2021
DOI: 10.1109/twc.2021.3076760
|View full text |Cite
|
Sign up to set email alerts
|

Online Learning-Based Reconfigurable Antenna Mode Selection Exploiting Channel Correlation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 13 publications
(5 citation statements)
references
References 32 publications
0
5
0
Order By: Relevance
“…By adopting zeroforcing fully-digital precoding, the received signal-to-noise ratio (SNR) at the UE can be equivalently used as an optimization metric to maximize the SE, and the authors of [10] proposed an iterative mode selection method to design the EMR domain precoding by maximizing this SNR metric. The work in [11] considered small-scale MIMO system with a single UE, where only EMR domain precoding was studied, and Thompson sampling and upper confidence bound algorithms were applied for its design. Obviously, when extending to hybrid arrays, mMIMO, and multi-user scenarios, these EMR domain precoding methods cannot be directly applied.…”
Section: Three-level Precoding For R-mmimo a Overview Of Existing Sch...mentioning
confidence: 99%
“…By adopting zeroforcing fully-digital precoding, the received signal-to-noise ratio (SNR) at the UE can be equivalently used as an optimization metric to maximize the SE, and the authors of [10] proposed an iterative mode selection method to design the EMR domain precoding by maximizing this SNR metric. The work in [11] considered small-scale MIMO system with a single UE, where only EMR domain precoding was studied, and Thompson sampling and upper confidence bound algorithms were applied for its design. Obviously, when extending to hybrid arrays, mMIMO, and multi-user scenarios, these EMR domain precoding methods cannot be directly applied.…”
Section: Three-level Precoding For R-mmimo a Overview Of Existing Sch...mentioning
confidence: 99%
“…One important problem existing in pattern reconfigurable MIMO (PR-MIMO) communication systems is how to choose a promising radiation mode during data transmission. In the literature, most solutions to date are dependent on the multiarmed bandit or Thompson sampling theory [5]- [7]. For example, in [6], the PR mode selection problem is formulated as a multi-armed bandit problem to select the best radiation pattern via an online learning process without the need for instantaneous channel state of information (CSI) of all radiation modes.…”
Section: Introductionmentioning
confidence: 99%
“…For example, in [6], the PR mode selection problem is formulated as a multi-armed bandit problem to select the best radiation pattern via an online learning process without the need for instantaneous channel state of information (CSI) of all radiation modes. In [7], a Thompson sampling algorithm with channel prediction (TS-CP) is proposed based on the multiarmed bandit theory. The TS-CP exploits channel correlation to predict the channel conditions of unexplored radiation modes.…”
Section: Introductionmentioning
confidence: 99%
“…On one hand, the mode selection mechanism brings unacceptable channel estimation overhead. The channel prediction based on the correlation among the pattern modes [24] and the effective mode selection scheme based on reinforcement learning (RL) [25]- [29] are the major solutions to this issue currently. On the other hand, the physical mechanism of how the radiation pattern of MR-MIMO affects the channel has not been revealed, and it is not clear how to design the optimal radiation pattern for capacity maximization in MR-MIMO systems, which is the focus of this paper.…”
Section: Introductionmentioning
confidence: 99%