| Full text | |
| Author(s): |
Total Authors: 3
|
| Affiliation: | [1] CY Cergy Paris Univ, CNRS, ENSEA, ETIS UMR 8051, F-95000 Cergy - France
[2] Ctr Digital Syst, Inst Mines Telecom, IMT Lille Douai, F-59653 Villeneuve Dascq - France
[3] Univ Lille, UPHF, Cent Lille, CNRS, UMR 8520, IEMN, F-59000 Lille - France
Total Affiliations: 3
|
| Document type: | Journal article |
| Source: | IEEE WIRELESS COMMUNICATIONS LETTERS; v. 10, n. 4, p. 750-754, APR 2021. |
| Web of Science Citations: | 0 |
| Abstract | |
In this letter, the outage performance of a two-user downlink non-orthogonal multiple access (NOMA) time-varying network without any knowledge on the channel state or distribution at the base station (BS) is investigated. Building on reinforcement learning techniques and, more precisely, on multi-armed bandits (MAB), we propose a novel adaptive NOMA scheme that optimally tunes which user should perform successive interference cancellation (SIC) jointly with the power allocation at the BS. Remarkably, our proposed scheme requires only a single bit (ACK-type) of feedback from each user and is still able to outperform OMA, as demonstrated by the numerical results in many settings of interest including stochastic and even non-stationary (adversarial) ones. (AU) | |
| FAPESP's process: | 18/12579-7 - ELIOT: enabling technologies for IoT |
| Grantee: | Vitor Heloiz Nascimento |
| Support Opportunities: | Research Projects - Thematic Grants |