检索结果-内蒙古大学图书馆

LEM: a Tool for Large-Scale Workflow Control in Edge-Based Industry 5.0 Applications 19

LEM: a Tool for Large-Scale Workflow Control in Edge-Based I...

19th Annual International Conference on Distributed computing in Smart systems and the Internet of Things, DCOSS-IoT 2023

作者： Reis, Rui Santos, Pedro M. Sousa, Mario J. Martins, Nuno Sousa, Joana Almeida, Luis Universidade Do Porto Faculdade de Engenharia Portugal Portugal Cister Research Center in Real-Time and Embedded Computing Systems Portugal

ISBN: (纸本)9798350346497

Edge computing is poised to greatly boost Industry 5.0 by providing a computing substrate that can run highly specialized applications with minimal latency, reducing the requirements on computational resources at the end-user and allowing the sharing of resources between multiple end-users. The intended services and workflows need to be designed, configured and deployed at target edge devices, and during operation their status needs to be monitored. There are several industrial frameworks that provide such functionalities, but often there is little support to execute them simultaneously over many target devices. In this paper we present the LEM tool, a tool that enables the management (monitor, configure, deploy) of workflows in a large number of edge devices. The tool connects to existing industrial frameworks to provide these functionalities, abstracting the low level configuration aspects of each framework and enabling simultaneous configuration of multiple devices, a feature that many frameworks do not support. The tool offers a web-based GUI that allows the infrastructure manager to conveniently check the status of all devices and flows running in each device, deploy new flows on selected devices, and start and stop flows. Experimental measurements show residual response time overhead as the number of devices increases. © 2023 IEEE.

关键词： edge Industry5.0 Node-RED workflow

来源：评论

学校读者我要写书评

暂无评论

Comparing Performance of Machine Learning Tools Across computing Platforms 18

Comparing Performance of Machine Learning Tools Across Compu...

引用

18th Conference on Computer Science and Intelligence systems, FedCSIS 2023

作者： Vicente, Pedro Santos, Pedro M. Asulba, Barikisu Martins, Nuno Sousa, Joana Almeida, Luis Portugal Universidade Do Porto Faculdade de Engenharia Portugal Cister Research Center in Real-Time and Embedded Computing Systems Portugal Nos Inovacao Portugal

ISBN: (纸本)9788396744784

embedded systems (ES) are wide-spread in our world and responsible for many critical systems. More recently, machine learning (ML) tools have become a well-established solution for data-intensive tasks, but their application in embedded systems is still gaining traction and their real-time performance is often unclear. We provide a (non-extensive) review of the ML tools that may be suited for deployment in ES, from which we selected two representative tools - the well-established Python-based Scikit-Learn, and the interoperability-oriented ONNX Runtime - to compare their response time. Using archetypal datasets and four pre-trained ML models, we measure the prediction time for each sample, for each model, in Scikit-Learn and ONNX Runtime in a standard desktop (to compare performance of the tools in the same platform), and for ONNX Runtime in a representative ES, a Raspberry Pi v4 (to compare performance of the same tool across platforms). We report that ONNX considerably improves over Scikit-Learn, and experiences a negligible performance degradation when ported to the RPi. © 2023 Polish Information Processing Society.

关键词： embedded systems

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of the Two-Ray Model for mmWave Overwater Communication 1

Empirical Evaluation of the Two-Ray Model for mmWave Overwat...

引用

1st IEEE Latin American Conference on Antennas and Propagation, LACAP 2024

作者： Celades, Jorge Rodriguez, Mauricio Gaitan, Miguel Gutierrez Pontificia Universidad Católica de Valparaíso Escuela de Ingeniería Eléctrica Chile CISTER - Research Centre in Real-Time & Embedded Computing Systems Porto Portugal Pontificia Universidad Católica de Chile Department of Electrical Engineering Chile

ISBN: (纸本)9798331527587

Understanding and characterizing millimeter wave (mmWave) communication in real-world scenarios is crucial to design reliable communication systems for Internet of Things (IoT) applications, including autonomous vessel's remote operation. To this aim, this research provides an empirical evaluation of large-scale fading for vessel-to-shore communication at 28 GHz. Specifically, we experimentally assess the path loss (PL) performance of short-range Line-of-Sight (LoS) links with low antenna heights. The measurements show trends that match well with the two-ray model PL predictions, yielding a root mean square error (RMSE) of 2.56 dB in the 10-100 m range. © 2024 IEEE.

关键词： large-scale fading mmWave overwater communication path-loss two-ray model

来源：评论

学校读者我要写书评

暂无评论

Comparing Performance of Machine Learning Tools Across computing Platforms

Comparing Performance of Machine Learning Tools Across Compu...

