Recently, networks throughout the world have been undergoing profound restructuring and transformation with the development of software-defined networking (SDN), network function virtualization (NFV), and 5th-generation wireless systems (5G). The new networking paradigms are eroding the dominance of traditional ossified architectures and reducing dependence on proprietary hardware. However, the corresponding improvements in network flexibility and scalability are also presenting unprecedented challenges for network management.
Artificial intelligence and machine learning (AI & ML) techniques for network management, operations, and automation improve the way we address networking today. Compared to meticulously manually designed strategies, AI & ML techniques offer enormous advantages in networking systems. For example, AI & ML provides a generalized model and uniform learning method without pre-specified processes for various network scenarios. In addition, such techniques can effectively handle complex problems and high-dimensional situations; indeed, AI & ML methods have already achieved remarkable success in many complex system control domains, including computer games and robotic control.
Besides the enormous advantages of AI & ML for networking, the development of new network techniques is also providing fertile ground for AI & ML deployment. For example, in-band network telemetry (INT) enabled end-to-end network visualization at the millisecond scale, and programmable Ethernet switch presents a versatile way to process packets and supports various formats and protocols. Therefore, the growing trend of applying AI & ML in networking is being driven by both task requirements (the increasing complexity of networks and increasingly demanding QoS/QoE requirements) and technological developments (new network monitoring technologies and big-data analysis techniques).
This special section will focus on networking aspects (mostly network layer and above). Prospective authors are invited to submit high-quality, original manuscripts on topics including, but not limited to:
- Closed-loop control
- Big-data intelligent analytic frameworks for networking data
- Self-learning network architecture and systems
- AI & ML algorithms for network measurement
- AI & ML algorithms for traffic classification
- In-network intelligent control with AI & ML
- Distributed intelligent multi-agent systems for network control
- AI & ML algorithms for network scheduling and control
- Traffic engineer with AI & ML
- Congestion control based on AI & ML
- Network QoS based on AI & ML
- Protocol design and optimization using machine learning
- Resource allocation for shared/virtualized networks using machine learning
Submissions Due: CLOSED
Notification to Authors: July 1, 2020
Revised Manuscript Due: July 15, 2020
Final Notification: August 1, 2020
Publication in 2020
Visit the Author Information page for details on how to submit.
- Haipeng Yao, Beijing University of Posts and Telecommunications, China (firstname.lastname@example.org)
- Mohsen Guizani, Qatar University, Qatar (email@example.com)
- Maozhen Li, Brunel University, United Kingdom (Maozhen.Li@brunel.ac.uk)
- F. Richard Yu, Carleton University, Canada (Richard.Yu@Carleton.ca)