Dominic Schupke

Aygun Baltaci, Irshad A. Meer, Mustafa Ozger et al.

Future uncrewed aerial vehicle (UAV) systems increasingly combine heterogeneous communication technologies, such as low-latency aerial mesh, terrestrial cellular, and satellite links, to improve robustness and coverage. Multipath transport is a natural mechanism for aggregating these links, yet its ability to support real-time UAV services in highly heterogeneous environments remains insufficiently characterized. We present a measurement-driven study based on UAV flight experiments in an integrated network comprising UAV-to-UAV aerial mesh, private cellular, and low Earth orbit (LEO) satellite connectivity. Using Multipath TCP (MPTCP) as a representative lossless, in-order multipath transport framework, we find that aggregation can preserve end-to-end connectivity under severe link outages. However, large round-trip time (RTT) heterogeneity amplifies packet reordering, leading to substantial receiver-side buffering and bursty delivery. In addition, when the available links do not provide sufficient capacity for the offered load, pronounced sender-side buffering emerges. These effects cause real-time streaming to violate delay constraints, including cases where aggregate capacity is sufficient. To interpret these results, we formalize the distinction between connectivity continuity and service continuity and show empirically that maintaining connectivity is necessary but not sufficient for timely real-time delivery in multi-technology UAV networks. The findings motivate multipath designs that explicitly account for delay constraints, rather than optimizing for connectivity alone.

Irshad A. Meer, Bruno Hörmann, Mustafa Ozger et al.

The integration of unmanned aerial vehicles (UAVs) into cellular networks presents significant mobility management challenges, primarily due to frequent handovers caused by probabilistic line-of-sight conditions with multiple ground base stations (BSs). To tackle these challenges, reinforcement learning (RL)-based methods, particularly deep Q-networks (DQN), have been employed to optimize handover decisions dynamically. However, a major drawback of these learning-based approaches is their black-box nature, which limits interpretability in the decision-making process. This paper introduces an explainable AI (XAI) framework that incorporates Shapley Additive Explanations (SHAP) to provide deeper insights into how various state parameters influence handover decisions in a DQN-based mobility management system. By quantifying the impact of key features such as reference signal received power (RSRP), reference signal received quality (RSRQ), buffer status, and UAV position, our approach enhances the interpretability and reliability of RL-based handover solutions. To validate and compare our framework, we utilize real-world network performance data collected from UAV flight trials. Simulation results show that our method provides intuitive explanations for policy decisions, effectively bridging the gap between AI-driven models and human decision-makers.

Irshad A. Meer, Karl-Ludwig Besser, Mustafa Ozger et al.

Multi-connectivity involves dynamic cluster formation among distributed access points (APs) and coordinated resource allocation from these APs, highlighting the need for efficient mobility management strategies for users with multi-connectivity. In this paper, we propose a novel mobility management scheme for unmanned aerial vehicles (UAVs) that uses dynamic cluster reconfiguration with energy-efficient power allocation in a wireless interference network. Our objective encompasses meeting stringent reliability demands, minimizing joint power consumption, and reducing the frequency of cluster reconfiguration. To achieve these objectives, we propose a hierarchical multi-agent deep reinforcement learning (H-MADRL) framework, specifically tailored for dynamic clustering and power allocation. The edge cloud connected with a set of APs through low latency optical back-haul links hosts the high-level agent responsible for the optimal clustering policy, while low-level agents reside in the APs and are responsible for the power allocation policy. To further improve the learning efficiency, we propose a novel action-observation transition-driven learning algorithm that allows the low-level agents to use the action space from the high-level agent as part of the local observation space. This allows the lower-level agents to share partial information about the clustering policy and allocate the power more efficiently. The simulation results demonstrate that our proposed distributed algorithm achieves comparable performance to the centralized algorithm. Additionally, it offers better scalability, as the decision time for clustering and power allocation increases by only 10% when doubling the number of APs, compared to a 90% increase observed with the centralized approach.