The diversity of users’ applications based on content delivery in indoor environments dramatically increased such that the conventional RF wireless networks might not be enough to support applications such as 4K video streaming and virtual reality. Visible light communication (VLC) has emerged recently as a complementary unlicensed media. In this paper, we propose a hybrid WiFi-VLC system consist of one WiFi access point (AP) and multiple VLC APs. Based on the requested data rate, users can be assigned to WiFi or VLC AP in downlink such as to maximize the fairness among all connected users. We propose a reinforcement learning algorithm that can be implemented at the WiFi AP and help with assigning the users to a specific AP based on their requested data rate. We propose a new reward function that improves the satisfaction of all connected users. Numerical simulation results show that the proposed method improved the user satisfaction based on Jain’s fairness index.
Reinforcement Learning Approach for Content-Aware Resource Allocation in Hybrid WiFi-VLC Networks
01.04.2021
1859877 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch