Submit to Sensors Review for Sensors Propose a Special Issue

Journal Browser

► Journal Browser

Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (30 April 2022) | Viewed by 18621

Share This Special Issue

Special Issue Editors

Dr. Xiao Liu

E-Mail Website
Guest Editor

School of Information Technology, Deakin University, Melbourne, Australia
Interests: software engineering; distributed computing and service computing, with special interests in workflow systems; cloud and edge computing; big data analytics; human-centric software engineering

Dr. Jiong Jin

E-Mail Website
Guest Editor

School of Software and Electrical Engineering, Swinburne University of Technology, Melbourne, Australia
Interests: network design and optimization; edge computing and distributed systems; robotics and automation; cyber-physical systems and Internet of Things as well as their applications in smart manufacturing, smart transportation and smart cities

Prof. Dr. Fang Dong

E-Mail Website
Guest Editor

Department of Computer Engineering, School of Computer Science and Engineering, Southeast University, Nanjing, China
Interests: cloud computing; edge computing; high performance computing

Special Issue Information

Dear Colleagues,

With the rapid growth of the Internet of Things (IoT) and 5G networks and beyond, the computing paradigm for intelligent IoT systems is shifting from conventional centralized cloud computing to distributed edge computing. Edge computing (i.e., fog computing) can effectively address the critical challenge of high latency faced by cloud computing by provisioning computing resources close to the IoT devices where massive data are being generated. More importantly, edge computing inherits the benefits of cloud services and emphasizes on the collaboration among cloud servers, edge servers, and end devices to achieve an optimized performance. However, there are still many open issues for edge-computing-based intelligent IoT systems.

The aim of this Special Issue is to promote the investigation of fundamental issues in edge-computing-based intelligent IoT systems from three perspectives, including architectures, algorithms, and applications. Specifically, potential topics include but are not limited to the following:

System architectures for edge-computing-based intelligent IoT systems;
Service and micro-service management at the cloud and edge;
Development tools including simulation toolkits for edge-computing-based intelligent IoT systems;
Collaborative resource management frameworks and task scheduling algorithms toward the cloud–edge-end continuum;
Innovative learning models at the edge for intelligent IoT applications;
Collaborative learning frameworks toward the cloud–edge-end continuum;
Security and privacy of edge-computing-based learning models;
Edge-computing-based workflow applications and workflow management for both scientific computing and business management;
Innovative applications in edge-computing-based intelligent IoT systems, such as in the area of autonomous driving, smart logistics, smart agriculture, and industry 4.0.

Dr. Xiao Liu
Dr. Jiong Jin
Prof. Dr. Fang Dong
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

Edge computing
Fog computing
Intelligent Internet of Things
Edge intelligence
Intelligent edge
Cloud–edge collaboration
Edge services
Edge workflows
Deep learning
Smart systems

Published Papers (6 papers)

Download All Papers

Editorial

Jump to: Research

2 pages, 155 KiB

Open AccessEditorial

Edge-Computing-Based Intelligent IoT: Architectures, Algorithms and Applications

by Xiao Liu, Jiong Jin and Fang Dong

Sensors 2022, 22(12), 4464; https://0-doi-org.brum.beds.ac.uk/10.3390/s22124464 - 13 Jun 2022

Cited by 1 | Viewed by 1052

Abstract

With the rapid growth of the Internet of Things (IoT), 5G networks and beyond, the computing paradigm for intelligent IoT systems is shifting from conventional centralized-cloud computing to distributed edge computing [...] Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

Research

Jump to: Editorial

23 pages, 1129 KiB

Open AccessArticle

Deep Reinforcement Learning Multi-Agent System for Resource Allocation in Industrial Internet of Things

by Julia Rosenberger, Michael Urlaub, Felix Rauterberg, Tina Lutz, Andreas Selig, Michael Bühren and Dieter Schramm

Sensors 2022, 22(11), 4099; https://0-doi-org.brum.beds.ac.uk/10.3390/s22114099 - 28 May 2022

Cited by 12 | Viewed by 3223

Abstract

The high number of devices with limited computational resources as well as limited communication resources are two characteristics of the Industrial Internet of Things (IIoT). With Industry 4.0 emerges a strong demand for data processing in the edge, constrained primarily by the limited available resources. In industry, deep reinforcement learning (DRL) is increasingly used in robotics, job shop scheduling and supply chain. In this work, DRL is applied for intelligent resource allocation for industrial edge devices. An optimal usage of available resources of the IIoT devices should be achieved. Due to the structure of IIoT systems as well as security aspects, multi-agent systems (MASs) are preferred for decentralized decision-making. In our study, we build a network from physical and virtualized representative IIoT devices. The proposed approach is capable of dealing with several dynamic changes of the target system. Three aspects are considered when evaluating the performance of the MASs: overhead due to the MASs, improvement of the resource usage of the devices as well as latency and error rate. In summary, the agents’ resource usage with respect to traffic, computing resources and time is very low. It was confirmed that the agents not only achieve the desired results in training but also that the learned behavior is transferable to a real system. Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

► Show Figures

Figure 1

18 pages, 2306 KiB

Open AccessArticle

Deep Learning-Based Dynamic Computation Task Offloading for Mobile Edge Computing Networks

by Shicheng Yang, Gongwei Lee and Liang Huang

Sensors 2022, 22(11), 4088; https://0-doi-org.brum.beds.ac.uk/10.3390/s22114088 - 27 May 2022

