GA-GRU-at-Based Channel Estimation Scheme for IEEE 802.11p Standard
Xiaojuan Bai, Yunqing Li, Fang Fang, Xianbin Wang, Aopei Yu · IEEE Communications Letters · 2025
Channel estimation in the IEEE 802.11p standard is particularly challenging because of its time and frequency selectivity, making it difficult for current channel estimation schemes to accurately track the channel, especially in high mobility scenarios. This letter proposes a deep learning-based channel estimation scheme using the GA-GRU-AT model. The scheme employs gated recurrent unit (GRU) optimized by genetic algorithm (GA) to more accurately extract time and frequency domain features of the channel, and incorporates adaptive time (AT) processing to further suppress noise propagation. Simulation results show that this scheme outperforms existing deep learning-based channel estimation schemes for the IEEE 802.11p standard under various modulation schemes and high mobility channel conditions.