Model-Free QoE-Aware Seamless Handoff in Heterogeneous Wireless Networks

Abstract

Next-generation wireless networks (NGWN) consist of the integration of various technologies, such as Mobile ad-hoc networks (MANET), Wi-Fi, WiMAX, and LTE which are connected to the internet. Switching off the nodes among networks with same or different technology is handled by mobile IP. The determination of hand-off is not solely reliant on received signal strength, as relying solely on this metric could result in unnecessary hand-offs. Various factors, such as power consumption in communication, delay, traffic load, and network bandwidth, also play crucial roles in ensuring successful transmission. This paper introduces a seamless hand-off technique based on Markov processes (S-MSH), which takes into account different network properties that impact the Quality of Experience (QoE) for mobile terminals (MT) during communication. The proposed approach focuses on creating a Markov Decision Process (MDP) model for the system, considering user traffic requirements. The Q-learning algorithm is applied to the model to predict whether a hand-off is beneficial. An integrated similarity index-based approach, termed S-MSH, has been introduced to expedite the convergence rate of MSH. Simulation and numerical results demonstrate that the proposed approach surpasses the performance of the Network Priority Multicriteria Vertical Handover Decision Algorithm (NPMH) and the Simple Additive Weighing Algorithm (SAW) in terms of total reward and the number of handoffs.