Development of Handover Decision Algorithms in Hybrid Li-Fi and Wi-Fi Networks

Abstract

A handover decision algorithm in a hybrid Light Fidelity (Li-Fi) and Wireless Fidelity (Wi-Fi) network is investigated in this paper. Li-Fi, a wireless network uses visible light spectrum to provide high-speed indoor data transmission along with illumination. As there is no interference between optical and Radio Frequency (RF) spectrum operating devices, a hybrid Li-Fi/Wi-Fi network (HLWNet) can be explored in order to improve the user Quality of Service (QoS). However, in a HLWNet system setup, user mobility may often prompt frequent handover which as a result, degrades the system throughput. In this paper, we proposed a Fuzzy Logic (FL) and fuzzy rule-based Artificial Neural Network (ANN) handover decision algorithms. The FL based handover algorithm uses input parameters namely the instantaneous Signal to Interference Noise Ratio (SINR), Received Signal Strength (RSS), average SINR and user velocity to decide whether handover needs to be prompted. However, because of the increase in the number of the input parameters which, in turn, increases the number of fuzzy rules, the computational complexity greatly affects the FL system. Thus, it is envisioned that using the learning power of ANN, limited fuzzy rules are generated, which it can be made to learn from the limited rules and be able generalize to make handover decision. Based on the accuracy test conducted, the FL based handover decision algorithm is 1.66 times more accurate than the ANN fuzzy rule-based handover decision algorithm in terms of successfully assigning access points (AP) to users.