Optimized antenna selection for mm-wave MIMO communication systems

Suryawanshi and Patil J Wireless Com Network (2025) 2025:9 https://doi.org/10.1186/s13638-025-02436-1 EURASIP Journal on Wireless Communications and Networking Open Access RESEARCH Optimized antenna selection for mm‑wave MIMO communication systems Rajashree Suryawanshi1*   and B. P. Patil1 *Correspondence: 1 Department of E&TC, Army Institute of Technology, Pune, India Abstract A millimeter-wave communication system uses multiple inputs and multiple outputs, which has high gains and spectral efficiency. To overcome empty path costs and create interactions using a suitable signal-to-noise ratio, large antenna arrays are used to perform precoding. To solve the complex problem without incurring significant performance losses, a novel deep learning-based method rather than methods with high delay, such as greedy search and saber selection, is proposed in this paper. For antenna selection, an optimized convolutional neural network (CNNs) is presented. In order to select antennas, the neural network takes the signal matrices as entries and returns the subset with the highest spectrum efficiency. An adaptive coati optimization technique is proposed for optimizing the weighting and bias of all of the layers in the CNN. As a consequence, a successive interference cancelation algorithm is used for prior coding with choice detectors to mitigate the route loss caused by high-frequency transmission. Simulation results show that the proposed model improves the throughput of the network. Besides, bit error rate and mean square error are reduced significantly by 0.44% and 1.54% than the existing antenna selection models. Keywords: MIMO, SE, Channel matrix, Antenna selection, Precoding 1 Introduction Millimeter-wave (mmW) communication is commonly regarded as one of the most effective ways to improve SE in 5G transmission networks [1]. MmW technology, which operates at frequencies ranging from 3 to 300 GHz, addresses the issue of spectral congestion. Multiple input, multiple output (MIMO) devices have been demonstrated to increase wireless communication capacity and reliability [2]. Combining mm-wave and MIMO communications has the potential to greatly increase data speeds. An RF chain connects each antenna in a MIMO system. As a result, the cost and complexity of hardware rise [3]. To meet modern data requirements, the mmW frequency band is thought to be a viable way to deploy massive MIMO. There has been considerable attention paid to the use of mmW frequencies. To meet the huge data rate needs of 5G transmission networks, massive MIMO architecture is being combined with mmW services [4]. With a large MIMO design, the SNR at acceptance is considerably improved [5]. Massive MIMO is gaining traction in a variety of research domains because it offers greater temporal flexibility. As a result, system performance has increased © The Author(s) 2025. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. Suryawanshi and Patil J Wireless Com Network (2025) 2025:9 [6]. Low-resolution ADCs significantly enhance system performance since they use the majority of energy in the recipient’s RF link. Recently, research on the underused extremely high-frequency spectrum, often known as the mmW band, has been conducted. Despite this, communications at such high frequencies have considerable route losses. To overcome free space route loss, large antenna array precoding and beamforming techniques may be able to offer sufficient array gain to create connections using a good SNR. A massive MIMO system using mmW frequencies may have a huge number of transmit antennas, making it difficult to properly precode to optimize spatial multiplexing benefits. Because of the high power and energy consumption, as well as the increasing complexity, each antenna requires its own radio frequency (RF) chain, which is not possible [7]. Because of their enormous number of antennas, mm-Wave systems consume a lot of energy and cost more in the digital realm. For increased cost effectiveness, a mixed analog/digital architecture is the most convenient option [8]. Many sensors are linked to a few RF networks that execute analog-to-digital conversions using an analog frontend [9]. There are two types of hybrid analog/digital architectures: fully connected architectures and partially connected architectures. A completely linked system has all of its antennas connected to the RF chains, whereas a partially connected system has some of its antennas connected to the RF chains. For the purpose of maximizing energy efficiency, a zero-forcing precoding technique as well as a low-complexity power control scheme is reported in [10–14]. Based on various beamforming algorithms (digital, analog, and hybrid), the authors of [8] evaluate the choice between spectral and power savings in antennas equipped with inferior ADCs. This study focuses on the selection of transmit antennas. In recent years, DL has received a great deal of attention in regard to applications such as artificial cluster choice [15] and cluster operation in congested mmW [16]. 1.1 Related works For an mm-wave MIMO system, Reba et al. [17] developed a GQSM transceiver structure. To avoid ICI, a new antenna selection strategy was used in this approach. A virtual antenna grouping was carried out to choose the antenna combinations in GQSM. By examining average BER, the authors assessed the performance of the suggested system. Additionally, the recommended system’s average BER performance was contrasted with that of mm-wave MIMO supported by QSM and GSM. According to simulations, the GQSM mm-wave MIMO system achieved a lower average BER than the current schemes. Comparing the GQSM mm-wave MIMO method with the PQSM method, the developed method was less complex. A multi-user mmW link optical radar cluster design is presented by Huang et al. [18] for general frequency-selective channels. At the BS, a minimal design SC connection, including their way postponement compensation, was first presented. In order to calculate (...truncated)