Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Services Computing and Software-Defined Systems for Future Internet
share announcement

Services Computing and Software-Defined Systems for Future Internet

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Networks".

Deadline for manuscript submissions: closed (20 December 2021) | Viewed by 4533

Special Issue Editors

Dr. Pradeeban Kathiravelu

E-Mail Website
Guest Editor
Department of Biomedical Informatics, Emory University, Atlanta, GA 30322, USA
Interests: network softwarization; software-defined systems; cloud-assisted networks; distributed systems; service-oriented architecture
Dr. Cristina Cervelló-Pastor

E-Mail Website
Guest Editor
Network Engineering Department, Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, Spain
Interests: optimization; placement; SDN/NFV; edge computing; resource orchestration; IA/ML; DL; DRL; automation
Special Issues, Collections and Topics in MDPI journals
Prof. Luís Veiga

E-Mail Website
Guest Editor
INESC-ID Lisboa / Instituto Superior Técnico, Universidade de Lisboa, 1000-029 Lisboa, Portugal
Interests: distributed systems; virtual machines; cloud and grid computing; peer-to-peer; middleware

Special Issue Information

Dear Colleagues,

The vision of a Future Internet has steered many research works. Fifth-generation (5G) networks built across the globe are considered a driving force for the Future Internet. Network softwarization strategies such as software-defined networking (SDN) and network functions virtualization (NFV) are set to bring more unified control and flexibility to classic network architectures. Software-defined systems have been built to enlarge the scope of the network softwarization efforts up to the Internet scale. Services computing enables the decoupling of complex workflows. The Internet of the future is a computer, where users will say what to do, and the network will do it. The computation is brought closer to the end-users’ computers in-network at the edge. We envision the future Internet to be more accessible and high-performing across the world, with new governance models and collective intelligence. Combined and made more flexible, resorting to containerization, services computing can scale to the Internet, composing dynamic workflows with minimal data transfer and low latency.

We invite researchers to contribute to this Special Issue with their original research works or survey papers that focus on the challenges and solutions towards realizing the Future Internet.

Topics of interest include but are not limited to the following:

  • Software-defined systems for wide area networks
  • Mobile edge computing (MEC) for 5G and Future Internet
  • Services computing for Future Internet applications
  • Towards accessible Internet
  • Cloud-assisted networks and Internet-scale overlay networks
  • Internet measurements for self-adaptive Internet-scale networks
  • Policy, management, and economic aspects of the Future Internet
  • Service workflow compositions in 5G networks
  • Network function virtualization (NFV) in the Future Internet and 5G
  • Software-defined cyber-physical systems
  • Latency-sensitive Internet service workflows
  • Internet-scale network operating systems
  • Energy efficiency in the Future Internet
  • Peer-to-peer networks and decentralized architectures on the Internet
  • QoS control and management in the Future Internet
  • Future Internet support for massive Internet of Things (IoT) deployments.

Dr. Pradeeban Kathiravelu
Prof. Cristina Cervelló-Pastor
Prof. Luís Veiga
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. Electronics 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 2400 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

  • service-oriented architecture (SOA)
  • software-defined systems (SDS)
  • Future Internet (FI)
  • workflow composition
  • mobile edge computing (MEC)
  • software-defined wide area networks (SD-WANs)
  • cloud-assisted networks (CANs)
  • network function virtualization (NFV)
  • 5G networks
  • NFV architectures
  • Placement
  • Optimization
  • Internet of Things (IoT) and cyber-physical systems (CPS)

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

18 pages, 5040 KiB  
Article
An Approach to Combine the Power of Deep Reinforcement Learning with a Graph Neural Network for Routing Optimization
by Bo Chen, Di Zhu, Yuwei Wang and Peng Zhang
Electronics 2022, 11(3), 368; https://doi.org/10.3390/electronics11030368 - 26 Jan 2022
Cited by 12 | Viewed by 3704
Abstract
Routing optimization has long been a problem in the networking field. With the rapid development of user applications, network traffic is continuously increasing in dynamicity, making optimization of the routing problem NP-hard. Traditional routing algorithms cannot ensure both accuracy and efficiency. Deep reinforcement [...] Read more.
Routing optimization has long been a problem in the networking field. With the rapid development of user applications, network traffic is continuously increasing in dynamicity, making optimization of the routing problem NP-hard. Traditional routing algorithms cannot ensure both accuracy and efficiency. Deep reinforcement learning (DRL) has recently shown great potential in solving networking problems. However, existing DRL-based routing solutions cannot process the graph-like information in the network topology and do not generalize well when the topology changes. In this paper, we propose AutoGNN, which combines a GNN and DRL for the automatic generation of routing policies. In AutoGNN, the traffic distribution in the network topology is processed by a GNN, while a DRL framework is used to train the parameters of neural networks without human expertise. Our experimental results show that AutoGNN can improve the average end-to-end delay of the network by up to 19.7% as well as present more robustness against topology changes. Full article
(This article belongs to the Special Issue Services Computing and Software-Defined Systems for Future Internet)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop