ABSTRACT
The unique features of millimeter waves (mmWaves) motivate its leveraging to future, beyond-fifth-generation/sixth-generation (B5G/6G)-based device-to-device (D2D) communications. However, the neighborhood discovery and selection (NDS) problem still needs intelligent solutions due to the trade-off of investigating adjacent devices for the optimum device choice against the crucial beamform training (BT) overhead. In this paper, by making use of multiband (µW/mmWave) standard devices, the mmWave NDS problem is addressed using machine-learning-based contextual multi-armed bandit (CMAB) algorithms. This is done by leveraging the context information of Wi-Fi signal characteristics, i.e., received signal strength (RSS), mean, and variance, to further improve the NDS method. In this setup, the transmitting device acts as the player, the arms are the candidate mmWave D2D links between that device and its neighbors, while the reward is the average throughput. We examine the NDS's primary trade-off and the impacts of the contextual information on the total performance. Furthermore, modified energy-aware linear upper confidence bound (EA-LinUCB) and contextual Thomson sampling (EA-CTS) algorithms are proposed to handle the problem through reflecting the nearby devices' withstanding battery levels, which simulate real scenarios. Simulation results ensure the superior efficiency of the proposed algorithms over the single band (mmWave) energy-aware noncontextual MAB algorithms (EA-UCB and EA-TS) and traditional schemes regarding energy efficiency and average throughput with a reasonable convergence rate.
ABSTRACT
In this paper, we introduce the idea of using adaptive hybrid modulation techniques to overcome channel fading effects on visible light communication (VLC) systems. A hybrid $ M $M-ary quadrature-amplitude modulation ($ M{\rm QAM} $MQAM) and multipulse pulse-position modulation (MPPM) technique is considered due to its ability to make gradual changes in spectral efficiency to cope with channel effects. First, the Zemax optics studio simulator is used to simulate dynamic VLC channels. The results of Zemax show that Nakagami and log-normal distributions give the best fitting for simulation results. The performance of $ M{\rm QAM} $MQAM-MPPM is analytically investigated for both Nakagami and log-normal channels, where we obtain closed-form expressions for the average bit-error rate (BER). The optimization problem of evaluating the hybrid modulation technique settings that lead to the highest spectral efficiency under a specific channel status and constraint of outage probability is formulated and solved using an exhaustive search. Our results reveal that the adaptive hybrid scheme improves system spectral efficiency compared to ordinary QAM and MPPM schemes. Our results reveal that the adaptive hybrid scheme improves system spectral efficiency compared to ordinary QAM and MPPM schemes. Specifically, at low average transmitted power, $ - 32\;{\rm dBm} $-32dBm, the adaptive hybrid scheme shows 280% improvement in spectral efficiency compared to adaptive versions of ordinary schemes. At higher power, $ - 20\;{\rm dBm} $-20dBm, 6.5% and 725% improvement are obtained compared to ordinary QAM and ordinary MPPM, respectively. Also, the adaptive hybrid scheme shows great improvement in average BER and outage probability compared to ordinary schemes. The hybrid scheme shows 28%, 34%, and 38% improvement, respectively, for $ m = 1,2,3 $m=1,2,3 for Nakagami channels at $ {\rm BER}{ = 10^{ - 3}} $BER=10-3. Also, the outage probability of hybrid schemes of $ {\rm BER}{ = 10^{ - 3}} $BER=10-3 shows 30% and 14% better performance than ordinary $ M{\rm QAM} $MQAM and MPPM schemes, respectively.
