Federated Learning in UAV-Assisted MEC Systems: A Comprehensive Survey

In recent years, the integration of Uncrewed Aerial Vehicles (UAVs) into Multi-Access Edge Computing (MEC) systems has emerged as a transformative paradigm revolutionizing the landscape of data processing and analysis. By leveraging UAVs as MEC platforms, computing and storage capabilities are extended closer to data sources, thus facilitating real-time data processing and enabling smooth decision-making. This synergy between UAVs and MEC not only enhances the efficiency of data-intensive applications but also unlocks new possibilities for innovative services across various domains such as environmental monitoring, urban planning, and emergency response. The escalating demand to harness big data for several applications, empowered by Artificial Intelligence (AI), heralds a new era of ubiquitous data-driven intelligent services. Traditionally, Machine Learning (ML) approaches involve aggregating datasets and training models centrally, which poses several security risks. Alternatively, Federated Learning (FL), as a decentralized ML method, enables users to collaboratively train their ML models without compromising the privacy of their data. This paper comprehensively overviews UAV-assisted MEC systems, which rely on ML for several services, by shedding light on the vast opportunities it presents and discussing how to tackle its related key challenges. Subsequently, we provide an in-depth survey of the fundamentals and enabling technologies of FL, a pioneering technique poised to democratize ML at the edge of wireless networks such as those supported by UAVs. Also, we conduct an extensive analysis to identify the various applications of FL in UAV-assisted MEC systems, along with a nuanced examination of their associated challenges and limitations. Finally, we discuss some of the most important future research directions.