.png){kind=icon}
.png){kind=icon}
Return
LLM-Driven Multicast Network Slicing for 6G Non-Terrestrial Networks
.png){kind=icon}
PRE
AI
Z
J
Y
L
F
DOI：10.1109/TBC.2025.3637704.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Non-terrestrial networks (NTNs) will play a central role in 6G broadcasting by providing ubiquitous coverage and the ability to offload media processing to space-borne compute. The next generation of immersive media services will require multicasting data from satellites to large groups of receivers with stringent latency and quality-of-service (QoS) demands. This paper proposes a large-language-model (LLM)-driven orchestration framework that translates broadcaster intents into optimized multicast network slices spanning ground and space resources. Building on the concept of computing-power networks (CPNs), the framework integrates compute-aware routing across GEO, MEO and LEO links, enforces delay-aware multicast constraints using an integer-linear-program formulation, and leverages LLM to adaptively admit multicast groups under resource constraints. A federated fine-tuning mechanism combined with a blockchain audit layer enables continuous improvement of the LLM while preserving data privacy and providing human-interpretable audit trails. Simulations demonstrate that the proposed method reduces end-to-end latency and energy consumption compared to traditional heuristics, while increasing the number of admitted multicast requests.
Keywords:
6G
non-terrestrial networks
multicast network slicing
large language models
federated learning
blockchain
broadcasting
Journal
IF:
4.8
Papers:
2.1K
Citations:
3.0K
Organization
Cited Papers