Deep Reinforcement Learning for Future Wireless Network Virtualization

in Special Issue   Posted on January 25, 2021 

Information for the Special Issue

Submission Deadline: Tue 15 Jun 2021
Journal Impact Factor : 1.061
Journal Name : Wireless Personal Communications
Journal Publisher:
Website for the Special Issue: https://www.springer.com/journal/11277/updates/18791004
Journal & Submission Website: https://www.springer.com/journal/11277

Special Issue Call for Papers:

Providing wireless network virtualization is a promising idea that has the potential to alleviate spectrum congestion and open up new network services. The paradigms differ with the degree of virtualization and sharing of resources. Each paradigm involves technological and non-technical challenges that must be resolved before a widespread technology becomes wireless virtualization. These problems require careful design and assessment for the virtualization of wireless networks to be a success. The design of future wireless networks needs to satisfy numerous criteria for Quality of Service (QoS). From wired to wireless networks, virtualization has been expanded. It enhances efficiency and utilisation and allows multi-tenancy and customised service with broader range of carrier frequencies. Due to the dynamic and unpredictable network status and heterogeneity of wireless users in IoT environment, network control problems are very challenging as the dimensionality and computational complexity rapidly increase. Also in the wireless domains such as WiFi, cellular network and wireless Internet of Things (IoT), new architectures involving virtualization have been evolving. In infrastructure-based wireless networks, relatively little virtualization has occurred, but the concept of virtualizing wireless access is gaining attention as it has the potential to enhance the use of spectrum and perhaps create new services. Virtualization of the wireless network requires both sharing of resources and spectrum sharing. Therefore, rational planning and resource allocation to provide entire network architecture, the QoS promised by each SP, mobility management and the spatial-temporal variations of traffic, cross INP signaling and location tracking contributes to vital research areas in Wireless Network Virtualization.

Deep Reinforcement Learning (DRL) has been developed by the use of Deep Neural Networks (DNNs) as a potential approach to solve high-dimensional and continuous control issues effectively. Deep Reinforcement Learning techniques provide great potential in IoT, edge and SDN scenarios and are used in heterogeneous networks for IoT-based energy management based on the QoS required by each Software Defined Network (SDN) service. Current research focuses on the implementation and validation of the Software-Defined Networks and Network Function Virtualization in Global Edge Computing Architecture, developing intelligent mechanisms that allow automated and dynamic management of the virtual communications established in the SDNs by user nodes. While DRL has shown great potential to solve emerging problems in complex wireless network virtualization, there are still domain-specific challenges that require further study, including the design of adequate DNN architectures with 5G network optimization issues, resource discovery and allocation, developing intelligent mechanisms that allow the automated and dynamic management of the virtual communications established in the SDNs which is considered as research perspective.

The objective of this specific issue is to explore recent developments in DRL and address practical challenges in Wireless Network Virtualization that promote researchers to present their research on the innovative DRL system, network modelling and architecture, technical challenges in terms of instantiation, operation and management of wireless network virtualization.

Original research and review articles in this area are encouraged in the following topic areas including, but are not limited to:

  • Wireless Virtualization and dynamic spectrum management using DRL
  • Experimentation and simulations of DRL in Network communications 
  • Channel allocation algorithms considering QoS for Mobile Network Virtualization
  • Addressing Physical Layer issues Wireless communication in using DRL 
  • Improved Service Provisioning in Wireless Virtualization Enabled Networks 
  • Spectrum Sharing in Virtualized Networks
  • DRL for Performance analysis in Dynamic spectrum resource allocation in Wireless Network Virtualization
  • Software-Defined Networks and Edge Computing over IoT : Challenges and Issues
  • Wireless Virtualization  and evaluation of virtual architectures
  • Application of DRL for power rate control, traffic shaping and Scheduling 
  • DRL for identifying network security threats and vulnerabilities in SDN
  • Virtualization via Software Defined Radio (SDR)
  • DRL in mobile edge computing, wireless caching, and mobile data offloading
  • DRL in Fault detection, auto-diagnosing and Network forensic applications 
  • Performance Analysis on efficient network access and channel utilization using DRL

Manuscript Submission Deadline: 15 June 2021Authors Notification Date: 20 August 2021Revised Papers Due Date: 25 November 2021Final notification Date: 05 February 2022

Lead Guest EditorDr. Tu NguyenAssistant Professor,Department of Computer Science, Purdue University Fort Wayne, Fort Wayne, USAnguyent@pfw.eduGuest EditorsDr. Nam P. NguyenAssistant Professor,Department of Computer Science,Purdue University Fort Wayne, USAnpnguyen@towson.eduDr. Claudio SavaglioDepartment of Computer Science, Modeling, Electronics and Systems Engineering (DIMES),University of Calabria, Italycsavaglio@dimes.unical.itAuthors should follow the WPC Journal manuscript format described at the journal site. Manuscripts should be submitted online through https://www.editorialmanager.com/wire/default.aspx.

Other Special Issues on this journal

Closed Special Issues