当前位置: X-MOL 学术J. Simul. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Bringing AI to the edge: A formal M&S specification to deploy effective IoT architectures
Journal of Simulation ( IF 1.3 ) Pub Date : 2021-01-04
Román Cárdenas, Patricia Arroba, José L. Risco Martín

ABSTRACT

Internet of Things applications are based on ubiquitous networks of multiple distributed devices, with limited computing resources and power, capable of collecting and storing data from heterogeneous sources in real-time. To avoid network saturation and delays, new architectures are needed to provide real-time Big Data and data analytics capabilities at the edge of the network, where energy efficiency needs to be considered to ensure a sustainable and effective deployment in areas of human activity. In this research, we present an IoT model based on the principles of Model-Based Systems Engineering. It covers the description of the entire architecture, from IoT devices to the processing units in edge data centres, and includes the location-awareness of user equipment, network, and computing infrastructures to optimise federated resource management in terms of delay and power consumption. We present a framework to assist the dimensioning and the dynamic operation of IoT data stream analytics applications.

Abbreviations : ADAS Advanced Driver Assistance System. 20, 21, 24AI Artificial Intelligence. 2, 24ANN Artificial Neural Network. 2, 21AP Access Point. 5, 10, 11, 12, 13, 17, 18, 19, 20CNF Core Network Function. 5DEVS Discrete Event System Specification. 3, 5, 6, 7, 9, 10, 11, 12, 15, 16, 17, 18, 20, 21, 24, 27, 28EDC Edge Data Centre. 2, 3, 5, 6, 9, 10, 12, 13, 20, 21, 22, 23, 25FaaS Function-as-a-Service. 3, 4, 5, 6FDD Frequency Division Duplexing. 11, 18, 19FSPL Free-Space Path Loss. 20GPU Graphics Processing Unit. 2, 21IoT Internet of Things. 2, 3, 4, 5, 6, 14, 19, 23, 24ISP Internet Service Provider. 5, 10M&S Modelling and Simulation. 3, 24M&S&O Modelling, Simulation, and Optimisation. 21MBSE Model-Based Systems Engineering. 3, 4, 5, 24MCS Modulation and Codification Scheme. 12MDC Micro Data Centre. 2ML Machine Learning. 2, 20, 24, 25NR 5G New Radio. 12P2P Point-to-Point. 5, 10PBCH Physical Broadcast Channel. 19PDCCH Physical Downlink Control Channel. 19PDSCH Physical Downlink Shared Channel. 19PSS Primary Synchronisation Signal. 11, 14PU Processing Unit. 7, 9, 21, 22, 23, 24, 25PUCCH Physical Uplink Control Channel. 19PUSCH Physical Uplink Shared Channel. 19QoS Quality of Service. 2, 4, 5, 6, 12, 24RAN Radio Access Network. 5, 10, 13, 16, 17, 20SDN Software-Defined Network. 5, 10SNR Signal-to-Noise Ratio. 11, 12, 14, 17UE User Equipment. 4, 5, 6, 10, 11, 12, 13, 14, 16, 17, 18, 19, 21, 22, 23, 24, 25WSN Wireless Sensor Network. 4



中文翻译:

将AI带到边缘:正式的M&S规范以部署有效的IoT架构

摘要

物联网应用程序基于多个分布式设备的普遍存在的网络,具有有限的计算资源和能力,能够实时从异构源收集和存储数据。为了避免网络饱和和延迟,需要新的体系结构以在网络边缘提供实时大数据和数据分析功能,在这些网络边缘需要考虑能源效率,以确保在人类活动领域的可持续有效部署。在这项研究中,我们提出了基于基于模型的系统工程原理的物联网模型。它涵盖了从物联网设备到边缘数据中心中的处理单元的整个体系结构的描述,并包括用户设备,网络,和计算基础架构,以优化延迟和功耗方面的联合资源管理。我们提出了一个框架,以协助物联网数据流分析应用程序的尺寸确定和动态操作。

缩写 :ADAS高级驾驶员辅助系统。20,21,24 AI人工智能。2,24 ANN人工神经网络。2,21 AP接入点。5,10,11,12,13,17,18,19,20 CNF核心网络功能。5 DEVS离散事件系统规范。3,5,6,7,9,10,11,12,15,16,17,18,20,21,24,27,28 EDC边缘数据中心。2,3,5,6,9,10,12,13,20,21,22,23,25个FAAS函数-作为一种服务。3,4,5,6 FDD频分双工。11,18,19 FSPL自由空间路径损耗。20 GPU图形处理单元。2,21的IoT物联网。2,3,4,5,6,14,19,23,24 ISP因特网服务提供商。5,10 M&S建模与仿真。3,24 M&S&O建模,仿真和优化。21 MBSE基于模型的系统工程。3,4,5,24 MCS调制和编纂方案。12 MDC微型数据中心。2 ML机器学习。2,20,24,25 NR 5G创新无线电。12 P2P点对点。5、10 PBCH物理广播信道。19 PDCCH物理下行链路控制信道。19 PDSCH物理下行链路共享信道。19 PSS主同步信号。11,14 PU处理单元。7,9,21,22,23,24,25 PUCCH物理上行链路控制信道。19 PUSCH物理上行链路共享信道。19 QoS服务质量。2,4,5,6,12,24 RAN无线电接入网络。5,10,13,16,17,20 SDN软件定义的网络。5、10 SNR信噪比。11,12,14,17 UE用户设备。4,5,6,10,11,12,13,14,16,17,18,19,21,22,23,24,25 WSN无线传感器网络。4

更新日期:2021-01-04
down
wechat
bug