High-speed AAV-assisted OTFS-enabled Intelligent Data Collection in Large-scale Wireless Sensor Networks

Sixth-generation (6G) communication emphasizes the deep integration of sensing, communication, and computing to support intelligent and rapid-response networks. Autonomous aerial vehicles (AAVs), known for their superior flexibility, terrain adaptability, and low deployment costs, are promising candidates for data collection in large-scale wireless sensor networks (WSNs). However, many existing AAVs-assisted data collection studies assume that AAVs operate at relatively low speeds and incorporate hovering time during data collection. In such scenarios, the AAVs inevitably require longer flying durations and consume much energy. Additionally, they often neglect the impact of the Doppler effect during the data collection. In most general and realistic scenarios, AAVs typically fly at high speeds without the need to hover, and the Doppler effect highly impacts the communication between sensor nodes (SNs) and AAVs. To address this, we propose a data collection framework that leverages orthogonal time frequency space (OTFS) modulation and non-orthogonal multiple access (NOMA) to mitigate the Doppler-induced interference in the up-link. We formulate an AAV-assisted data collection efficiency maximization problem by jointly considering AAV energy consumption, and the SNs’ uploading rates and bit error rates (BERs). Given the NP-hard nature of this problem, we design a three-step solution: the first two steps employ heuristic algorithms and the third step integrates a bi-directional long short-term memory (BiLSTM) for intelligent AAV symbol detection. Simulation results validate the superiority of our proposed solution.