Deep Learning for Selection Between RF and VLC Bands in Device-to-Device Communication

Najla, Mehyar; Mach, Pavel; Bečvář, Zdeněk

doi:10.1109/lwc.2020.3003786

Cited by 23 publications

(13 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the coverage boundary of the D2D communication range forms a cluster of equal ROI points in (9). Using these points, the mobility management parameters can be derived for an industrial LiFi network.…”

Section: Analytical Model In Moving Iiotmentioning

confidence: 99%

“…In the game, the data packet size, the price of licensed spectrum and data rates are determined with equilibrium solutions, and each VLC transmitter (VLCT) determines the optimal data transmission route. Najla et al focus on a multiobjective optimization problem which is the selection between RF and VLC bands for D2D [8], [9]. In these studies, they propose low-complexity heuristic algorithm and deep neural network for solving the problem.…”

Section: Introductionmentioning

confidence: 99%

“…None of them consider the crucial impact of device mobility properly. In [6]- [9], [13], there is no explanation about user movements and assume that device positions are fixed. At least, in [10], [11], it is said that this is initial work in this field, they do not consider the mobility of the users and they leave these aspects for further research.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LiFi-Based D2D Communication in Industrial IoT

Ozyurt

Popoola

2023

IEEE Systems Journal

View full text Add to dashboard Cite

This paper analyses the performance of LiFi-based device-to-device (D2D) communication in industrial internetof-things (IIoT). We present a comprehensive analysis of mobility management of D2D communication in industrial LiFi networks. Using the semiangle at half illuminance of the AP and D2D transmitting IIoT, a coverage model for the D2D communication range is derived. By adopting stochastic geometry, closed-form expressions for mode selection rate and residence time are derived as functions of the AP density, IIoT density, and velocity. The results have shown that high velocity and denser deployment cause a decrease in the average D2D residence time and an increase in the average D2D transition rate or vice versa. The proposed analytical models are then verified with Monte Carlo simulation results. The results provide system-level design insights.

show abstract

Section: Analytical Model In Moving Iiotmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LiFi-Based D2D Communication in Industrial IoT

Ozyurt

Popoola

2023

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…In the game, the data packet size, the price of licensed spectrum and data rates are determined with equilibrium solutions, and each VLC transmitter (VLCT) determines the optimal data transmission route. Najla et al focus on a multi-objective optimization problem which is the selection between RF and VLC bands for D2D [11], [12]. In these studies, they propose low-complexity heuristic algorithm and deep neural network for solving the problem.…”

Section: Introductionmentioning

confidence: 99%

CoMP-JT Scheme for D2D Communication in Industrial LiFi Networks

Ozyurt

Poppola

2022

IEEE Access

View full text Add to dashboard Cite

This paper focuses on the combined technique of device-to-device (D2D) and coordinated multipoint joint transmission (CoMP-JT) to bridge the indoor industrial wireless gap with LiFi-based networks. It also considers the mobility challange of industrial internet-of-things (IIoT) within a realistic scenario. Using the semiangle at half illuminance of the LiFi access point and D2D transmitting IIoT, we derive a coverage model for the communication range. Using stochastic geometry, the analytical expressions for CoMP-JT probability and coverage performance are derived in terms of different parameters, such as transmitter densities and bias factor. The analytical approximations match quite well with the Monte Carlo method-based simulation results. INDEX TERMS Coordinated multipoint joint transmission, device-to-device communication, industrial internet-of-things, LiFi, visible light communication.

show abstract

“…Shao et al [13] proposed a self-optimization algorithm based on Q-learning, where the switching parameters of the APs were optimized by a centralized coordinator. In addition, other AI algorithms have also been used in VLC handover mechanisms; for example, Ji et al [14] used a support vector machine (SVM) approach and Najla et al [15] used a deep neural network (DNN) approach to propose algorithms that effectively improve the network switching performance in VLC-and RF-based heterogeneous networks. However, the performance of the RL algorithms adopted in the above studies is significantly reduced by the restrictions on the Qtable in a large-scale indoor scene with an ultradense deployment of VLC APs.…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning-Based Adaptive Handover Mechanism for VLC in a Hybrid 6G Network Architecture

et al. 2021

View full text Add to dashboard Cite

Visible light communication (VLC) is considered an important complementary technology for extremely high sixth-generation (6G) data transmission and has become part of a hybrid 6G indoor network architecture with an ultradense deployment of VLC access points (APs) that presents severe challenges to user mobility. An adaptive handover mechanism, which includes a seamless handover protocol and a selection algorithm optimized with a deep reinforcement learning (DRL) method, is proposed to overcome these challenges. Experimental simulation results reveal that the average downlink data rate with the proposed algorithm is up to 48% better than those with traditional RL algorithms and that this algorithm also outperforms the deep Q-network (DQN), Sarsa and Q-learning algorithms by 8%, 13% and 13%, respectively. INDEX TERMS 6G, visible light communication (VLC), handover, deep reinforcement learning (DRL).

show abstract

Deep Learning for Selection Between RF and VLC Bands in Device-to-Device Communication

Cited by 23 publications

References 16 publications

LiFi-Based D2D Communication in Industrial IoT

LiFi-Based D2D Communication in Industrial IoT

CoMP-JT Scheme for D2D Communication in Industrial LiFi Networks

Deep Reinforcement Learning-Based Adaptive Handover Mechanism for VLC in a Hybrid 6G Network Architecture

Contact Info

Product

Resources

About