Optimal Channel Selection in Hybrid RF/VLC Networks: A Multi-Armed Bandit Approach
Optimal Channel Selection in Hybrid RF/VLC Networks: A Multi-Armed Bandit Approach
复制标题
DOI：
10.1109/tvt.2022.3163078
复制
发表时间：
2022-06
影响因子：
6.8
通讯作者：
M. Fouda;S. Hashima;S. Sakib;Z. Fadlullah;Kohei Hatano;X. Shen
中科院分区：
文献类型：
--
作者：
M. Fouda;S. Hashima;S. Sakib;Z. Fadlullah;Kohei Hatano;X. Shen
我们研究了混合射频和可见光通信（RF/VLC）网络的最佳频带/信道选择。特别是，我们首先开发了一个鲁棒的基于混合射频/VLC的系统模型，用于最佳的频带/信道选择。然后，我们将其表述为一个在线随机预算约束多臂强盗（MAB）问题。提出了两种基于不同最优策略的在线学习算法，即能量感知带上置信度选择带（EABS-UCB）和能量感知带汤普森采样选择带（EABS-TS）。成本/预算是根据所选频段发射设备的电池消耗。通过大量的仿真，证实了所提出的EABS-TS在能量效率、平均吞吐量和收敛性能方面优于随机、蛮力和EABS-UCB频段选择方案。
We investigate optimal band/channel selection in hybrid radio frequency and visible light communication (RF/VLC) networks. Particularly, we first develop a robust hybrid RF/VLC based system model for the optimal band/channel selection. We then formulate it as an online stochastic budget-constrained multi-armed bandit (MAB) problem. Two online learning algorithms based on different optimal policies are proposed to choose the appropriate band, i.e., energy-aware band selection with upper confidence bound (EABS-UCB) and energy-aware band selection with Thompson sampling (EABS-TS). The cost/budget is the battery consumption of the transmitting device according to the selected band. Through extensive simulations, it is confirmed that the proposed EABS-TS emerges as the superior technique compared with the random, brute-force, and EABS-UCB band selection schemes, in terms of energy efficiency, average throughput, and convergence performance.