced Information Networking and Applications: Proceedings of the 33rd International Conference on Advanced Information Networking and Applications (AINA-2019) 33. Springer, 2020, pp. 485–497.
- [4] R. Durner and W. Kellerer, “Network function offloading through classification of elephant flows,” IEEE Transactions on Network and Service Management, vol. 17, no. 2, pp. 807–820, 2020.
- [5] J. G. Gomez, V. Hernandez, and G. RamirezGonzalez, “Traffic classification in ip networks through machine learning techniques in final systems,” IEEE Access, 2023.
- [6] M. Hamdan, B. Mohammed, U. Humayun, A. Abdelaziz, S. Khan, M. A. Ali, M. Imran, and M. N. Marsono, “Flow-aware elephant flow detection for software-defined networks,” IEEE Access, vol. 8, pp. 72 585–72 597, 2020.
- [7] C. Hardegen, B. Pfülb, S. Rieger, and A. Gepperth, “Predicting network flow characteristics using deep learning and real-world network traffic,” IEEE Transactions on Network and Service Management, vol. 17, no. 4, pp. 2662–2676, 2020.
- [8] C. Hardegen, B. Pfülb, S. Rieger, A. Gepperth, and S. Reißmann, “Flow-based throughput prediction using deep learning and real-world network traffic,” in 2019 15th International Conference on Network and Service Management (CNSM). IEEE, 2019, pp. 1–9.
- [9] P. Jurkiewicz, “Boundaries of flow table usage reduction algorithms based on elephant flow detection,” in 2021 IFIP Networking Conference (IFIP Networking). IEEE, 2021, pp. 1–9.
- [10] P. Jurkiewicz, G. Rzym, and P. Boryło, “Flow length and size distributions in campus internet traffic,” Computer Communications, vol. 167, pp. 15–30, 2021.
- [11] W.-X. Liu, J. Cai, Y. Wang, Q. C. Chen, and J.- Q. Zeng, “Fine-grained flow classification using deep learning for software defined data center networks,” Journal of Network and Computer Applications, vol. 168, p. 102766, 2020.
- [12] P. Megyesi and S. Molnár, “Analysis of elephant users in broadband network traffic,” in Advances in Communication Networking: 19th EUNICE/IFIP WG 6.6 International Workshop, Chemnitz, Germany, August 28-30, 2013. Proceedings 19. Springer, 2013, pp. 37–45.
- [13] P. Jurkiewicz, “flow-models: A framework for analysis and modeling of IP network flows,” SoftwareX, vol. 17, p. 100929, 2022.
- [14] P. Poupart, Z. Chen, P. Jaini, F. Fung, H. Susanto, Y. Geng, L. Chen, K. Chen, and H. Jin, “Online flow size prediction for improved network routing,” in 2016 IEEE 24th International Conference on Network Protocols (ICNP). IEEE, 2016, pp. 1–6.
- [15] A. Shaikh, J. Rexford, and K. G. Shin, “Load sensitive routing of long-lived ip flows,” ACM SIGCOMM Computer Communication Review, vol. 29, no. 4, pp. 215–226, 1999.
- [16] G. Shen, Q. Li, S. Ai, Y. Jiang, M. Xu, and X. Jia, “How powerful switches should be deployed: A precise estimation based on queuing theory,” in IEEE INFOCOM 2019-IEEE Conference on Computer Communications. IEEE, 2019, pp. 811–819.
- [17] P. Xiao, W. Qu, H. Qi, Y. Xu, and Z. Li, “An efficient elephant flow detection with cost-sensitive in sdn,” in 2015 1st International Conference on Industrial Networks and Intelligent Systems (INISCom). IEEE, 2015, pp. 24–28.
- [18] H. Xu, H. Huang, S. Chen, and G. Zhao, “Scalable software-defined networking through hybrid switching,” in IEEE INFOCOM 2017-IEEE Conference on Computer Communications. IEEE, 2017, pp. 1–9.
Uwagi
Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-87084906-b051-4a4c-833c-a7235bc3e274