Study of a Smarter AQM Algorithm to Reduce Network Delay
DOI:
https://doi.org/10.5281/zenodo.8071387Anahtar Kelimeler:
Neural Network- Testing- Training- DQNÖz
The focus of our study was to study the behavior of the smart RED algorithm with parameter adaptation based on a neural network structure. Previously Kim et. al. [2] and Basheer et. al. [1], introduced the use of deep reinforcement learning for active queue management (AQM). This work studies the performance deep reinforcement learning, using a simple topology. Transmitters and receivers communicate and all information is routed over a single bottleneck link. This work studies the effect of changing the bottleneck link bandwidth and bottleneck latency on this algorithm. It is observed that increasing training data size will increase the performance of the algorithm. This paper shows a detailed flowchart of the training process and the specific hardware configuration and also demonstrates results.
Referanslar
M. Kim, M. Jaseemuddin, and A. Anpalagan, “Deep Reinforcement Learning Based Active Queue Management for IoT Networks,” J. Netw. Syst. Manag., vol. 29, no. 3, 2021, doi: 10.1007/s10922-021-09603-x.
H. Ma, D. Xu, Y. Dai, and Q. Dong, “An intelligent scheme for congestion control: When active queue management meets deep reinforcement learning,” Comput. Networks, vol. 200, no. October, p. 108515, Dec. 2021, doi: 10.1016/j.comnet.2021.108515.
J. Szyguła, A. Domański, J. Domańska, D. Marek, K. Filus, and S. Mendla, “Supervised Learning of Neural Networks for Active Queue Management in the Internet,” Sensors, vol. 21, no. 15, p. 4979, Jul. 2021, doi: 10.3390/s21154979.
G. Abbas, Z. Halim, and Z. H. Abbas, “Fairness-Driven Queue Management: A Survey and Taxonomy,” IEEE Commun. Surv. Tutorials, vol. 18, no. 1, pp. 324–367, 2016, doi: 10.1109/COMST.2015.2463121.
Baker, F., Fairhurst, G.: IETF Recommendations Regarding Active Queue Management. In: Internet Engineering Task Force (IETF), RFC 7567, 2015.
M. M. Hamdi, S. A. Rashid, M. Ismail, M. A. Altahrawi, M. F. Mansor, and M. K. Abufoul, “Performance Evaluation of Active Queue Management Algorithms in Large Network,” ISTT 2018 - 2018 IEEE 4th Int. Symp. Telecommun. Technol., pp. 3–8, 2018, doi: 10.1109/ISTT.2018.8701716.
R. Adams, “Active Queue Management: A Survey,” IEEE Commun. Surv. Tutorials, vol. 15, no. 3, pp. 1425–1476, 2013, doi: 10.1109/SURV.2012.082212.00018.
C. Li, “Deep Reinforcement Learning,” in Reinforcement Learning for Cyber-Physical Systems, November, Boca Raton, Florida : CRC Press, [2019]: Chapman and Hall/CRC, 2019, pp. 125–154.
N. C. Luong et al., “Applications of Deep Reinforcement Learning in Communications and Networking: A Survey,” IEEE Commun. Surv. Tutorials, vol. 21, no. 4, pp. 3133–3174, 2019, doi: 10.1109/COMST.2019.2916583.
M. Fajri and K. Ramli, “Design of network traffic congestion controller with PI AQM based on ITAE index,” Int. J. Electron. Telecommun., vol. 66, no. 4, pp. 715–721, 2020, doi: 10.24425-ijet.2020.134032/754.
D. A. Alwahab and S. Laki, “A simulation-based survey of active queue management algorithms,” ACM Int. Conf. Proceeding Ser., no. February, pp. 71–77, 2018, doi: 10.1145/3193092.3193106.
L. Campanile, M. Gribaudo, M. Iacono, F. Marulli, and M. Mastroianni, “Computer network simulation with ns- 3: A systematic literature review,” Electron., vol. 9, no. 2, pp. 1–25, 2020, doi: 10.3390/electronics9020272.
Yayınlanmış
Sayı
Bölüm
Lisans
Telif Hakkı (c) 2022 AINTELIA Science Notes Journal
Bu çalışma Creative Commons Attribution-NonCommercial 4.0 International License ile lisanslanmıştır.
Makale gönderen yazarlar, Aintelia Science Notes Journal'da (ASNJ) yayınlanmak üzere kabul edildikten sonra çalışmalarının telif haklarını saklı tutarlar. Göndererek yazarlar şunları kabul ederler:
- Telif Hakkının Saklı Tutulması: Yayınlanan makalenin telif hakkı yazar(lar)da kalır. BAUDER Press'e, çalışmayı yayınlama, çoğaltma, dağıtma ve arşivleme konusunda münhasır olmayan bir lisans verilir.
- Lisanslama: Makale, CC BY-NC 4.0 lisansı altında yayınlanır ve üçüncü tarafların, yazar(lar)a ve dergiye uygun şekilde atıfta bulunulması koşuluyla, çalışmayı ticari olmayan amaçlarla paylaşmasına ve uyarlamasına izin verir.
- Yazar Hakları: Yazarlar, derginin orijinal yayın yeri olarak belirtilmesi koşuluyla, makalelerini herhangi bir ortamda (depolar, tezler, konferanslar, öğretim materyalleri) kısıtlama olmaksızın depolama, dağıtma ve yeniden kullanma özgürlüğüne sahiptir.