引用

Federated Conference on Computer Science and Information systems (FedCSIS)

作者： Pedro Vicente Pedro M. Santos Barikisu Asulba Nuno Martins Joana Sousa Luis Almeida Instituto Superior de Engenharia do Porto (ISEP) CISTER Research Center in Real-Time & Embedded Computing Systems Portugal Universidade do Porto Faculdade de Engenharia NOS Inovacao Portugal

关键词：

来源：评论

学校读者我要写书评

暂无评论

An ETSI ITS-enabled Robotic Scale Testbed for Network-Aided Safety-Critical Scenarios

An ETSI ITS-enabled Robotic Scale Testbed for Network-Aided ...

引用

International Conference on Dependable systems and Networks Workshops (DSN-W)

作者： José M. Pinheiro Ênio V. Filho Pedro M. Santos L. Almeida Faculdade de Engenharia – Universidade do Porto Instituto Superior de Engenharia do Porto – Instituto Politécnico do Porto CISTER Research Center in Real-Time & Embedded Computing Systems Portugal

Vehicle-to-Everything (V2X) communications allows new and exciting relevant Intelligent Transportation systems (ITS) applications such as cooperative perception. In some vehicular use-cases, infrastructure can have a crucial role in safeguarding safety, e.g. in an intersection in which inflowing vehicles do not have Line-of-Sight (blind corner) and an emergency braking action is required. Performance evaluation of vehicular communications systems (end-to-end delay, packet loss ratio, etc.) often resorts to static wireless testbeds, but there tends to be little consideration about the other subsystems involved in the time-sensitive goal, namely sensors, processing and decision-making, and vehicle actuators. In this paper we present a laboratorial testbed in which ETSI ITS/IEEE 802.11pbased On-Board and Road-Side Units (OBU/RSU) are deployed on a 1110-scale autonomous robotic vehicle and on the road-side respectively, the latter being part of a road-side infrastructure that includes a camera and an edge processing node. We target a use-case of collision avoidance supported by the network, in which the infrastructure detects an impending collision and issues a DEN message to prevent it. We aim to take a step beyond the traditional end-to-end delay characterization that is limited to the communication subsystem, by proposing a tool that enables realistic characterization of the entire end-to-end (detection-to-action) delay in safety-critical use-cases. Results show that the end-to-end latency of the system (camera-edge processing node-RSU-OBU-vehicle actuators) is under 100ms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEM: a Tool for Large-Scale Workflow Control in Edge-Based Industry 5.0 Applications

LEM: a Tool for Large-Scale Workflow Control in Edge-Based I...

引用

International Conference on Distributed computing in Sensor systems (DCOSS)

作者： Rui Reis Pedro M. Santos Mário J. Sousa Nuno Martins Joana Sousa Luis Almeida Faculdade de Engenharia Universidade do Porto Portugal Instituto Superior de Engenharia do Porto (ISEP) Portugal CISTER Research Center in Real-Time & Embedded Computing Systems Portugal NOS Inovação Portugal

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of the Two-Ray Model for mmWave Overwater Communication

Empirical Evaluation of the Two-Ray Model for mmWave Overwat...

引用

Antennas and Propagation (LACAP), IEEE Latin American Conference on

作者： Jorge Celades Mauricio Rodríguez Miguel Gutiérrez Gaitán Escuela de Ingeniería Eléctrica Pontificia Universidad Católica de Valparaíso Chile CISTER - Research Centre in Real-Time & Embedded Computing Systems Porto Portugal Department of Electrical Engineering Pontificia Universidad Católica de Chile Chile

ISBN: (数字)9798331527587

ISBN: (纸本)9798331527594

Understanding and characterizing millimeter wave (mmWave) communication in real-world scenarios is crucial to design reliable communication systems for Internet of Things (IoT) applications, including autonomous vessel’s remote operation. To this aim, this research provides an empirical evaluation of large-scale fading for vessel-to-shore communication at 28 GHz. Specifically, we experimentally assess the path loss (PL) performance of short-range Line-of-Sight (LoS) links with low antenna heights. The measurements show trends that match well with the two-ray model PL predictions, yielding a root mean square error (RMSE) of 2.56 dB in the 10-100 m range.

关键词： Measurement uncertainty Receiving antennas Line-of-sight propagation Interference Predictive models Reliability engineering Market research Internet of Things Millimeter wave communication Root mean square

来源：评论

学校读者我要写书评

暂无评论

EDF Scheduling and Minimal-Overlap Shortest-Path Routing for real-time TSCH Networks 2

EDF Scheduling and Minimal-Overlap Shortest-Path Routing for...

引用

2nd Workshop on Next Generation real-time embedded systems, NG-RES 2021

作者： Gaitán, Miguel Gutiérrez Almeida, Luís Santos, Pedro Miguel Yomsi, Patrick Meumeu CISTER-Research Centre in Real-Time and Embedded Computing Systems Porto Portugal Faculty of Engineering University of Porto Portugal Institute of Engineering Portugal Facultad de Ingenieriá Universidad Andrés Bello Santiago de Chile Chile

ISBN: (纸本)9783959771788

With the scope of Industry 4.0 and the Industrial Internet of Things (IIoT), wireless technologies have gained momentum in the industrial realm. Wireless standards such as WirelessHART, ISA100.11a, IEEE 802.15.4e and 6TiSCH are among the most popular, given their suitability to support real-time data traffic in wireless sensor and actuator networks (WSAN). Theoretical and empirical studies have covered prioritized packet scheduling in extenso, but only little has been done concerning methods that enhance and/or guarantee real-time performance based on routing decisions. In this work, we propose a greedy heuristic to reduce overlap in shortest-path routing for WSANs with packet transmissions scheduled under the earliest-deadline-first (EDF) policy. We evaluated our approach under varying network configurations and observed remarkable dominance in terms of the number of overlaps, transmission conflicts, and schedulability, regardless of the network workload and connectivity. We further observe that well-known graph network parameters, e.g., vertex degree, density, betweenness centrality, etc., have a special influence on the path overlaps, and thus provide useful insights to improve the real-time performance of the network. © Miguel Gutiérrez Gaitán, Luís Almeida, Pedro Miguel Santos, and Patrick Meumeu Yomsi.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey

arXiv

引用

arXiv 2022年

作者： Kurunathan, Harrison Huang, Hailong Li, Kai Ni, Wei Hossain, Ekram CISTER - Research Centre in Real-Time and Embedded Computing Systems Porto Portugal The Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Hong Kong Sydney Australia The University of Manitoba Canada

Over the past decade, Unmanned Aerial Vehicles (UAVs) have provided pervasive, efficient, and cost-effective solutions for data collection and communications. Their excellent mobility, flexibility, and fast deployment enable UAVs to be extensively utilized in agriculture, medical, rescue missions, smart cities, and intelligent transportation systems. Machine learning (ML) has been increasingly demonstrating its capability of improving the automation and operation precision of UAVs and many UAV-assisted applications, such as communications, sensing, and data collection. The ongoing amalgamation of UAV and ML techniques is creating a significant synergy and empowering UAVs with unprecedented intelligence and autonomy. This survey aims to provide a timely and comprehensive overview of ML techniques used in UAV operations and communications and identify the potential growth areas and research gaps. We emphasize the four key components of UAV operations and communications to which ML can significantly contribute, namely, perception and feature extraction, feature interpretation and regeneration, trajectory and mission planning, and aerodynamic control and operation. We classify the latest popular ML tools based on their applications to the four components and conduct gap analyses. This survey also takes a step forward by pointing out significant challenges in the upcoming realm of ML-aided automated UAV operations and communications. It is revealed that different ML techniques dominate the applications to the four key modules of UAV operations and communications. While there is an increasing trend of cross-module designs, little effort has been devoted to an end-to-end ML framework, from perception and feature extraction to aerodynamic control and operation. It is also unveiled that the reliability and trust of ML in UAV operations and applications require significant attention before full automation of UAVs and potential cooperation between UAVs and humans come to fruit

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Differentially Private Energy Sharing Among Smart Grid-Powered Base Stations

Differentially Private Energy Sharing Among Smart Grid-Power...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Liwan Qi Bochun Wu Fei Wang Kai Li Wei Ni Abbas Jamalipour State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China College of Physics and Electromechanical Engineering Hexi University Zhangye China University of Cambridge Cambridge U.K. Real-Time and Embedded Computing Systems Research Centre (CISTER) Porto Portugal Commonwealth Scientific and Industrial Research Organisation (CSIRO) Sydney NSW Australia School of Electrical and Information Engineering University of Sydney NSW Australia

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Allowing for energy sharing among base stations (BSs), we investigate a distributed BS system equipped with renewable power units and energy storage batteries. While offering significant benefits, this raises concerns about privacy protection. By leveraging the Laplace mechanism, our differential privacy (DP)-based method safeguards energy consumption data related to processing data tasks from different BSs. To address a long-term average cost minimization problem, we propose a distributed online algorithm for efficient energy sharing. We demonstrate that the boundary constraints of energy storage batteries can still be satisfied by choosing parameters appropriately. We provide a theoretical bound for the optimality gap and validate the effectiveness of our theoretical results. Numerical results indicate our algorithm can potentially reduce the average costs of BSs by up to 34%.

关键词： Renewable energy sources Privacy Energy consumption Base stations Vehicular and wireless technologies Costs Batteries Smart grids Protection Optimization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：