Embedded real-time systems in cyber-physical applications: a frequency domain analysis methodology

IF 2.4 4区计算机科学 Q2 COMPUTER SCIENCE, THEORY & METHODS

International Journal of General Systems Pub Date : 2020-01-06 DOI:10.1080/03081079.2019.1703701

C. Aciti, R. Cayssials, E. Ferro, J. Urriza, J. Orozco

{"title":"Embedded real-time systems in cyber-physical applications: a frequency domain analysis methodology","authors":"C. Aciti, R. Cayssials, E. Ferro, J. Urriza, J. Orozco","doi":"10.1080/03081079.2019.1703701","DOIUrl":null,"url":null,"abstract":"ABSTRACT Cyber-Physical Systems (CPSs) use sensors and actuators to interface between an embedded system and the physical world. The time-continuous domain of the physical world should be periodically sampled by real-time tasks in an embedded system to preserve its dynamic properties in the time-discrete domain. Because the task execution pattern may vary during runtime, a jitter in the execution of a real-time task hinders the periodicity of its execution. The effects of jitters in CPSs are difficult to determine when the premises of the Nyquist-Shannon sampling theorem are not satisfied. This paper proposes using frequency domain analysis to determine the perturbations that a real-time system produces on real-world applications; accordingly, the paper defines both a design and an evaluation criterion for real-time systems in CPS applications. The Fixed Priority discipline is analysed through simulations to conclude that no special design techniques are required when the utilization factors are less than 20%.","PeriodicalId":50322,"journal":{"name":"International Journal of General Systems","volume":"49 1","pages":"201 - 221"},"PeriodicalIF":2.4000,"publicationDate":"2020-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/03081079.2019.1703701","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of General Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1080/03081079.2019.1703701","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}

引用次数: 2

Abstract

ABSTRACT Cyber-Physical Systems (CPSs) use sensors and actuators to interface between an embedded system and the physical world. The time-continuous domain of the physical world should be periodically sampled by real-time tasks in an embedded system to preserve its dynamic properties in the time-discrete domain. Because the task execution pattern may vary during runtime, a jitter in the execution of a real-time task hinders the periodicity of its execution. The effects of jitters in CPSs are difficult to determine when the premises of the Nyquist-Shannon sampling theorem are not satisfied. This paper proposes using frequency domain analysis to determine the perturbations that a real-time system produces on real-world applications; accordingly, the paper defines both a design and an evaluation criterion for real-time systems in CPS applications. The Fixed Priority discipline is analysed through simulations to conclude that no special design techniques are required when the utilization factors are less than 20%.

查看原文本刊更多论文

网络物理应用中的嵌入式实时系统:一种频域分析方法

摘要网络物理系统（CPSs）使用传感器和执行器来连接嵌入式系统和物理世界。嵌入式系统中的实时任务应该定期对物理世界的时间连续域进行采样，以保持其在时间离散域中的动态特性。由于任务执行模式在运行时可能会发生变化，因此实时任务执行中的抖动会阻碍其执行的周期性。当不满足奈奎斯特-香农采样定理的前提时，很难确定CPSs中抖动的影响。本文提出使用频域分析来确定实时系统在实际应用中产生的扰动；因此，本文定义了CPS应用中实时系统的设计和评估标准。通过模拟对固定优先级学科进行分析，得出结论：当利用率低于20%时，不需要特殊的设计技术。

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

International Journal of General Systems 工程技术-计算机：理论方法

CiteScore

4.10

自引率

20.00%

发文量

审稿时长

6 months

期刊介绍： International Journal of General Systems is a periodical devoted primarily to the publication of original research contributions to system science, basic as well as applied. However, relevant survey articles, invited book reviews, bibliographies, and letters to the editor are also published. The principal aim of the journal is to promote original systems ideas (concepts, principles, methods, theoretical or experimental results, etc.) that are broadly applicable to various kinds of systems. The term “general system” in the name of the journal is intended to indicate this aim–the orientation to systems ideas that have a general applicability. Typical subject areas covered by the journal include: uncertainty and randomness; fuzziness and imprecision; information; complexity; inductive and deductive reasoning about systems; learning; systems analysis and design; and theoretical as well as experimental knowledge regarding various categories of systems. Submitted research must be well presented and must clearly state the contribution and novelty. Manuscripts dealing with particular kinds of systems which lack general applicability across a broad range of systems should be sent to journals specializing in the respective topics.