MARS: Message Passing for Antenna and RF Chain Selection for Hybrid Beamforming in MIMO Communication Systems

TL;DR

This work addresses energy-efficient reception in uplink MIMO with hybrid beamforming by introducing an LDPC-based, partially connected HBF architecture and a message-passing RF/antenna selection scheme (MARS). It develops two MP variants, MARS-S (sequential) and MARS-P (parallel), plus a heuristic continuous-genetic beamformer, to jointly optimize RF/antenna selection and beamforming under QoS and power constraints. The LDPC-inspired connections guarantee information exchange across RF/antenna nodes, enabling distributed optimization with reduced complexity relative to exhaustive search. Results show substantial power savings and higher energy efficiency compared with fully/partially connected and other benchmarks, validating the practical potential for energy-efficient, flexible HBF in dense MIMO systems with large antenna counts.

Abstract

In this paper, we consider a prospective receiving hybrid beamforming structure consisting of several radio frequency (RF) chains and abundant antenna elements in multi-input multi-output (MIMO) systems. Due to conventional costly full connections, we design an enhanced partially connected beamformer employing a low-density parity-check (LDPC)-based structure. As a benefit of the LDPC-based structure, information can be exchanged among clustered RF/antenna groups, which results in a low computational complexity order. Advanced message passing (MP) capable of inferring and transferring information among different paths is designed to support the LDPC-based hybrid beamformer. We propose a message-passing enhanced antenna and RF chain selection (MARS) scheme for minimizing the operational power of antennas and RF chains of the receiver as well as hybrid beamforming. Furthermore, sequential and parallel MP schemes for MARS are designed, namely, MARS-S and MARS-P, respectively, to address the convergence speed issue. A heuristic genetic algorithm is designed for receiving hybrid beamforming, comprising gene generation initialization, elite selection, crossover, and mutation. Simulations validate the convergence of both the MARS-P and the MARS-S algorithms. Due to the asynchronous information transfer of MARS-P, it requires higher power than MARS-S, which strikes a compelling balance among power consumption, convergence, and computational complexity. It is also demonstrated that the proposed MARS scheme outperforms the existing benchmarks using the heuristic method of fully/partially connected architectures in the open literature by requiring the lowest power and realizing the highest energy efficiency.

Figures (12)

• Figure 1: Proposed structure of the antenna and RF chain selection for hybrid beamforming in uplink.
• Figure 2: Example of the proposed LDPC-based structure for MP considering $\varrho=\text{mod} (N_{ant}, N_{RF})$ with $N_{ant}\in\{5,6\}$ antenna nodes and $N_{RF}=3$ RF chain nodes. (a) $\varrho\neq 0$ and $N_{ant}=5$; (b) $\varrho=0$ and $N_{ant}=6$. Ant. and Msg. are acronyms for antenna and message, respectively.
• Figure 3: Example of sequential MP with the proposed MARS-S scheme considering $N_{ant}^C=4$ antenna controllers and $N_{RF}^C=2$ RF chain controllers.
• Figure 4: Example of parallel MP with the proposed MARS-P scheme considering $N_{ant}^C=4$ antenna controllers and $N_{RF}^C=2$ RF chain controllers.
• Figure 5: Convergence of the proposed MARS-S and MARS-P subschemes in terms of (a) power consumption and (b) EE.

Theorems & Definitions (3)

• Definition 1
• Lemma 1
• proof