Channel prediction based on adaptive structure extreme learning machine for UAV mmWave communications

In unmanned aerial vehicle (UAV) millimeter wave (mmWave) communications, the inter-UAV wireless channel is fast varying because the high mobility of the UAV transmission platform. In such dynamic scenarios, it is very costly to obtain the inter-UAV channel state information (CSI) with the conventional pilot-aided channel estimation. Aiming to address this critical issue, in this paper, we propose a novel adaptive-structure extreme learning machine (ASELM) enabled fast channel predication to obtain the CSI in a proactive fashion, which can further support agile beam-based inter-UAV mmWave communication. In particular, ASELM copes with the channel variations by adaptively adjusting the number of neurons in the hidden-layer of ELM. Moreover, a sliding window prediction mechanism (SWPM) predicts subsequent-CSI by efficiently reuses the predicted concurrent-CSI to train the ASELM, which is able to save the pilot overhead for channel sampling (estimation) towards longer-range channel prediction and improve prediction accuracy at affordable costs. Simulation results show that the proposed ASELM enabled fast channel predication can achieve lower normalized mean square error than traditional prediction algorithm in the considered inter-UAV mmWave communication scenarios.