Edge Computing Optimization Using Artificial Intelligence Methods

A special issue of IoT (ISSN 2624-831X).

Deadline for manuscript submissions: closed (30 June 2021) | Viewed by 9343

Special Issue Editors


E-Mail Website
Guest Editor
1. Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049-001 Lisboa, Portugal
2. INESC-ID, Rua Alves Redol 9, 1000-029 Lisboa, Portugal
3. INOV, Rua Alves Redol 9, 1000-029 Lisboa, Portugal
Interests: Computer Networks; Wireless Communications; Internet of Things; Artificial Intelligence

E-Mail Website
Guest Editor
1. Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049-001 Lisboa, Portugal
2. INESC-ID, Rua Alves Redol 9, 1000-029 Lisboa, Portugal
Interests: Computer Networks; Delay Tolerant Networks; Vehicular Networks; Internet of Vehicles

E-Mail Website
Guest Editor
Department of Informatics, University of Sussex, Brighton BN1 9QJ, UK
Interests: computer networks; network security; artificial intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The growing importance of the Internet of Things (IoT) and the ubiquitous high capacity provided by 5G technologies have brought the specter of massive quantities of data being generated and/or consumed by sensors, actuators, and smart devices. Such massive amounts of data require considerable processing power, which is available in the cloud. However, cloud-based computation and data delivery models do not allow the stringent quality of service (QoS) guarantees to be efficiently harnessed. The latter is due to the number of hops of wired networks between the data endpoints and the cloud, which leads to a significant increase in latency, which may dramatically affect real-time control and other critical systems. Moreover, forwarding all the data generated by such devices directly to the cloud may devour the network bandwidth, leading to congestion. Therefore, it is necessary that critical processing to be hosted closer to the endpoint devices, i.e., closer to the sources and sinks of the data so that data can be processed and filtered out by the time it reaches the cloud. This can be achieved through Edge Computing (EC).

Efficient, scalable, and QoS-aware placement of IoT data processing jobs in EC resources is a complex optimization problem and, currently, an active research topic. As new jobs are created, they have to be assigned computational resources dynamically, matching job requirements with the cost, reliability, location (and mobility), besides the current availability of the resources. Less critical or demanding communication jobs may be offloaded to the cloud. The use of Artificial Intelligence (AI) methods to jointly tackle the problem of job placement optimization, including jobs belonging to AI-based data analytics software, constitute currently active research topics addressed by this Special Issue.

For this Special Issue, original scientific articles are welcome on the following as well as closely related topics:

  • AI-based algorithms to optimize job placement in EC
  • AI software architectures favoring distributed computing job placement in EC resources (e.g., Distributed Deep Neural Network architectures)
  • AI-based mechanisms supporting open EC markets leveraging the participation of third-party computing resources opportunistically (e.g., parked autonomous vehicles)
  • AI-based methods to optimize mobile EC resources’ placement (e.g., EC capable drones)

Prof. Dr. António M.R.C. Grilo
Prof. Dr. Paulo Rogerio Pereira
Prof. Dr. Naércio Magaia
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. IoT is an international peer-reviewed open access quarterly 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 1200 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
  • Job Placement Optimization
  • Artificial Intelligence
  • Distributed Data Flow
  • Mobile and Opportunistic Edge Computing Resources

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

18 pages, 9433 KiB  
Article
Predictive Maintenance of Bus Fleet by Intelligent Smart Electronic Board Implementing Artificial Intelligence
by Alessandro Massaro, Sergio Selicato and Angelo Galiano
IoT 2020, 1(2), 180-197; https://doi.org/10.3390/iot1020012 - 1 Oct 2020
Cited by 19 | Viewed by 6959
Abstract
This paper is focused on the design and development of a smart and compact electronic control unit (ECU) for the monitoring of a bus fleet. The ECU system is able to extract all vehicle data by the on-board diagnostics-(ODB)-II and SAE J1939 standards. [...] Read more.
This paper is focused on the design and development of a smart and compact electronic control unit (ECU) for the monitoring of a bus fleet. The ECU system is able to extract all vehicle data by the on-board diagnostics-(ODB)-II and SAE J1939 standards. The integrated system Internet of Things (IoT) system, is interconnected in the cloud by an artificial intelligence engine implementing multilayer perceptron artificial neural network (MLP-ANN) and is able to predict maintenance of each vehicle by classifying the driver behavior. The key performance indicator (KPI) of the driver behavior has been estimated by data mining k-means algorithm. The MLP-ANN model has been tested by means of a dataset found in literature by allowing the correct choice of the calculus parameters. A low means square error (MSE) of the order of 10−3 is checked thus proving the correct use of MLP-ANN. Based on the analysis of the results, are defined methodologies of key performance indicators (KPIs), correlating driver behavior with the engine stress defining the bus maintenance plan criteria. All the results are joined into a cloud platform showing fleet efficiency dashboards. The proposed topic has been developed within the framework of an industry research project collaborating with a company managing bus fleet. Full article
(This article belongs to the Special Issue Edge Computing Optimization Using Artificial Intelligence Methods)
Show Figures

Graphical abstract

Back to TopTop