基于迭代轮询的光交换机时延确保调度算法（特邀）

黄瀚庭; 闫付龙; 郭胜洁; 张杰

doi:10.13756/j.gtxyj.2024.05.240018

您当前的位置：

首页 >

文章列表页 >

基于迭代轮询的光交换机时延确保调度算法（特邀）

专题：数据中心内光交换 | 更新时间：2024-10-08

- 基于迭代轮询的光交换机时延确保调度算法（特邀）
- Optical Switch Delay Guaranteed Scheduling Algorithm based on Iterative Round Robin
- 光通信研究 2024年第5期页码：24001801-24001805
- 作者机构：
  
  北京邮电大学　信息光子学与光通信国家重点实验室，北京　100876
- 作者简介：
  
  黄瀚庭，硕士。E-mail：2019211765@bupt.edu.cn
- 基金信息：
  
  国家重点研发计划资助项目(2021YBF2800805);国家自然科学基金青年资助项目(62301062);浙江省重点研发计划资助项目(2023C01148)
- DOI：10.13756/j.gtxyj.2024.05.240018
  中图分类号： TN929
- 纸质出版日期：2024-10-10，
  
  收稿日期：2024-01-26，
  
  修回日期：2024-03-11，
- 稿件说明：
移动端阅览
黄瀚庭，闫付龙，郭胜洁，等. 基于迭代轮询的光交换机时延确保调度算法[J]. 光通信研究，2024(5)：240018.

Huang H T, Yan F L，Guo S J，et al, Optical Switch Delay Guaranteed Scheduling Algorithm based on Iterative Round Robin[J]. Study on Optical Communications, 2024(5)：240018.
黄瀚庭，闫付龙，郭胜洁，等. 基于迭代轮询的光交换机时延确保调度算法[J]. 光通信研究，2024(5)：240018. DOI： 10.13756/j.gtxyj.2024.05.240018.

Huang H T, Yan F L，Guo S J，et al, Optical Switch Delay Guaranteed Scheduling Algorithm based on Iterative Round Robin[J]. Study on Optical Communications, 2024(5)：240018. DOI： 10.13756/j.gtxyj.2024.05.240018.

摘要

【目的】

数据中心庞大的数据传输及交换业务量对交换设备有着很高的性能要求，不仅需要具备良好的扩展性，还需提供大带宽和低切换时延。快速光交换机具有切换速率极快和接入带宽远大于电交换机的优越性能，面对现今愈发庞大的数据交换需求，为实现更高的接入速率和更好的处理性能，交换机结构将向全光方向发展。其中，针对快速光交换机的调度算法研究多以提供100%吞吐率为目标，在提供服务质量（QoS）保证方面的研究相对较少。

【方法】

对此，文章基于矩阵分解和业务整形的思想，采用迭代与轮询相结合的方法，提出了一种时延确保的光交换机迭代调度算法。文章提出的迭代轮询（IRR）调度算法首先将业务速率矩阵映射为业务矩阵，然后基于业务矩阵的服务要求计算得到服务要求矩阵序列，最后从服务要求矩阵序列中提取调度矩阵序列。

【结果】

理论分析证明，IRR调度算法能够提供基于端口的时延确保，并且给出了在给定业务条件下时延上界的计算方法。

【结论】

IRR调度算法可应用于光交换机的时延性能优化与时延确保光交换系统的设计中，为下一代全光网络具备确定性QoS提供关键支撑。

Abstract

【Objective】

In the context of extensive data transmission and exchange operations in data centers

there is a high-performance demand for switching equipment. Switching equipment not only needs to exhibit excellent scalability but also must provide large bandwidth and low switching delay. Fast optical switches possess superior performance with extremely faster switching rates and access bandwidth than electrical switches. Faced with the ever-growing demand for data exchange in the present day

the structure of switches is evolving towards all-optical directions to achieve greater access rates and processing performance. In the study of fast optical switches

the scheduling algorithms focus on achieving a 100% throughput

with relatively less emphasis on ensuring Quality of Service (QoS).

【Methods】

This paper proposes an iterative scheduling algorithm for optical switches that ensures latency

based on the principles of matrix decomposition and traffic shaping. We combine iteration and round robin mechanisms

and propose the Iterative Round Robin (IRR) scheduling algorithm. Initially

the IRR algorithm maps the traffic rate matrix to a traffic matrix

and then calculates the service requirement matrix sequence based on the service requirements of the traffic matrix. Finally the scheduling matrix sequence is extracted from the service requirement matrix sequence.

