A New Vision-Aided Beam Prediction Scheme for mmWave Wireless Communications

Ying, Ziqiang; Yang, Haojun; Gao, Jia; Zheng, Kan

doi:10.1109/iccc51575.2020.9344988

Cited by 8 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, vision-aided wireless communication (VAWC) has received much attention as a key enabling technology in realizing 6G-enabled SSC due to its capability to manipulate beamforming using visual and radio information collected by cameras in mmWave and THz bands [101], as shown in Figure 5. VAWC uses machine learning techniques to analyze the data collected by cameras.…”

Section: Vision-aided Wireless Communicationmentioning

confidence: 99%

“…• Maximizing beamforming gain: Unlike conventional codebook-based beam management, VAWC can effectively improve the beamforming accuracy by using the UE's angle information obtained via RGB images at base stations. In [101], it is shown that the orientation error of DL-based object detection is below 0.5 degrees, which can be used to maximize the beamforming gain using VAWC. Moreover, with the advancement of sensing technologies, positioning errors are expected to be further reduced in higher frequency bands.…”

Section: Selection Of Deep Learning Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Key Technologies for 6G-Enabled Smart Sustainable City

Kim,

Shim

et al. 2024

Electronics

View full text Add to dashboard Cite

With the advancement of information and communication technologies (ICTs), the way we live and communicate with each other is changing rapidly. As urban environments continue to evolve, the smart sustainable city (SSC) has sparked considerable attention. We are hoping for a new era in which numerous devices and machines including vehicles, sensors, and robots are all connected to communicate, respond, and operate in real time. The next-generation communication system, the sixth generation (6G), is expected to play a crucial role in improving the efficiency of urban operations and services. In this paper, we first provide the recent trends and key features of standardization in the SSC. To make the future SSC, we highlight key candidate technologies of 6G such as non-terrestrial networks, advanced mobile edge computing, vision-aided wireless communication, artificial intelligence (AI)-based wireless communication, and integrated sensing and communication. We put forth the main technical challenges given to each prime technology along with the potential benefits to pave the way for 6G-enabled SSC. We further address how the potential benefits of prime technologies enable various urban practice cases for 6G-enabled SSC.

show abstract

Section: Vision-aided Wireless Communicationmentioning

confidence: 99%

Section: Selection Of Deep Learning Techniquesmentioning

confidence: 99%

Key Technologies for 6G-Enabled Smart Sustainable City

Kim,

Shim

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Alrabieh et al [22] proposed learning mapping functions and predicting the optimal beam and blockages directly from the sub-6 GHz channel. Ying et al [23] used object recognition to locate users based on the RGB images captured by the cameras. Then they used a multilayer perceptron to predict the angles between the users and the cameras.…”

Section: Related Workmentioning

confidence: 99%

A Stacked Autoencoder and Multilayer Perceptrons for mmWave Beamforming Prediction

Mettiti¹,

Oumsis²

2022

ISI

View full text Add to dashboard Cite

The millimeter-wave frequencies planned for 6G systems present challenges for channel modeling. At these frequencies, surface roughness affects wave propagation and causes severe attenuation of millimeter-wave (mmWave) signals. In general, beamforming techniques compensate for this problem. Analog beamforming has some major advantages over its counterpart, digital beamforming, because it uses low-cost phase shifters for massive MIMO systems compared to digital beamforming that provides more accurate and faster results in determining user signals. However, digital beamforming suffers from high complexity and expensive design, making it unsuitable for mmWave systems. The techniques proposed so far for analog beamforming are often challenging in practice. In this work, we have proposed a deep learning model for analog beams training that helps predict the optimal beam vector. Our model uses an available dataset of 18 base stations, over 1 million users, 60 GHz frequency. The training process first applies a stacked autoencoder to extract the features from the training datasets, and then uses a multilayer perceptron (MLP) to train and predict the optimal beams. Then, the results are evaluated by computing the mean squared error between the expected and predicted beams using the test set. The results show high efficiency compared to the benchmark method, which uses only the MLP for the training process.

show abstract

“…The use of camera images as side information for the beam and blockage prediction is discussed in [10]. In [11] the optimal beams are predicted adopting object detection from camera images to locate the positions of the users. Then an angle prediction model has been used to estimate the angles between the users and the cameras which is finally used for beam selection from a predefined code book.…”

Section: Previous Workmentioning

confidence: 99%

LiDAR aided Wireless Networks - Beam Prediction for 5G

Marasinghe

Jayaweera

Rajatheva

et al. 2022

2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)

View full text Add to dashboard Cite

5G New Radio (NR) mmWave operates with narrow beams. Beam-based connections require careful management of beams to ensure a reliable connection, specially when the user has mobility. 5G NR beam management achieve this, at the expense of periodic reporting with increased overheads and resource usage. Concurrently, recent interest in sensing for assisting wireless systems provides an opportunity to extract situational awareness information which can aid in proactive decisions for the network. In this work, we utilize an infrastructure-mounted light detection and ranging (LiDAR) sensor system simultaneously operating with the wireless system to predict future beam decisions. A recurrent neural network (RNN) based learning model is proposed for the beam prediction, employing tracking information of users facilitated by the LiDARs and beam sequence information from the wireless system. Furthermore, a method for predictive beam management with increased periodicity of the reporting mechanism and aperiodic reporting is analyzed. The results for the considered scenario reveal 86.8% of the resources can be saved compared to the conventional beam reporting procedure, while achieving an 88.7% accuracy for optimal beam decisions.

show abstract

A New Vision-Aided Beam Prediction Scheme for mmWave Wireless Communications

Cited by 8 publications

References 11 publications

Key Technologies for 6G-Enabled Smart Sustainable City

Key Technologies for 6G-Enabled Smart Sustainable City

A Stacked Autoencoder and Multilayer Perceptrons for mmWave Beamforming Prediction

LiDAR aided Wireless Networks - Beam Prediction for 5G

Contact Info

Product

Resources

About