Blind LTE-U/WiFi Coexistence System Using Convolutional Neural Network

Abstract

With the rapid development of wireless communications technology, long term evolution (LTE) technology in unlicensed bands (LTE-U) can effectively solve the lack of spectrum resources. However, the competition in LTE-U and wireless fidelity (WiFi) will seriously interfere their communication quality, which making the friendly coexistence of LTE-U and WiFi becomes a hot research area. In this paper, we propose a classification algorithm based on deep learning to realize the identification of LTE-U and WiFi signal. Experiment results use mixed data at different signal to noise ratios (SNRs) and compare the classification results within two data forms. Experimental results show that our proposed deep learning-aided method can effectively distinguish LTE-U and WiFi signals and further achieve their friendly coexistence.

Keywords

• Automatic LTE-U
• WiFi
• in-phase and quadrature
• deep learning
• unlicensed band