Intra-RAN Online Distributed Reinforcement Learning For Uplink Power Control in 5G Cellular Networks

Jian Song, Istvan Kovacs, Majid Butt, Jens Steiner, Klaus Ingemann Pedersen

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

3 Citationer (Scopus)

Abstract

Uplink power control plays a significant role in maintaining a good signal quality at the serving cell while minimizing interference to neighboring cells, thus maximizing the system performance. Traditionally, a single value open-loop power control (OLPC) parameter, P 0 , is configured for all the user equipments (UEs) in a cell, and often same setting is used for similar cells. Recent studies have demonstrated that optimal P 0 depends on many factors, which yields a complex multidimensional optimization problem and there are no efficient approaches known to solve it under practical system-level settings. In this paper, we propose a solution based on reinforcement learning (RL) where each BS autonomously adjusts its P 0 setting to maximize its throughput performance. As compared to conventional sub-optimal approach, our solution encompasses a smart clustering of UEs, where each cluster specifies its own P 0 . The proposed solution is evaluated by extensive system level simulations, where our results demonstrate a potential performance enhancement as compared to the baseline proposals.
OriginalsprogEngelsk
Titel2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring)
ForlagIEEE (Institute of Electrical and Electronics Engineers)
Publikationsdato25 aug. 2022
Sider1-7
ISBN (Trykt)978-1-6654-8244-8
ISBN (Elektronisk)978-1-6654-8243-1
DOI
StatusUdgivet - 25 aug. 2022
Begivenhed2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring) - Helsinki, Finland
Varighed: 19 jun. 202222 jun. 2022

Konference

Konference2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring)
LokationHelsinki, Finland
Periode19/06/202222/06/2022
NavnI E E E V T S Vehicular Technology Conference. Proceedings
ISSN1550-2252

Fingeraftryk

Dyk ned i forskningsemnerne om 'Intra-RAN Online Distributed Reinforcement Learning For Uplink Power Control in 5G Cellular Networks'. Sammen danner de et unikt fingeraftryk.

Citationsformater