PTAS: PIFO-Based Time-Aware Shaper for Massive Concurrent Flows in Time-Sensitive Networks

IF 6.7 2区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

IEEE Transactions on Network Science and Engineering Pub Date : 2024-10-24 DOI:10.1109/TNSE.2024.3486038

Jie Ren;Dong Yang;Weiting Zhang;Kai Gong;Weiliang Chen;Wen Wu;Hongke Zhang

{"title":"PTAS: PIFO-Based Time-Aware Shaper for Massive Concurrent Flows in Time-Sensitive Networks","authors":"Jie Ren;Dong Yang;Weiting Zhang;Kai Gong;Weiliang Chen;Wen Wu;Hongke Zhang","doi":"10.1109/TNSE.2024.3486038","DOIUrl":null,"url":null,"abstract":"Time-sensitive networking (TSN) specifies a time-aware shaper (TAS) to enhance the real-time support of Ethernet for time-triggered traffic. In TAS, flow/frame isolation is necessary for obtaining a deterministic queuing order, which is the key to achieving determinism. However, this isolation is difficult to fulfill when accessing a large number of concurrent flows generated by industrial devices without TSN capabilities due to the uncontrollable sending times and a limited number of egress queues in TAS. In this paper, a novel TAS framework is designed for massive concurrent flows, named push-in-first-out (PIFO) based time-aware shaper (PTAS). Specifically, the PTAS takes advantage of a PIFO queue to buffer and sort all time-triggered frames based on expected sending time (EST), while an ephemeral memory EST allocation algorithm is proposed to obtain ESTs that can ensure a deterministic queuing order. Through frame sorting rather than conventional isolation, the PTAS efficiently provides a deterministic transmission guarantee for massive concurrent flows. Furthermore, the deterministic flow scheduling constraints for the PTAS are derived, based on which the PTAS is proven to have better schedulability than conventional TAS. In addition to simulation, the PTAS is also implemented on a TSN testbed for evaluation. Extensive experimental results demonstrate that the PTAS can reduce up to 37.0% maximum end-to-end latency, 98.8% jitter, and save 40.1% queue resources in high-concurrency scenarios while scheduling up to 15.5% more flows as compared with conventional TAS.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"83-95"},"PeriodicalIF":6.7000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Network Science and Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10734149/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

Time-sensitive networking (TSN) specifies a time-aware shaper (TAS) to enhance the real-time support of Ethernet for time-triggered traffic. In TAS, flow/frame isolation is necessary for obtaining a deterministic queuing order, which is the key to achieving determinism. However, this isolation is difficult to fulfill when accessing a large number of concurrent flows generated by industrial devices without TSN capabilities due to the uncontrollable sending times and a limited number of egress queues in TAS. In this paper, a novel TAS framework is designed for massive concurrent flows, named push-in-first-out (PIFO) based time-aware shaper (PTAS). Specifically, the PTAS takes advantage of a PIFO queue to buffer and sort all time-triggered frames based on expected sending time (EST), while an ephemeral memory EST allocation algorithm is proposed to obtain ESTs that can ensure a deterministic queuing order. Through frame sorting rather than conventional isolation, the PTAS efficiently provides a deterministic transmission guarantee for massive concurrent flows. Furthermore, the deterministic flow scheduling constraints for the PTAS are derived, based on which the PTAS is proven to have better schedulability than conventional TAS. In addition to simulation, the PTAS is also implemented on a TSN testbed for evaluation. Extensive experimental results demonstrate that the PTAS can reduce up to 37.0% maximum end-to-end latency, 98.8% jitter, and save 40.1% queue resources in high-concurrency scenarios while scheduling up to 15.5% more flows as compared with conventional TAS.

查看原文本刊更多论文

PTAS：基于pifo的时间感知整形器，用于时间敏感网络中的海量并发流

时间敏感网络TSN （Time-sensitive networking）指定了一个时间感知整形器（time-aware shaper），以增强以太网对时间触发流量的实时支持。在TAS中，流/帧隔离是获得确定性排队顺序的必要条件，是实现确定性的关键。然而，当访问由没有TSN功能的工业设备产生的大量并发流时，由于TAS中的发送时间不可控和出口队列数量有限，这种隔离很难实现。本文针对大规模并发流设计了一种新的时间感知成形器框架，即基于push-in-first-out （PIFO）的PTAS。具体而言，PTAS利用PIFO队列根据预期发送时间（EST）对所有时间触发帧进行缓冲和排序，同时提出了一种短时内存EST分配算法，以获得能够保证确定性队列顺序的EST。通过帧排序而不是传统的隔离，PTAS有效地为大量并发流提供了确定性传输保证。在此基础上，推导了PTAS的确定性流调度约束，并在此基础上证明了PTAS比传统TAS具有更好的可调度性。除了仿真之外，还在TSN测试台上实现了PTAS进行了评估。大量的实验结果表明，在高并发场景下，PTAS可以减少37.0%的最大端到端延迟，98.8%的抖动，节省40.1%的队列资源，同时比传统TAS多调度15.5%的流。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering

CiteScore

12.60

自引率

9.10%

发文量

393

期刊介绍： The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.