Location Based Social Networks (LBSNs) have recently emerged as a hot research area. However, the high mobility of LBSN users and the need to quickly provide access points in their interest zones present a unique research challenge. In order to address this challenge, in this paper, we consider the Unmanned Aerial Vehicles (UAVs) to be a viable candidate to promptly form a wireless, meshed offloading backbone to support the LBSN data sensing and relevant data computations in the LBSN cloud. In the considered network, UAV-mounted cloudlets are assumed to carry out adaptive recommendation in a distributed manner so as to reduce computing and traffic load. Furthermore, the computational complexity and communication overhead of our proposed adaptive recommendation are analyzed. The effectiveness of the proposed recommendation system in the considered LBSN is evaluated through computer-based simulations. Simulation results demonstrate that our proposal achieves much improved performance compared to conventional methods in terms of accuracy, throughput, and delay.

中文翻译：

---

一种用于LBSN的新型自适应UAV-Mounted Cloudlet辅助推荐系统

基于位置的社交网络（LBSN）最近成为一个热门的研究领域。然而，LBSN 用户的高移动性以及在他们感兴趣的区域内快速提供接入点的需求带来了独特的研究挑战。为了应对这一挑战，在本文中，我们认为无人驾驶飞行器 (UAV) 是快速形成无线网状卸载骨干网的可行候选者，以支持 LBSN 数据传感和 LBSN 云中的相关数据计算。在所考虑的网络中，假设安装在无人机上的小云以分布式方式进行自适应推荐，以减少计算和流量负载。此外，分析了我们提出的自适应推荐的计算复杂性和通信开销。通过基于计算机的模拟评估所提出的推荐系统在所考虑的 LBSN 中的有效性。仿真结果表明，与传统方法相比，我们的建议在准确性、吞吐量和延迟方面实现了大大提高的性能。