Open-RAN based proactive positioning approach to enhance UAV-assisted mobile networks

Incorporating unmanned aerial vehicles as flying base stations (UAV-BSs) within the open radio access network (Open-RAN) framework presents a transformative shift in augmenting unmanned aerial vehicle (UAV)-assisted networks. This integration synergy facilitates the network coverage of remote devices, improves the adaptability to dynamic scenarios, and the intelligence of network deployments, proving especially important in scenarios, such as search and rescue missions, live tracking, and the provisioning of mobile services, where conventional infrastructure may be overwhelmed or only partially functional. The open and programmable attributes of Open-RAN enable extensible applications (*Apps) running on the near-real time RAN intelligent controller (NR-time RIC) to dynamically adjust the placement of UAV-BSs, guided by the predicted user equipment (UE) locations, the demands of UE data, and prevailing network conditions. We introduce an artificial intelligence (AI)-driven orchestration mechanism using the Open-RAN architecture to manage the UAV-BS communication resources, through a short-term prediction of the UEs mobility patterns, their requirements, and the operational limits of the UAVs. Additionally, the proposed integration of UAV units equipped with multiple-access edge computing (MEC) functionalities facilitates the prompt data processing, mitigating the challenges presented by the UEs mobility and the variability of wireless connections. This comprehensive UAV-BS-Open-RAN provides a framework for the future of mobile networks, enhanced by our machine learning (ML) solution, with an improvement of more than 30% in delay when compared to the state-of-the-art solution, accompanied by an improvement in both packet delivery ratio (PDR) and throughput.