A Novel Distance Tracking Framework for Estimating User Position in MmWave WLANs

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.