Cited by 16 | Viewed by 3311

Abstract

This paper investigates the computation offloading problem in mobile edge computing (MEC) networks with dynamic weighted tasks. We aim to minimize the system utility of the MEC network by jointly optimizing the offloading decision and bandwidth allocation problems. The optimization of joint offloading decisions and bandwidth allocation is formulated as a mixed-integer programming (MIP) problem. In general, the problem can be efficiently generated by deep learning-based algorithms for offloading decisions and then solved by using traditional optimization methods. However, these methods are weakly adaptive to new environments and require a large number of training samples to retrain the deep learning model once the environment changes. To overcome this weakness, in this paper, we propose a deep supervised learning-based computational offloading (DSLO) algorithm for dynamic computational tasks in MEC networks. We further introduce batch normalization to speed up the model convergence process and improve the robustness of the model. Numerical results show that DSLO only requires a few training samples and can quickly adapt to new MEC scenarios. Specifically, it can achieve

99 %

normalized system utility by using only four training samples per MEC scenario. Therefore, DSLO enables the fast deployment of computation offloading algorithms in future MEC networks. Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

► Show Figures

Figure 1

22 pages, 4220 KiB

Open AccessArticle

Unified InterPlanetary Smart Parking Network for Maximum End-User Flexibility

by Ciprian Iacobescu, Gabriel Oltean, Camelia Florea and Bogdan Burtea

Sensors 2022, 22(1), 221; https://0-doi-org.brum.beds.ac.uk/10.3390/s22010221 - 29 Dec 2021

Cited by 1 | Viewed by 1510

Abstract

Technological breakthroughs have offered innovative solutions for smart parking systems, independent of the use of computer vision, smart sensors, gap sensing, and other variations. We now have a high degree of confidence in spot classification or object detection at the parking level. The only thing missing is end-user satisfaction, as users are forced to use multiple interfaces to find a parking spot in a geographical area. We propose a trustless federated model that will add a layer of abstraction between the technology and the human interface to facilitate user adoption and responsible data acquisition by leveraging a federated identity protocol based on Zero Knowledge Cryptography. No central authority is needed for the model to work; thus, it is trustless. Chained trust relationships generate a graph of trustworthiness, which is necessary to bridge the gap from one smart parking program to an intelligent system that enables smart cities. With the help of Zero Knowledge Cryptography, end users can attain a high degree of mobility and anonymity while using a diverse array of service providers. From an investor’s standpoint, the usage of IPFS (InterPlanetary File System) lowers operational costs, increases service resilience, and decentralizes the network of smart parking solutions. A peer-to-peer content addressing system ensures that the data are moved close to the users without deploying expensive cloud-based infrastructure. The result is a macro system with independent actors that feed each other data and expose information in a common protocol. Different client implementations can offer the same experience, even though the parking providers use different technologies. We call this InterPlanetary Smart Parking Architecture NOW—IPSPAN. Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

► Show Figures

Figure 1

20 pages, 495 KiB

Open AccessArticle

Trajectory Design for UAV-Based Data Collection Using Clustering Model in Smart Farming

by Tariq Qayyum, Zouheir Trabelsi, Asad Malik and Kadhim Hayawi

Sensors 2022, 22(1), 37; https://0-doi-org.brum.beds.ac.uk/10.3390/s22010037 - 22 Dec 2021

Cited by 16 | Viewed by 2879

Abstract

Unmanned aerial vehicles (UAVs) play an important role in facilitating data collection in remote areas due to their remote mobility. The collected data require processing close to the end-user to support delay-sensitive applications. In this paper, we proposed a data collection scheme and scheduling framework for smart farms. We categorized the proposed model into two phases: data collection and data scheduling. In the data collection phase, the IoT sensors are deployed randomly to form a cluster based on their RSSI. The UAV calculates an optimum trajectory in order to gather data from all clusters. The UAV offloads the data to the nearest base station. In the second phase, the BS finds the optimally available fog node based on efficiency, response rate, and availability to send workload for processing. The proposed framework is implemented in OMNeT++ and compared with existing work in terms of energy and network delay. Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

► Show Figures

Figure 1

23 pages, 6429 KiB

Open AccessArticle

Monitoring Illegal Tree Cutting through Ultra-Low-Power Smart IoT Devices

by Alessandro Andreadis, Giovanni Giambene and Riccardo Zambon

Sensors 2021, 21(22), 7593; https://0-doi-org.brum.beds.ac.uk/10.3390/s21227593 - 16 Nov 2021

Cited by 12 | Viewed by 5099

Abstract

Forests play a fundamental role in preserving the environment and fighting global warming. Unfortunately, they are continuously reduced by human interventions such as deforestation, fires, etc. This paper proposes and evaluates a framework for automatically detecting illegal tree-cutting activity in forests through audio event classification. We envisage ultra-low-power tiny devices, embedding edge-computing microcontrollers and long-range wireless communication to cover vast areas in the forest. To reduce the energy footprint and resource consumption for effective and pervasive detection of illegal tree cutting, an efficient and accurate audio classification solution based on convolutional neural networks is proposed, designed specifically for resource-constrained wireless edge devices. With respect to previous works, the proposed system allows for recognizing a wider range of threats related to deforestation through a distributed and pervasive edge-computing technique. Different pre-processing techniques have been evaluated, focusing on a trade-off between classification accuracy with respect to computational resources, memory, and energy footprint. Furthermore, experimental long-range communication tests have been conducted in real environments. Data obtained from the experimental results show that the proposed solution can detect and notify tree-cutting events for efficient and cost-effective forest monitoring through smart IoT, with an accuracy of 85%. Full article

(This article belongs to the Special Issue Edge Computing-Based Intelligent IoT (ECIIoT): Architectures, Algorithms and Applications)

► Show Figures