LAUSR

Mobile edge computing (MEC) offers a promising approach for providing computation and storage services to user terminals (UTs). However, the computational resources deployed on the base stations or fixed locations are insufficient for temporary emergency scenarios. To expand MEC capacity, an air-ground cooperation architecture that leverages the low cost, rapid deployment, and mobility of low-altitude platform is proposed. A joint optimization strategy for air-ground cooperation caching and content delivery is introduced to reduce delays caused by limited wireless backhaul capacity, energy constraints of edge nodes in air (ENAs), and repeated content delivery. This strategy incorporates trajectory planning of UAVs, transmission power allocation, downlink bandwidth allocation, content caching, and user association. Content popularity is predicted using an LSTM network based on historical data. We employ the block coordinate descent (BCD) method to address the optimization problem and design the popularity prediction-based air-ground cooperation caching and content delivery (PP-AG3C) algorithm. Numerical simulations show that our algorithm outperforms benchmark algorithms in average delivery delay, data transmission energy, and cache hit rate. When the number of UTs is 60, compared with PP-AG3C algorithm, The average data transmission energy consumption of TPCU-AG3C algorithm, TCU-AG3C algorithm, TC-AG3C algorithm, RT-AG3C algorithm and FT-AG3C algorithm increased by 30.79%, 49.41%, 76.70%, 152.85%, and 51%, respectively.