Adaptive CNN-based Private LTE Solution for Fair Coexistence with Wi-Fi in Unlicensed Spectrum

Abstract

Recently, the expansion of wireless network deployments is resulting in increased scarcity of available licensed radio spectrum. As the domain of wireless communications is progressing rapidly, many industries are looking into wireless network solutions that can increase their productivity. Private LTE is a promising wireless network solution as it can be customised independently without the control of a mobile network operator while providing reliable and spectrum efficient services. For this reason, the deployment of Private LTE in the unlicensed spectrum and its coexistence with Wi-Fi is becoming a popular topic in research. In this paper, we propose a coexistence scheme for private LTE network in unlicensed spectrum that enables a fair spectrum sharing with co-located Wi-Fi networks. This is achieved by exploiting various LTE frame configurations consisting of different combinations of downlink, uplink, special subframe and muted subframes. The configuration of a single frame is decided based on a rule based algorithm that exploits Wi-Fi spectrum occupancy statistics that is obtained from a technology recognition system which is based on a Convolutional Neural Network. The performance of the proposed private LTE scheme and its coexistence with Wi-Fi is investigated for different traffic scenarios showcasing how the proposed scheme can lead to a harmless coexistence of LTE and Wi-Fi.

Technology recognition and traffic characterization for wireless technologies in ITS band

“…Blank subframes were introduced in some of the LTE frames to represent a varying spectrum utilization. The blank subframes are introduced by modifying the srsRAN source code based on our previous work in [40]. For the LTE dataset collection, the FDD mode with a 10 MHz bandwidth and a 5.9 GHz center frequency is used for the downlink traffic.…”

Coexistence Scheme for Uncoordinated LTE and WiFi Networks Using Experience Replay Based Q-Learning

“…Similarly, CNN based models are used to perform identification of WiFi transmissions from other co-located transmissions of other technologies in [27,28]. Our CNN based technology classification proposed in [26] is used to implement coexistence schemes between private LTE and WiFi in [29,30]. These coexistence schemes use Channel Occupancy Time (COT) to estimate the WiFi traffic and select optimal transmission time of LTE and WiFi.…”

“…The algorithm uses possible states of LTE shown in Table 2. When blank subframes are introduced in the LTE frame, the LTE throughput decreases proportionally [30]. Hence, the 10 states in Table 2 are used to represent all the possible range of throughput levels.…”

Reseña del servicio de radio de banda ancha ciudadana

“…LTE privado es empleado en empresas para la conectividad de dispositivos de Internet Industrial de las Cosas (IIoT, Industrial Internet of Things) o dispositivos móviles de trabajadores para el funcionamiento de aplicaciones IIoT en ambientes más amplios [26].…”