CNN-Based mmWave Path Loss Modeling for Fixed Wireless Access in Suburban Scenarios

Chen, Hong; Ma, Shengjie; Lee, Hyukjoon

doi:10.1109/lawp.2020.3014314

Cited by 34 publications

(23 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of CNN's prediction can be influenced as well. In [23], a CNN-based path loss model is proposed for mmWave path loss modeling in suburban environments. The CNN-based path loss model has four subnetworks to predict the path loss values of the four directional antennas of an Rx.…”

Section: B Cnn-based Path Loss Modelmentioning

confidence: 99%

“…Close inspection in the contribution of input values to the predicted path loss values of the CNN model obtained in [23] has suggested CNNs may not have been completely successful in approximating the underlying path loss model. The first observation made is that it is difficult to find a correlation between the path loss predictions and TRseparation, as shown in Fig.…”

Section: Ae-cnn Path Loss Modelmentioning

confidence: 99%

“…The unsatisfactory performance of conventional path loss modeling methods and their low efficiency in practice have prompted researchers to find an alternative path loss modeling method such as deep learning methods [21]- [23]. Deep learning is a subset of machine learning algorithms that use multiple processing layers to learn representations of data with multiple levels of autonomous feature abstraction [24].…”

Section: Introductionmentioning

confidence: 99%

“…In [23], for instance, it is shown that CNNs can be trained to predict path loss values based on the input images that are expected to encode the structural information of a local map for each pair of Tx and Rx locations. However, it is not clear whether the CNNs are trained to model the underlying path loss functions based on all the latent features which may not even be extracted as expected.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Millimeter Wave Path Loss Modeling for 5G Communications Using Deep Learning With Dilated Convolution and Attention

Chen

Lee

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

An accurate and efficient path loss modeling method for millimeter wave communications plays a significant role in the large-scale deployment of a fifth-generation (5G) mobile communication system. Conventional path loss modeling methods such as deterministic methods, empirical methods, and machine learning-based methods, in practice, cannot achieve the desired level of performance in terms of accuracy. This paper proposes a novel path loss model for 5G communications in suburban scenarios using deep learning with dilated convolution and attention. Dilated convolution is used to alleviate the locality of feature extraction and capture the global information on input images. Attention rendered by global context blocks helps the attention-enhanced convolutional neural network (AE-CNN) model utilize the global information on inputs to extract essential features of propagation environments. A distance-embedded local area multi-scanning algorithm which generates input images that can improve learning the latent features with dependency on distance is proposed. The experimental results indicate that the AE-CNN model can outperform state-of-the-art deterministic and empirical methods in terms of root mean square error in test scenarios.

show abstract

Section: B Cnn-based Path Loss Modelmentioning

confidence: 99%

Section: Ae-cnn Path Loss Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Millimeter Wave Path Loss Modeling for 5G Communications Using Deep Learning With Dilated Convolution and Attention

Chen

Lee

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…This article aims to develop a new path loss model at 28 GHz specifically tuned to fit Lagos Island's unique terrain comprising highrise buildings and highly clustered buildings.The objectives of this article are to: (i) Investigate the large-scale path loss effect of Lagos Island at 28 GHz mmWave considering five different scenarios. (ii) Develop a deterministic path loss model using a 3D ray-tracing technique to establish a generic path loss model at 28 Transmitter point 2 TX3…”

Section: Introductionmentioning

confidence: 99%

Deterministic 5G mmWave Large-Scale 3D Path Loss Model for Lagos Island, Nigeria

Hinga

Atayero

2021

IEEE Access

View full text Add to dashboard Cite

5G millimeter wave (mmWave) application in mobile connectivity to realize high-speed, reliable communication is attributed with high path loss. This paper presents a detailed 3D ray-tracing technique at 28 GHz for Lagos Island to investigate five unique path loss scenarios: path loss, free space path loss with antenna pattern, free space path loss without antenna pattern, excess path loss with antenna pattern, and the excess path loss without antenna pattern for an urban environment. The Close-In (CI) model, Floating Intercept (FI) path loss model, and a root mean square error (RMSE) are used to model and evaluate the best path loss model for Lagos Island. The average achieved FI (α ,β, σ) parameters were 189.92352, 0.1654, and 0.66948, While the average CI (η,Xσ) parameters were 2.309355 and 56.236425. From all the scenarios evaluated, the lowest path loss exponent achieved was 0.45, while the highest path loss exponent was 3.8. We have established that the FI path loss model accurately characterizes path loss for the Lagos Island environment with the lowest RMSE of 0.0359 dB and the highest RSME of 0.0997 dB. In contrast, the CI model over-predict the path loss at 28 GHz with the lowest RMSE of 0.0495 dB and the highest RMSE of 2.2547 dB. This work opens up a new area of research on mm-Wave at 28 GHz in Lagos Island, and the results obtained from this work can be used to benchmark future studies on mmWave in a similar environment.

show abstract

Optimizing radio access in 5G vehicle networks using novel machine learning-driven resource management

Natarajan,

Mahadev,

Alfurhood

et al. 2023

Opt Quant Electron

View full text Add to dashboard Cite

The huge crossover of vehicle network needs cannot be met by present cellular technologies and vehicular networks. To achieve desired results in a vehicle context, resource management has evolved into a complicated task. The 5G wireless network claims to provide communications that are ultra-fast, delayed less, and dependable. Software-defined networking (SDN) is one of the major technologies that will enable 5G. Additionally, it guarantees increased performance all around. Managing the increased mobility of vehicles and maintaining smooth transfer between base stations are the main concerns. Additionally, providing safety-critical applications like autonomous driving requires very low latency and great dependability. Due to the limited amount of spectrum available and the dynamic nature of vehicular communication, effective resource allocation strategies are required. To maintain network efficiency, interference, and channel congestion must be reduced, and priority techniques are required to meet the needs of various services. In this study, we proposed a traffic classification using Magnified Recurrent Neural Network (MRNN) and optimized the radio access in 5g vehicle networks using Boosting Ant Colony Optimization (BACO) for the resource allocation procedure. The BACO-MRNN algorithm produced the best results based on several performance metrics, including accuracy of 98.10%, precision of 97.23%, recall of 98.15%, F1-Score of 98.45%, and RMSE of 30.10%.Additionally, the BACO-MRNN classification revealed a very advanced capacity for discrimination. The entire potential of connected vehicles and the fulfillment of smart transportation systems depend on the effective resolution of radio access difficulties in 5G vehicle networks.

show abstract

CNN-Based mmWave Path Loss Modeling for Fixed Wireless Access in Suburban Scenarios

Cited by 34 publications

References 14 publications

Millimeter Wave Path Loss Modeling for 5G Communications Using Deep Learning With Dilated Convolution and Attention

Millimeter Wave Path Loss Modeling for 5G Communications Using Deep Learning With Dilated Convolution and Attention

Deterministic 5G mmWave Large-Scale 3D Path Loss Model for Lagos Island, Nigeria

Optimizing radio access in 5G vehicle networks using novel machine learning-driven resource management

Contact Info

Product

Resources

About