【Results】

Theoretical analysis validates that the IRR scheduling algorithm can provide port-based guaranteed latency and provides a method for calculating latency upper bounds under the given traffic conditions.

【Conclusion】

The IRR scheduling algorithm can be applied in optimizing the latency performance of optical switches and in designing optical switch systems with guaranteed latency.This contributes crucial support to the provision of deterministic QoS for the next generation all-optical networks.

关键词

迭代轮询光交换机调度算法时延确保

Keywords

IRRoptical switchscheduling algorithmdelay guarantee

references

熊庆旭, 冯金鑫. 基于矩阵分解的光交换机分组调度算法[J]. 通信学报, 2006, 27(4): 80-86.

Xiong Q X, Feng J X. Packet Scheduling based on Matrix Decomposition in Optical Switches[J]. Journal on Communications, 2006, 27(4): 80-86.

熊庆旭. 输入排队结构交换机分组调度研究[J]. 通信学报, 2005, 26(6): 118-129.

Xiong Q X. Research on Packet Scheduling in Input-queued Switches[J]. Journal on Communications, 2005, 26(6): 118-129.

陈伯文, 王曜辉, 陈琪, 等. 混合线速率的虚拟光网络映射成本优化方法[J]. 光通信研究, 2022(6): 1-8.

Chen B W, Wang Y H, Chen Qi, et al. Optimized Network Cost Approaches of Virtual Optical Network Mapping based on Mixed Line Rate[J]. Study on Optical Communications, 2022(6): 1-8.

Kim D U, Han K E, Song J, et al. Photonic Frame based Packet Switching Optical Network[C]//2018 European Conference on Optical Communication (ECOC). Rome, Italy: IEEE, 2018: 8535297.

Song J, Han K E, Kim D U, et al. Scheduling Algorithm for All-optical Switch under Non-uniform Traffic Condition[C]//Optical Fiber Communication Conference. San Diego, California, Washington, D. C.: OSA, 2018: w2a.27.

Miao W, Luo J, Di Lucente S, et al. Novel Flat Datacenter Network Architecture based on Scalable and Flow-controlled Optical Switch System[J]. Optics Express, 2014, 22(3): 2465-2472.

Kumar G, Dukkipati N, Jang K, et al. Swift: Delay is Simple and Effective for Congestion Control in the Datacenter[C]//Annual Conference of the ACM Special Interest Group on Data Communication on the Applications, Technologies, Architectures, and Protocols for Computer Communication. Virtual Event, USA: ACM, 2020: 514-528.

Wang L K, Ye T, Lee T T, et al. A Parallel Complex Coloring Algorithm for Scheduling of Input-Queued Switches[J]. IEEE Transactions on Parallel and Distributed Systems, 2018, 29(7): 1456-1468.

Yan F, Xie C, Calabretta N. Traffic Rate Matrix Decomposition Based Conflict Free Scheduling for a Fast Optical Switching Network[C]//Optical Fiber Communication Conference (OFC) 2021. Washington, D.C., USA: Optica Publishing Group, 2021: W1E.4.

Deng L, Wong W S, Chen P N, et al. Delay-constrained Input-Queued Switch[J]. IEEE Journal on Selected Areas in Communications, 2018, 36(11): 2464-2474.

Li Y L, Miao R, Liu H Q. HPCC: High Precision Congestion Control[C]//ACM Special Interest Group on Data Communication 2019. Beijing, China: ACM, 2019: 44-58.

马尚琪. 数据中心光互连网络流量调度算法的研究[D]. 西安: 西安电子科技大学, 2020.

Ma S Q. Research on Traffic Scheduling Algorithm of Optical Interconnection Network in Data Center[D]. Xi’an, China: Xidian University, 2020.

Chang C S, Chen W J, Huang H Y. On Service Guarantees for Input-buffered Crossbar Switches: a Capacity Decomposition Approach by Birkhoff and von Neumann[C]//1999 Seventh International Workshop on Quality of Service. London, UK: IEEE, 1999: 766481.

Zhang J H, Ye T, Lee T T, et al. Birkhoff-von-Neumann Switches with Deflection-compensated Mechanism[DB/OL]. (2013-08-20) [2024-01-26]. http://arxiv.org/abs/1308.4280http://arxiv.org/abs/1308.4280.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种光交换核心节点调度算法研究

切换时延不为零的光交换调度算法

时隙光突发交换网络调度问题研究

带VOQ和交叉点缓冲的交叉矩阵