RNN based EPON dynamic bandwidth allocation algorithm for complex network

Jinxia Yu; Yanyan Fu; Fan Xiao; Huijuan Jia; Panke Qin; Zongqu Zhao; Junru You; Feiyang Liu; Shangya Han; Jiawei Wang

doi:10.1515/joc-2021-0250

Article

RNN based EPON dynamic bandwidth allocation algorithm for complex network

Jinxia Yu , Yanyan Fu , Fan Xiao , Huijuan Jia , Panke Qin , Zongqu Zhao , Junru You , Feiyang Liu , Shangya Han and Jiawei Wang

Published/Copyright: March 2, 2022

Published by

Become an author with De Gruyter Brill

Submit Manuscript Author Information

From the journal Journal of Optical Communications Volume 45 Issue 3

Abstract

In the development of ethernet passive optical networks (EPONs), quality of service (QoS) support and fairness per optical network unit (ONU) are crucial issues. However, making an elaborate analysis of the existing prediction-based bandwidth allocation algorithm, light load penalty, low prediction precision are pointed out. We present an improved dynamic bandwidth pre-allocation algorithm (R-DBA), which employs recurrent neural network (RNN) to predict the high-priority service traffic in EPON. And we introduce mixed integer linear programming (MILP) for optimally building DBA algorithm. This algorithm achieves the prediction of the high-priority service traffic by RNN during the waiting time and supports bandwidth pre-allocation, thus ensuring the fairness of the bandwidth allocation.

Keywords: dynamic bandwidth allocation; recurrent neural network; the complex network

Corresponding author: Yanyan Fu, College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, 454000, China, E-mail: oceans399@163.com

Author contribution: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
Research funding: This work is partiality supported by the projects of Henan Provincial Department of Science and Technology (No. 16210017), support plan of scientific and technological innovation team in university of Henan province (20IRTSTHN013), This study is also supported by Shaanxi key laboratory of information communication network and security (ICNS202006).
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.

References

1. Banerjee, A, Park, Y, Clarke, F, Song, H, Yang, SH, Kramer, G, et al.. Wavelength-division-multiplexed passive optical network (WDM-PON) technologies for broadband access: a review [Invited]. J Opt Networking 2005;4:737–58. https://doi.org/10.1364/JON.4.000737.Search in Google Scholar

2. Kazovsky, LG, Shaw, W, Gutierrez, D, Cheng, N, Wong, S. Next-Generation Optical Access Network. J Lightwave Tech 2007;25:3428–42. https://doi.org/10.1109/JLT.2007.907748.Search in Google Scholar

3. Kramer, G, Pesavento, G. Ethernet passive optical network (EPON): building a next-generation optical access network. IEEE Commun Mag 2002;40:66–73. https://doi.org/10.1109/35.983910.Search in Google Scholar

4. Binh, NK, Kang, B, Choi, S. Delay analysis of fixed multi-thread algorithm for DBA in long reach PON. 2018 Tenth International Conference on Ubiquitous and Future Networks (ICUFN) 2018;580–2. https://doi.org/10.1109/ICUFN.2018.8437005.Search in Google Scholar

5. Jing, Q, Shen, Sm. Research of an improved dynamic uplink bandwidth allocation algorithm for optical networks. Study Opt Commun 2020;5:7–11. https://doi.org/10.13756/j.gtxyj.2020.05.002.Search in Google Scholar

6. Nikoukar, A, Hwang, IS, Liem, AT, Wang, CJ. QoS-aware energy-efficient mechanism for sleeping mode ONUs in enhanced EPON. Photon Network Commun 2015;30:59–70. https://doi.org/10.1007/s11107-015-0499-x.Search in Google Scholar

7. Memon, KA, Mohammadani, KH, Laghari, AA, Yadav, R, Das, B, Tareen, WUK, et al.. Dynamic bandwidth allocation algorithm with demand forecasting mechanism for bandwidth allocations in 10-gigabit-capable passive optical network. Optik 2019;183:1032–42. https://doi.org/10.1016/j.ijleo.2019.03.003.Search in Google Scholar

8. Thangappan, T, Manimaran, E, Arasu, A, Arulprakash, R, Harish Ganapathi, JS. Review of dynamic bandwidth allocation in GPON. In: 2020 International Conference on Communication and Signal Processing (ICCSP); 2020. p. 884–8. https://doi.org/10.1109/ICCSP48568.2020.9182151.Search in Google Scholar

9. Qin, P, Wang, J, Wu, J, Han, S. Global bandwidth scheduling algorithm for complex IP over OTN network. Phys Stat Mech Appl 2020;540. https://doi.org/10.1016/j.physa.2019.123104.Search in Google Scholar

10. Yu, J, Han, S, Ye, Q, Qin, P, Tang, Y, Wang, X, et al.. Enhanced redirection strategy for peer to peer services in high-speed and large-capacity ethernet passive optical networks. J Opt Commun 2024;44:s887–97. https://doi.org/10.1515/joc-2020-0027.Search in Google Scholar

11. Kramer, G, Mukherjee, B, Pesavento, G. IPACT: a dynamic protocol for an Ethernet PON (EPON). IEEE Commun Mag 2002;40:74–80. https://doi.org/10.1109/35.983911.Search in Google Scholar

12. Assi, CM, Ye, Y, Dixiti, S, Ali, MA. Dynamic bandwidth allocation for quality-of-service over ethernet PONs. IEEE J Sel Area Commun 2003;21:1467–77. https://doi.org/10.1109/JSAC.2003.818837.Search in Google Scholar

13. Ghani, N, Shami, A, Assi, C, Raja, MYA. Intra-ONU bandwidth scheduling in ethernet passive optical networks. IEEE Commun Lett 2004;8:683–5. https://doi.org/10.1109/LCOMM.2004.837664.Search in Google Scholar

14. Zheng, J. Efficient bandwidth allocation algorithm for ethernet passive optical networks. IEEE Common 2006;153:464–8. https://doi.org/10.1049/ip-com:20050358.10.1049/ip-com:20050358Search in Google Scholar

15. Dixit, A, Lannoo, B, Das, G, Colle, D, Pickavet, M, Demeester, P. Dynamic bandwidth allocation with SLA awareness for QoS in ethernet passive optical networks. J Opt Commun Netw 2013;5:240–53. https://doi.org/10.1364/JOCN.5.000240.Search in Google Scholar

16. Hatem, JA, Dhaini, AR, Elbassuoni, S. Deep learning-based dynamic bandwidth allocation for future optical access networks. IEEE Access 2019;7:97307–18. https://doi.org/10.1109/ACCESS.2019.2929480.Search in Google Scholar

17. Ruan, LH, Dias, MPI, Wong, E. Machine Learning-Based Bandwidth Prediction for Low-Latency H2M Applications. IEEE Internet Things J 2019;6:3743–52. https://doi.org/10.1109/JIOT.2018.2890563.Search in Google Scholar

18. Bai, X, Shami, A, Assi, C. On the fairness of dynamic bandwidth allocation schemes in Ethernet passive optical networks. Comput Commun 2006;29:2123–35. https://doi.org/10.1016/j.comcom.2006.01.005.Search in Google Scholar

19. Singhal, A, Gupta, A, Singh, H, Singhal, T, Bakshi, S. A novel dynamic bandwidth allocation algorithm in optical access systems. Opt Quant Electron 2021;53. https://doi.org/10.1007/s11082-021-03358-0.Search in Google Scholar

20. Ruan, L, Wong, E. Machine intelligence in allocating bandwidth to achieve low-latency performance. 2018 International Conference on Optical Network Design and Modeling (ONDM) 2018;226–9. https://doi.org/10.23919/ONDM.2018.8396135.Search in Google Scholar

21. Hwang, IS, Shyu, ZD, Ke, LY, Chang, CC. A novel early DBA mechanism with prediction-based fair excessive bandwidth allocation scheme in EPON. Comp Commun 2008;31:1814–23. https://doi.org/10.1016/j.comcom.2007.11.021.Search in Google Scholar

22. Jiang, X, Zhu, N, Dong, L. Improved neural network algorithm in EPON dynamic bandwidth allocation. ComEngApp 2012;48:112–5.Search in Google Scholar

23. Dong, C. A study of fair dynamic bandwidth allocation based on burst traffic prediction in EPON. Zhenjiang: Jiangsu university; 2010.Search in Google Scholar

Received: 2021-10-21

Accepted: 2022-01-28

Published Online: 2022-03-02

Published in Print: 2024-07-26

You are currently not able to access this content.

Articles in the same Issue

https://doi.org/10.1515/joc-2021-0250

Keywords for this article

dynamic bandwidth allocation; recurrent neural network; the complex network