Hierarchical MAB Framework for Energy-Aware Beam Training for Near-Field Communications
Yunxing Xiang, Yi Yan, Yunchao Song, Jing Gao, Xiaohui You, Jun Wang, Huibin Liang, Yixin Jiang · 2025
Read Hierarchical MAB Framework for Energy-Aware Beam Training for Near-Field Communications by Yunxing Xiang, Yi Yan, Yunchao Song, Jing Gao, Xiaohui You, Jun Wang, Huibin Liang, Yixin Jiang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12788118.txt.
Description
Yunxing Xiang and co-authors trained beams with a bandit framework in two thousand twenty-five. Near-field systems use huge antenna arrays for fast links. Finding the best beam for each user costs energy. Devices also run on limited batteries. The team built a two-phase learning scheme. It schedules users and trains beams in layers.
Phase one scores users by rate and battery level. A confidence-bound rule balances trying and trusting. Phase two then trains beams for chosen users. Two further rules search coarse then fine directions. Energy awareness extends device working life. Link quality is guarded at the same time. The scheme targets dense future wireless deployments.
Catalog record
| CREATOR | Yunxing Xiang, Yi Yan, Yunchao Song, Jing Gao, Xiaohui You, Jun Wang, Huibin Liang, Yixin Jiang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |