50 Gbit/s-EPON中基于预测的多波长带宽分配算法

朱祥; 李国勇; 许鸥

doi:10.13756/j.gtxyj.2021.05.003

您当前的位置：

首页 >

文章列表页 >

50 Gbit/s-EPON中基于预测的多波长带宽分配算法

光通信系统与网络技术 | 更新时间：2022-06-20

- 50 Gbit/s-EPON中基于预测的多波长带宽分配算法
- Multi-Wavelength Bandwidth Allocation Algorithm based on Prediction in 50 Gbit/s-EPON
- 光通信研究 2021年第5期页码：24-30
- 作者机构：
  
  1.太原理工大学电气与动力工程学院，太原　030024
  2.广东工业大学信息工程学院，广州　510006
- 作者简介：
  
  朱祥（1996-），男，山西太原人。硕士，主要研究方向为智能控制。
  许鸥，副教授。E-mail：xuou@gdut.edu.cn
- 基金信息：
  
  国家重点研发计划资助项目(2019YFB1803803)
- DOI：10.13756/j.gtxyj.2021.05.003
  中图分类号： TP393
- 纸质出版日期：2021-10-10，
  
  收稿日期：2020-12-31，
扫描看全文
朱祥, 李国勇, 许鸥. 50 Gbit/s-EPON中基于预测的多波长带宽分配算法[J]. 光通信研究, 2021,(5):24-30.

ZHU Xiang, LI Guo-yong, XU Ou. Multi-Wavelength Bandwidth Allocation Algorithm based on Prediction in 50 Gbit/s-EPON[J]. Study on Optical Communications, 2021,(5):24-30.
朱祥, 李国勇, 许鸥. 50 Gbit/s-EPON中基于预测的多波长带宽分配算法[J]. 光通信研究, 2021,(5):24-30. DOI： 10.13756/j.gtxyj.2021.05.003.

ZHU Xiang, LI Guo-yong, XU Ou. Multi-Wavelength Bandwidth Allocation Algorithm based on Prediction in 50 Gbit/s-EPON[J]. Study on Optical Communications, 2021,(5):24-30. DOI： 10.13756/j.gtxyj.2021.05.003.

摘要

根据IEEE 802.3ca新标准中对50 Gbit/s-以太网无源光网络（EPON）上行链路的说明，网络上行链路中需要对多波长进行动态带宽分配。文章采用长短时记忆神经网络对网络流量进行预测，旨在提高带宽分配的效率；同时，考虑到网络中不同类型业务对网络时延和带宽要求的差别，分别对不同优先级的业务采取不同的分配方案。仿真实验表明，基于神经网络预测的方法可以有效降低网络的延迟；对不同业务采取不同分配方案时，高优先级业务的延迟降低，并且随着网络负载的提高，延迟变化幅度较小。文章所提算法满足了高优先级业务的需求，虽然低优先级业务延迟与之前方式相比有所增大，但考虑到低优先级业务对延迟要求并不高，因此对于网络整体服务质量影响不大。

Abstract

According to the description of 50 Gbit/s-Ethernet Passive Optical Network (EPON) in IEEE 802.3ca new standard

multi-wavelength dynamic bandwidth allocation is needed in network uplink. In this paper

long short-term memory neural network is used to predict the network traffic in order to improve the efficiency of bandwidth allocation. At the same time

considering the different requirements of network delay and bandwidth for different types of services in the network

different allocation schemes are adopted for different priority services. The simulation results show that the neural network prediction method can effectively reduce the delay of the network. When different allocation schemes are adopted for different services

the latency of high-priority services decreases

and the latency varies with the increase of network load. The algorithm proposed in this paper meets the requirements of high-priority service. Although the latency of low-priority service is increased compared with the previous method

it has little impact on the overall service quality of the network considering that low-priority service does not have high latency requirements.

关键词

50 Gbit/s以太网无源光网络长短时记忆神经网络动态带宽分配网络服务质量

Keywords

50 Gbit/s-EPONlong short-term memory neural networkdynamic bandwidth allocationquality of service

references

IEEE Std 802.3ca-2020, IEEE Standard for Ethernet Amendment 9: Physical Layer Specifications and Management Parameters for 25 Gbit/s and 50 Gbit/s Passive Optical Networks[S].

吴旭佳.下一代以太无源光接入网的带宽资源管理研究[D].上海: 上海交通大学, 2019.

Kramer G, Mukherjee B, Pesavento G. IPACT a Dynamic Protocol for an Ethernet PON (EPON) [J]. IEEE Communications Magazine, 2002, 40(2): 74-80.

Hussain S B, Hu W, Xin H, et al. Low-Latency Dynamic Wavelength and Bandwidth Allocation Algorithm for NG-EPON[J]. Journal of Optical Communications and Networking, 2017, 9(12): 1108-1115.

Wang W, Guo W, Hu W. On the Efficiency and Fairness of Dynamic Wavelength and Bandwidth Allocation Algorithms for Scheduling Multi-type ONUs in NGEPON[J]. Optical Fiber Technology, 2018, 45: 208-216.

董传成.基于突发业务预测且公平的EPON动态带宽分配策略研究[D].镇江: 江苏大学, 2010.

杜爽, 徐展琦, 马涛, 等.基于神经网络模型的网络流量预测综述[J].无线电通信技术, 2020, 46(2): 216-222.

Wen Y, Zhu G. Prediction for Non-Gaussian Self-Similar Traffic with Neural Network[C]//World Congress on Intelligent Control & Automation.Dalian, China: IEEE, 2006: 1713171.

Chen Q, Zhu X, Ling Z, et al. Enhanced LSTM for Natural Language Inference[C]//the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver, Canada: ACL, 2017: P17-1152.

Leland W E, Taqqu M S, Willinger W, et al. On the Self-Similar Nature of Ethernet Traffic[J]. ACM SIG-COMM Computer Communication Review, 1993, 23(4): 183-193.

更多指标>

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

避免轻载惩罚支持多业务的EPON动态带宽分配

一种保证QoS的EPON上行动态带宽分配算法