Novel Handover Algorithms Using Pattern Recognition for Hybrid LiFi Networks

Owing to the combination of high-speed data transmission and ubiquitous coverage, the hybrid light fidelity (LiFi) and wireless fidelity (WiFi) network (HLWNet) has been recently proposed as a promising scheme for the next generation indoor wireless network. The handover problem in the HLWNet, however, becomes critical, due to the small cell size of the LiFi access point and the line-of-sight propagation of the optical signal. To provide accurate and timely handover decisions for the HLWNet,
$w$
e regard the handover in HLWNet as a pattern recognition problem for the first time. In this paper, channel quality, optical channel blockage, user movement, and device orientation are characterized to model a practical simulation scenario. Two different pattern recognition techniques have been applied to design handover algorithms in the HLWNet. The simulation results show that the proposed handover algorithms are able to provide higher user throughput, lower handover rate, and better robustness performance as compared to benchmarks.