Key Technologies Towards the Integration of AI and Radio Access Network
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Communications".
Deadline for manuscript submissions: 30 September 2026 | Viewed by 171
Special Issue Editors
Interests: AI-enabled communications; wireless foundation model; AI-RAN
Interests: physical layer security; wireless AI; B5G/6G wireless communication systems; internet of things; R&D of experimental platform for wireless communications
Special Issues, Collections and Topics in MDPI journals
Interests: reconfigurable intelligent surface; non-orthogonal multiple access; MIMO systems; wireless security; millimeter wave communications
Interests: 5G; big data; physical layer security; AI in wireless networks; IoT
Special Issues, Collections and Topics in MDPI journals
Interests: agentic AI and AI-native resource management; mobile edge computing; cyber-physical systems security
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
In the IMT-2030 (6G) vision published in 2023, ITU-R clearly identified the integration of AI and communications as one of the six pillars for 6G. It is widely acknowledged that future wireless networks will undergo a paradigm shift toward AI-native architectures, where communication systems are natively designed to support AI services and AI is deeply embedded across network layers. In this context, the integration of AI and radio access networks (RAN) plays a crucial role in enabling AI-native wireless systems. Generally speaking, the integration of AI and RAN includes two aspects: AI for RAN and RAN for AI. AI for RAN focuses on utilizing AI techniques to enhance RAN functionalities at the physical layer, MAC layer, and network layer, with the goal of improving RAN performance, such as spectral efficiency, throughput, energy efficiency, etc. RAN for AI, on the other hand, aims at developing communication and networking solutions that efficiently support AI services within the RAN entities, enabling low-latency, distributed, and scalable AI inference and training.
While preliminary studies have shown the great potential of integrating AI and RAN, the research in this area is still facing critical challenges. First, the existing cellular network architecture is connectivity-centric, and it is unclear how to jointly orchestrate communications, computing, and storage resources within the networks to support ubiquitous intelligence. Second, although a rich body of literature has appeared studying the use of deep learning algorithms to enhance communications systems, these algorithms still suffer from weak generalization capabilities across diversified scenarios. Third, the mainstream AI models, such as Transformer, are computationally intensive, requiring a relatively long time to output the inference results. However, most wireless applications have very stringent constraints on latency (e.g., physical layer processing usually needs to be completed within milliseconds). Last but not least, most of the state-of-the-art technologies are evaluated using simulations, and it is demanding to develop testbeds for performance evaluation in real-world environments.
Motivated by the rapid progress and growing interests in this area, this Special Issue aims to provide a timely platform for reporting recent advances with emerging technologies and system designs, and address the aforementioned challenges related to the integration of AI and RAN. We invite high-quality, original research contributions covering topics including, but not limited to, the following:
Information theoretic fundamentals for AI-RAN integration;
Emerging network architecture design to support the integration of AI and RAN;
AI-enabled physical-layer technologies;
AI-driven MAC layer design and resource management;
AI for integrated sensing and communications (ISAC);
Co-deign of communications, computing, and storage;
Resource orchestration and network slicing;
Cooperative and distributed learning under wireless environments;
low-latency AI inference and training over wireless networks;
Device–edge–cloud collaboration for AI applications;
Agent/multi-agent architectures, protocols, and algorithms;
Emerging applications enabled by the integration of AI and RAN, e.g., UAV, embodied AI, industrial robots, and self-driving;
Advanced RAN algorithms for AI-native EdgeWireless-specific neural network design;
The interplay between generative AI and wireless networks;
Semantic and task-oriented (goal-oriented) communications;
Cross-layer design for AI-RAN co-optimization;
Dataset construction and benchmarks for performance evaluation;
Wireless foundation models with applications;
Security, privacy, and trust management;
Demos, testbeds, and field trials;
Standard Progress in the field of RAN and AI integration.
Dr. Yuwei Wang
Dr. Li Sun
Dr. Maged Elkashlan
Dr. Qinghe Du
Dr. Bilal Hussain
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 250 words) can be sent to the Editorial Office for assessment.
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. Sensors 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 2600 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
- AI
- radio access network
- physical-layer technologies
- resource management
- ISAC
- cooperative and distributed learning
- collaborative Inference
- wireless foundation model
- multi-agent
- 6G
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.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
