M. P. R, Sai Kiran

Network dependability and performance have improved significantly with advancements in 5G and wireless local area networks (WLANs). The utilization of the millimeter-wave (mmWave, above 30 GHz) frequency spectrum has facilitated increased data rates, enabling applications like virtual and augmented reality, tele-surgery, self-driving automobiles, etc. Standards like IEEE 802.11ad and 11ay, which operate around the 60 GHz band, utilize multiple-antenna-based high-gain directional beamforming to enhance coverage. However, periodic beam training methods are associated with increased power consumption of the smart phone or station (STA), thereby reducing the battery life and channel utilization. Frequent beam training of STAs can be avoided if the location of the STAs can be estimated accurately and at a low cost. This paper introduces a smart extended Kalman filter (EKF) based real-time distance estimation framework (SmartEKDF) using smartphone inertial sensors and GPS location. The proposed architecture comrprises of EKF and recurrent neural network (RNN) with long short-term memory (LSTM) layers to accurately estimate the real-time distance covered by an individual. The experiments show that the proposed method achieves an average accuracy of 98.84% and 99.43% when evaluated over travel distances of 100m and 400m, respectively. Also, the average inference time for one second of data is 2.02ms.

The next-generation wireless communication technologies, such as 5G Frequency Range 2 (FR2), WLANs, etc., are utilizing the millimeter-wave (mmWave) spectrum for increased data rates. For example, applications involving unmanned aerial vehicles (UAVs) for coverage extension in 5G comprise a huge amount of user data to be transmitted to the gNodeB (gNB). Hence, utilizing mmWave communication technologies such as 5G FR2 to establish the link between the UAV and gNB can be a suitable option. However, one of the critical technologies of 5G FR2 is the utilization of directional beamforming, and the impact of the axial unsteadiness of UAV s on the coverage needs to be carefully analyzed. This paper studies and models the effect of beam misalignment manifested due to axial disturbances in UAVs while hovering at a fixed altitude on the network performance. Firstly, a stochastic model for beam misalignment is developed by collecting real-time inertial data from a hovering UAV over multiple flights. Second, an analytical formulation of the coverage probability in a directional UAV to gNB mmWave communication link is formulated. The performance analysis shows that the analytical model matches the simulation outcomes with less than 2% error.

Next-generation communication technologies such as millimeter-wave wireless local area networks (mmWave WLANs) use multiple antenna-based directional beamforming where the location of the communicating entities plays a crucial role. Currently, the standards such as IEEE 802.11ad and 11ay employ beamforming training for the stations (STAs) and access points (APs) to estimate the sector or direction in which the communication is feasible and to establish the link successfully. However, frequent beam training increases power consumption and reduces channel utilization. Considering the location of AP is fixed, the frequent beam training of the STAs can be limited if the STAs can estimate the location accurately in real-time, which requires an accurate distance estimation framework. In this paper, we propose a novel Recurrent Neural Network (RNN) based architecture for accurately estimating the distance by the user using the smartphone IMU sensors. The proposed method combines signal processing techniques with RNNs leveraging the Long Short Term Memory (LSTM) layers to estimate the distance traveled by a person in real-time. Experimental analysis performed in different scenarios shows that the proposed method provides an average accuracy of 97.98% and 95.98% when tested over a travel distance of 100 m and 400 m, respectively.