Technology recognition and traffic characterization for wireless technologies in ITS band

Abstract

The rapid advancement of wireless technologies requires efficient spectrum management considering issues such as interference management and fair coexistence between different technologies. Wireless technology recognition is one of the approaches used to enable intelligent spectrum management. This work proposes a technology classification and traffic characterization system that can recognize and characterize a wide range of wireless technologies that may coexist in the ITS 5.9 GHz band, namely LTE, Wi-Fi, 5G NR, C-V2X PC5, and ITS-G5 technologies. Compared to current state-of-the-art technology recognition solutions, a short time resolution window is selected based on the shortest possible frame duration of the considered technologies. We carried out a “complexity and accuracy trade-off” analysis for six distinct technology recognition models trained and validated at different sampling rates, including 1, 5, 10, 15, 20, and 25 Msps. In addition, the performance of the technology recognition models was evaluated under different channel conditions. For average to high SNR, a less complex CNN model with lower sampling rates (e.g., 5 Msps) can effectively distinguish the signal with 96% classification accuracy. On the other hand, high classification accuracy is obtained using complex, high sampling rate-based CNN models (e.g., 20 Msps) for low (less than 0 dB) SNR channels. A traffic characterization process is also proposed, where the output of the technology recognition is used to identify the traffic characteristics of the technologies in terms of channel occupancy time, transmission pattern, and frame count. The obtained results show that the proposed solution can be used to effectively characterize the identified traffic.