Deep Learning Based Proactive Optimization for Mobile LiFi Systems with Channel Aging

TL;DR

This paper proposes a proactive optimization method using LSTM networks to predict user positions and channels in mobile LiFi systems, effectively addressing channel aging and enabling real-time, near-optimal transmission schemes.

Contribution

It introduces a novel LSTM-based proactive approach to predict mobile user channels in LiFi systems, reducing delays caused by traditional iterative optimization methods.

Findings

LSTM model accurately predicts user positions and orientations.

Proactive optimization improves real-time transmission scheme performance.

Simulation results show reduced processing delay and enhanced system efficiency.

Abstract

This paper investigates the channel aging problem of mobile light-fidelity (LiFi) systems. In the LiFi physical layer, the majority of the optimization problems for mobile users are non-convex and require the use of dual decomposition or heuristics techniques. Such techniques are based on iterative algorithms, and often, cause a high processing delay at the physical layer. Hence, the obtained solutions are no longer optimal since the LiFi channels are evolving. In this paper, a proactive-optimization (PO) approach that can alleviate the LiFi channel aging problem is proposed. The core idea is to design a long-short-term-memory (LSTM) network that is capable of predicting posterior positions and orientations of mobile users, which can be then used to predict their channel coefficients. Consequently, the obtained channel coefficients can be exploited to derive near-optimal transmission-schemes prior to the intended service-time, which enables real-time service. Through various simulations, the performance of the designed LSTM model is evaluated in terms of prediction error and time, as well as its application in a practical LiFi optimization problem.