In the 5G intelligent edge scenario, more and more accelerator-based single-board computers (SBCs) with low power consumption and high performance are being used as edge devices to run the inferencing part of the artificial intelligence (AI) model to deploy intelligent applications. In this paper, we investigate the inference workflow and performance of the You Only Look Once (YOLO) network, which is the most popular object detection model, in three different accelerator-based SBCs, which are NVIDIA Jetson Nano, NVIDIA Jetson Xavier NX and Raspberry Pi 4B (RPi) with Intel Neural Compute Stick2 (NCS2). Different video contents with different input resize windows are detected and benchmarked by using four different versions of the YOLO model across the above three SBCs. By comparing the inference performance of the three SBCs, the performance of RPi + NCS2 is more friendly to lightweight models. For example, the FPS of detected videos from RPi + NCS2 running YOLOv3-tiny is 7.6 times higher than that of YOLOv3. However, in terms of detection accuracy, we found that in the process of realizing edge intelligence, how to better adapt a AI model to run on RPi + NCS2 is much more complex than the process of Jetson devices. The analysis results indicate that Jetson Nano is a trade-off SBCs in terms of performance and cost; it achieves up to 15 FPSs of detected videos when running YOLOv4-tiny, and this result can be further increased by using TensorRT.
A transmit antenna selection (TxAS) aided multi-user multiple-input multiple-output (MU-MIMO) system is proposed for operating in the MIMO downlink channel environments, which shows significant improvement in terms of higher data rate when compared to the conventional MU-MIMO systems operating without adopting TxAS, while maintaining low hardware costs. We opt for employing a simple yet efficient zero-forcing beamforming (ZFBF) linear precoding scheme at the transmitter in order to reduce the decoding complexity when considering users’ side. Moreover, considering that users within the same cell may require various qualities of service (QoS), we further propose a novel user-oriented smart TxAS (UOSTxAS) scheme, of which the main idea is to carry out AS based on the QoS requirements of different users. At last, we implement the proposed UOSTxAS scheme in the software defined radio (SDR) MIMO communication hardware platform, which is the first prototype hardware system that runs the UOSTxAS MU-MIMO scheme. Our results show that, by employing TxAS, the proposed UOSTxAS scheme is capable of offering higher data rates for priority users, while reasonably ensuring the performance of the common users requiring lower rates both in simulation and in the implemented SDR MIMO communication platform.
In recent years, antenna selection (AS) has become one of the most popular research topics for massive multiple-input multiple-output (MIMO) system due to its capability of reducing the number of radio frequency chains utilized for MIMO communications, while remaining the MIMO advantages, such as increased bandwidth efficiency and reliability. In this paper, an efficient norm-based AS (NBAS) algorithm is investigated and implemented in the software defined radio (SDR) MIMO communication platform, which consists of field-programmable gate arrays (FPGAs). Owing to the high freedom and fast reconfigurable FPGA hardware, the SDR MIMO communication platform is capable of developing prototype of NBAS-aided MIMO system. More specifically, the implemented NBAS aided SDR MIMO system is capable of achieving uplink communication from users to the base station via time division duplex (TDD). A time-varying fading channel generation model is designed for SDR MIMO platform to enrich our experimental results. Additionally, a novel multiplexer (MUX) circuit module is designed and implemented to enhance the hardware performance of the FPGA in term of delay and resource usage. The results show that by implementing the low-complexity NBAS, the channel capacity performance of the SDR MIMO system can be significantly improved by around 15%. It is also showed that our proposed optimized MUX circuit intellectual property may reduce the critical path delay by about 2.16 ns, and save at lease 3% hardware resources in SDR FPGA. INDEX TERMS Multiple-input multiple-output, antenna selection, software defined radio, FPGA.
In this paper, we propose and implement a novel framework of deep learning based antenna selection (DLBAS)-aided multiple-input–multiple-output (MIMO) software defined radio (SDR) system. The system is constructed with the following three steps: (1) a MIMO SDR communication platform is first constructed, which is capable of achieving uplink communication from users to the base station via time division duplex (TDD); (2) we use the deep neural network (DNN) from our previous work to construct a deep learning decision server to assist the MIMO SDR platform for making intelligent decision for antenna selection, which transforms the optimization-driven decision making method into a data-driven decision making method; and (3) we set up the deep learning decision server as a multithreading server to improve the resource utilization ratio. To evaluate the performance of the DLBAS-aided MIMO SDR system, a norm-based antenna selection (NBAS) scheme is selected for comparison. The results show that the proposed DLBAS scheme performed equally to the NBAS scheme in real-time and out-performed the MIMO system without AS with up to 53% improvement on average channel capacity gain.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.