Radio Resource Management for 6G in-X Subnetworks

Radio resource management (RRM) involves selecting key transmission parameters—such as transmit power, frequency resources, precoder, and modulation. The complexity of this process is expected to increase significantly with the tenfold densification anticipated in 6G networks compared to 5G. The concept of in-X subnetworks has been introduced as a further leap of heterogeneous network, with the aim of providing highly localized wireless coverage for use cases such as in-robot, in-production module, in-vehicle, in-room communication. These subnetworks are expected to support diverse services, possibly extreme requirements in terms of ultra-short control cycle time, reliability, and service availability, surpassing the capabilities of 5G and its evolution. While the specific characteristics of in-X subnetworks can offer opportunities for efficient radio design, interference can be a major limiting factor in dense deployments. Subnetworks may be then characterized by such high density (e.g., vehicles in a congested road, robots in matrix production), and they can also be mobile, leading to rapid interference fluctuations. These aspects may result in wide and rapidly fluctuating interference patterns, which make the RRM problem more challenging than in traditional wireless setups, characterized by static base stations/access points and lower cell densities. The radio resource management problem is usually non-convex with NP-hardness, while traditional optimization methods and heuristics have shown efficacy in certain scenarios, these algorithms have exponential computational complexity and typically require many iterations. The dynamic and complex environment of In-X subnetworks, coupled with stringent low latency requirements, calls for more adaptive solutions with lower computational complexity. This necessity is driving the adoption of advanced artificial intelligence (AI) solutions. This challenge, supported by two EU SNS JU projects, 6G-SHINE and CENTRIC, focuses on developing machine learning-based solutions for optimizing sub-band allocation and power control within dense in-factory subnetworks.

Speakers:
Saeed Hakimi
Postdoctoral researcher
Aalborg University

Moderators:
Jiaying Meng
Junior Programme Officer
International Telecommunication Union (ITU)

Vishnu Ram OV
Independent Research Consultant
Consultant

The AI for Good Global Summit is the leading action-oriented United Nations platform promoting AI to advance health, climate, gender, inclusive prosperity, sustainable infrastructure, and other global development priorities. AI for Good is organized by the International Telecommunication Union (ITU) – the UN specialized agency for information and communication technology – in partnership with 40 UN sister agencies and co-convened with the government of Switzerland.

Join the Neural Network!
👉https://aiforgood.itu.int/neural-netw...
The AI for Good networking community platform powered by AI.
Designed to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to advance the SDGs using AI.

🔴 Watch the latest #AIforGood videos!
aiforgood

📩 Stay updated and join our weekly AI for Good newsletter:
http://eepurl.com/gI2kJ5

🗞Check out the latest AI for Good news:
https://aiforgood.itu.int/newsroom/

📱Explore the AI for Good blog:
https://aiforgood.itu.int/ai-for-good...

🌎 Connect on our social media:
Website: https://aiforgood.itu.int/
Twitter: Twitter: AIforGood
LinkedIn Page: LinkedIn: 26511907
LinkedIn Group: LinkedIn: 8567748
Instagram: Instagram: aiforgood
Facebook: Facebook: AIforGood

Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.

• #science_technology
• #ai_for_good
• #ai
• #artificial_intelligence
• #machine_learning
• #deep_learning
• #ai_for_good_global_summit