Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator

Riviello, Daniel Gaetano; Tuninato, Riccardo; Zimaglia, Elisa; Fantini, Roberto; Garello, Roberto

doi:10.3390/s23020910

Cited by 7 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Leveraging the accurate CSI, the BS can design the appropriate precoding vector, thus improving the transmission quality. This is especially significant in FDD systems because, unlike in TDD systems where channel reciprocity is taken into account, the CSI of the downlink cannot be directly obtained from the channel estimation at the BS [5][6][7]. The CSI at the BS in FDD systems relies heavily on accurate feedback from the UE in real time, which poses a formidable challenge since the feedback overhead increases in a linear manner as the number of antennas grows [8].…”

Section: Introductionmentioning

confidence: 99%

Multi-Head Transformer Architecture with Higher Dimensional Feature Representation for Massive MIMO CSI Feedback

Chen,

Guo,

Cui

2024

Applied Sciences

View full text Add to dashboard Cite

To achieve the anticipated performance of massive multiple input multiple output (MIMO) systems in wireless communication, it is imperative that the user equipment (UE) accurately feeds the channel state information (CSI) back to the base station (BS) along the uplink. To reduce the feedback overhead, an increasing number of deep learning (DL)-based networks have emerged, aimed at compressing and subsequently recovering CSI. Various novel structures are introduced, among which Transformer architecture has enabled a new level of precision in CSI feedback. In this paper, we propose a new method named TransNet+ built upon the Transformer-based TransNet by updating the multi-head attention layer and implementing an improved training scheme. The simulation results demonstrate that TransNet+ outperforms existing methods in terms of recovery accuracy and achieves state-of-the-art.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Head Transformer Architecture with Higher Dimensional Feature Representation for Massive MIMO CSI Feedback

Chen,

Guo,

Cui

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Fifth-generation systems promise to provide data rates as much as ten times higher compared to the previous generations of wireless communication, and that too at a faster pace [ 1 , 2 ]. The utilization of millimeter wave bands makes it possible to achieve the goals set in terms of data rate and latency.…”

Section: Introductionmentioning

confidence: 99%

On Scalability of FDD-Based Cell-Free Massive MIMO Framework

Hassan,

Baig,

Aslam

2023

Sensors

View full text Add to dashboard Cite

Cell-free massive multiple-input multiple-output (MIMO) systems have the potential of providing joint services, including joint initial access, efficient clustering of access points (APs), and pilot allocation to user equipment (UEs) over large coverage areas with reduced interference. In cell-free massive MIMO, a large coverage area corresponds to the provision and maintenance of the scalable quality of service requirements for an infinitely large number of UEs. The research in cell-free massive MIMO is mostly focused on time division duplex mode due to the availability of channel reciprocity which aids in avoiding feedback overhead. However, the frequency division duplex (FDD) protocol still dominates the current wireless standards, and the provision of angle reciprocity aids in reducing this overhead. The challenge of providing a scalable cell-free massive MIMO system in an FDD setting is also prevalent, since computational complexity regarding signal processing tasks, such as channel estimation, precoding/combining, and power allocation, becomes prohibitively high with an increase in the number of UEs. In this work, we consider an FDD-based scalable cell-free network with angular reciprocity and a dynamic cooperation clustering approach. We have proposed scalability for our FDD cell-free and performed a comparative analysis with reference to channel estimation, power allocation, and precoding/combining techniques. We present expressions for scalable spectral efficiency, angle-based precoding/combining schemes and provide a comparison of overhead between conventional and scalable angle-based estimation as well as combining schemes. Simulations confirm that the proposed scalable cell-free network based on an FDD scheme outperforms the conventional matched filtering scheme based on scalable precoding/combining schemes. The angle-based LP-MMSE in the FDD cell-free network provides 14.3% improvement in spectral efficiency and 11.11% improvement in energy efficiency compared to the scalable MF scheme.

show abstract

“…This approach considers environmental factors and model evolution effects, yielding more accurate and effective predictions when applied in environments similar to the model. Stochastic channel models include the Geometric Stochastic Model (GBSM) [11], Non-Geometric Stochastic Model (NGSM) [12], Graph-Based Model, and Saleh-Valenzuela (SV) [13] model. GBSM encompasses Regular-Shaped and Irregular-Shaped models, while NGSM includes the Tapped Delay Line and Clustered Delay Line models.…”

mentioning

confidence: 99%

Application of Artificial Potential Field Method in Three-Dimensional Path Planning for UAV Considering 5G Communication

Tang,

Chen,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Maintaining robust communication between UAV(Unmanned aerial vehicle) and host computers is pivotal for ensuring the security and reliability of UAV in executing automated tasks. The advent of 5G, the latest generation of mobile communication technology, presents an opportunity to establish low-latency and high-reliability communication links between UAV and host computers. While automatic flight schemes of UAV are typically calculated through three-dimensional path planning, existing schemes often overlook the communication quality between UAV and the host computer during flight execution. This study proposes a novel approach to three-dimensional path planning that integrates considerations of 5G communication intensity into the traditional artificial potential field (APF) method. Utilizing ray tracing method, the average 5G communication intensity within a given region is computed, and areas with optimal average 5G communication quality are identified as 5G secondary gravitational points. These points guide the UAV's three-dimensional path toward regions with superior 5G communication quality. To address the challenge of local minimum traps inherent in traditional APF methods, this study proposes employing a fuzzy control algorithm to generate auxiliary forces, enabling UAV to avoid such traps proactively. Simulation experiments conducted using MatlabR2023b validate the efficacy of the proposed approach. Results demonstrate that the enhanced APF method effectively mitigates local minimum problems, albeit with a marginal increase in average path length (13.7769%). Notably, the average path's 5G communication intensity experiences a substantial improvement (20.7919%), indicating that the algorithm prioritizes enhancing communication quality at the expense of slightly longer paths. Moreover, in scenarios with severe signal masking at the transmitter, the algorithm exhibits even greater improvements in average path 5G communication intensity.INDEX TERMS 5G, artificial potential field, three-dimensional path planning, ray tracing, fuzzy control. I. INTRODUCTIONT HE aerial unmanned aerial vehicle (UAV), comprises a fundamental system consisting of the UAV itself, a host computer, and communication equipment facilitating communication between the UAV and the host computer. Over recent years, propelled by rapid advancements in the UAV industry, the applications of UAV has diversified extensively. From rudimentary transportation tasks, UAV has expanded their scope to encompass a myriad of complex missions, including high-altitude inspection, agricultural and forestry operations, geographic mapping, urban aerial photography, and detection and rescue missions. To execute these multifaceted tasks efficiently, UAV necessitates high-precision automatic control, entailing the development of automated, efficient, and safe flight plans. The advent of the latest cellular mobile communication network technology, 5G, has changed UAV operations by enabling real-time transmission of ultrahigh-definition imagery and remote low-latenc...

show abstract

Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator

Cited by 7 publications

References 38 publications

Multi-Head Transformer Architecture with Higher Dimensional Feature Representation for Massive MIMO CSI Feedback

Multi-Head Transformer Architecture with Higher Dimensional Feature Representation for Massive MIMO CSI Feedback

On Scalability of FDD-Based Cell-Free Massive MIMO Framework

Application of Artificial Potential Field Method in Three-Dimensional Path Planning for UAV Considering 5G Communication

Contact Info

Product

Resources

About