Deep Learning Aided Friendly Coexistence of WiFi and LTE in Unlicensed Bands

Abstract

Unlicensed long term evolution (LTE) technology is considered one of promising solutions to address the problem of limited spectrum resources with the booming of big data and internet of things (IoT). However, the unlicensed band is rich resource, which is mainly occupied by wireless fidelity (WiFi). The biggest challenge for the unlicensed LTE technology is how to friendly coexistent with WiFi. Many Researchers in academia and industry have proposed various solutions to deal with this problem. For example, the mLTE-U scheme needs dynamic environmental information to keep it running. In this paper, we propose a classification method based on convolutional neural networks (CNN) algorithm in order to distinguish unlicensed LTE and WiFi. We collect the real data about unlicensed LTE and WiFi. Simulation results show that the identification of two incumbent technology performs well under high signal-to-noise ratios (SNRs).