Deep Reinforcement Learning for NextG Radio Access Network Slicing With Spectrum Coexistence
IEEE Networking Letters · 2023-09 · 5 (3) · 149-153
DOI: 10.1109/lnet.2023.3284665 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Networking Letters, 2023-09. Verfasst von Yi Shi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 17 Literaturangaben. Gefördert von: U.S. Army Research Office.
Abstract (Originalsprache)
Reinforcement learning (RL) is applied for dynamic admission control and resource allocation in NextG radio access network slicing. When sharing the spectrum with an incumbent user (that dynamically occupies frequency-time blocks), communication and computational resources are allocated to slicing requests, each with priority (weight), throughput, latency, and computational requirements. RL maximizes the total weight of granted requests over time beyond myopic, greedy, random, and first come, first served solutions. As the state-action space grows, Deep Q-network effectively admits requests and allocates resources as a low-complexity solution that is robust to sensing errors in detecting the incumbent user activity.
Förderung
- U.S. Army Research Office
Zitieren
APA
Shi, Y., Costa, M., Erpek, T., & Sagduyu, Y. E. (2023). Deep Reinforcement Learning for NextG Radio Access Network Slicing With Spectrum Coexistence. IEEE Networking Letters, 5(3), 149-153. https://doi.org/10.1109/lnet.2023.3284665
Vancouver
Shi Y, Costa M, Erpek T, Sagduyu YE. Deep Reinforcement Learning for NextG Radio Access Network Slicing With Spectrum Coexistence. IEEE Networking Letters. 2023;5(3):149-153. doi:10.1109/lnet.2023.3284665
BibTeX
@article{Shi2023,
author = {Shi, Yi and Costa, Maice and Erpek, Tugba and Sagduyu, Yalin E.},
title = {Deep Reinforcement Learning for NextG Radio Access Network Slicing With Spectrum Coexistence},
journal = {IEEE Networking Letters},
year = {2023},
volume = {5},
number = {3},
pages = {149--153},
doi = {10.1109/lnet.2023.3284665}
}
EUVIMED