FITEE Special Feature on
AI-Empowered Digital-Twin-Based Network Autonomy
Call for Papers
(Submission by June 1, 2024)
With large-scale deployment and application of 5G networks, factors such as nearly ten million base stations, thousands of optimization parameters, and the coexistence of 3G/4G/5G wireless networks have led to a sharp increase in the difficulty and cost of operating and optimizing mobile communication networks, seriously affecting user experience. Network intelligence has become an important means to solve this problem. However, due to the limitations of existing network architecture design, the application of artificial intelligence (AI) in network intelligence can only be conducted in a scenario-based and plug-in manner. The validity, availability, and timeliness of the data required for AI applications are also difficult to guarantee. These issues make it difficult for AI applications to achieve the expected performance. Dissonance may arise between different use cases, affecting the stability and reliability of the network.
In view of the existing challenges, 6G wireless network needs to fully consider the application of AI at the beginning of the architecture design. Through the design of native AI, 6G flexibly supports the application of AI in network operation and operation maintenance. At the same time, the digital twin network provides AI training and pre-validation of effects, reducing trial-and-error costs and achieving a high degree of network autonomy. Network autonomy based on native AI and digital twin technology has become an important research direction for 6G and has received widespread attention in the industry. The design of native AI can provide on-demand computing capacity, data, and model/algorithm support for 6G networks, systematically supporting ubiquitous AI applications in network operation and optimization. The digital twin technology has been widely applied in industries such as industrial manufacturing and aviation. The digital twin of wireless networks not only provides network visualization, but also provides network performance and fault prediction, problem localization, AI algorithm training and performance pre-validation, etc. Combined with the design of endogenous AI, it supports the implementation of highly autonomous networks.
Focusing on the theories, models, technologies, architectures, and prototypes of native AI and digital twins in 6G wireless networks, this special feature is aimed to enable the researchers in academia and industry to have a deeper understanding of the basic theories, hardware design, system architecture, algorithm optimization, and application technologies related to 6G network autonomy, and to provide assistance and inspiration for researching related topics and promoting the industry consensus of 6G wireless network architecture as well as the standardization and implementation of related technologies.
We invite papers on the following topics (but not limited to):
● Use cases and scenarios of wireless network autonomy
● QoS definition and evaluation of AI services
● AI service orchestration and management throughout the entire lifecycle
● Wireless network architecture for native AI
● Dataset for wireless network AI training
● Data collection and management in wireless networks
● Distributed learning for network AI applications
● Functionality and performance modeling of network elements such as terminals and base stations
● Fast modeling and simulation of wireless channels for digital twins
● Wireless network service prediction
● Modeling and prediction of the performance and user experience in wireless networks
● Fault prediction, localization, and root cause analysis in wireless networks
● Prototype and outfield verification of native AI and network digital twins
Editorial Board
Editor-in-Chief
Prof. Ping Zhang, Beijing Univ Posts Telecommun
Executive Lead Editor
Guangyi Liu, Principal Scientist, China Mob Res Inst
Editors (in alphabetical order by last name)
Dr. Tao Chen, Principal Scientist, VTT, Finland
Prof. Yongming Huang, Southeast Univ
Prof. Yong Li, Tsinghua Univ
Prof. Jiangzhou Wang, Univ Kent, UK
Prof. Jun Wang, Univ College London, UK
Prof. Yang Yang, Hong Kong Univ Sci Technol (Guangzhou)
Prof. Honggang Zhang, Zhejiang Lab
Prof. Jianhua Zhang, Beijing Univ Posts Telecommun
Prof. Yan Zhang, Univ Oslo, Norway
Prof. Jinkang Zhu, Univ Sci Technol China
Submission Instructions
All submitted manuscripts must be written in English and must not be under consideration elsewhere for publication. Guidelines for authors are available at https://www.fitee.zjujournals.com/en/aboutus/8550/. Either Word or LaTeX format is acceptable. When Word is used, the layout of the text should be in single column, 1.5 lines spacing, 10.5 pt font size, and Times New Roman font. A template is available at http://www.jzus.zju.edu.cn/download/FITEE_LaTex_template.zip. Manuscripts should be submitted via https://www.editorialmanager.com/zusc/ under the article type “S.I. - NetAut”.
Important Dates
Manuscript submission by June 1, 2024
Acceptance notification by Aug. 31, 2024
Publication date: Oct./Nov., 2024
Introduction to FITEE
FITEE is a peer-reviewed journal launched by the Chinese Academy of Engineering (CAE) and Zhejiang University, and co-published by Springer & Zhejiang University Press. It is SCI-E indexed, with an IF of 3.0 (2022 JCR). FITEE aims to publish the latest implementation of applications, principles, and algorithms in the broad area of Electrical and Electronic Engineering. All articles will undergo international peer review and crosscheck processes before they are accepted to ensure high quality.
For inquiries regarding this special issue, please contact:
Editorial Office, Ziyang Zhai (managing editor),
jzus_zzy@zju.edu.cn,
+86-571-88273162
