Abstract : Incorporating unmanned aerial vehicle as a flying base stations (UAV-BSs) within the open radio access network (Open-RAN) framework presents a transformative shift in unmanned aerial vehicle (UAV)-assisted networks, enhancing network coverage for ground devices while improving adaptability to dynamic scenarios. In this context, it is important to design an intelligent proactive UAV-BS positioning approach, which might consider ML algorithms to predict user movement and Quality of Service to improve the network operation. In this article, we introduce PURSUIT, an artificial intelligence (AI)-driven proactive positioning approach to manage UAV-BS position to improve the QoS of ground users. The key contributions include a user equipment (UE) mobility prediction model using the Kalman filter to estimate UE positions, a proactive UAV-BS deployment method employing Weighted K-Means and Hungarian algorithms for optimal positioning, and a quality of service (QoS)-aware estimation model using neural networks to optimize UAV-BS placement based on UE application demands and network conditions. We conducted simulations using the ns3-ORAN module and SUMO with realistic mobility traces to evaluate the performance of PURSUIT. Simulation results demonstrate that PURSUIT achieves a 30% reduction in delay compared to state-of-the-art reactive solutions, with specific improvements of 23% over Kalman Filter-only prediction, and 36% over a no-prediction approach. Furthermore, PURSUIT enhances packet delivery ratio (PDR) by over 5% across prediction strategies and up to 10% compared to reactive methods, alongside a 16% throughput improvement over Kalman Filter-only and 9% over no-prediction approaches.
Index terms : 5G, Open-RAN, UAV-assisted networks, UAV-BS positioning