A Robust Link Maintenance Algorithm for Directional UAV Networks Based on Breakage Probability Prediction

Millimeter-wave (mmWave) communications, coupled with directional antenna-based Flying Ad-Hoc Networks (FANETs), have received considerable attention for their potential to provide high-speed, low-latency communications for a variety of applications. However, the high mobility of Unmanned Aerial Vehicles (UAVs) in FANETs leads to dynamic changes in relative positions, resulting in frequent link failures. Effective link maintenance in such networks has become a critical challenge. This paper addresses this issue by developing mathematical models of link disconnections in directional antenna-based FANETs. Specifically, we derive the probability density functions for link disconnections due to distance and angular misalignment in closed-form expressions. Based on these prediction models, we propose the Adaptive Link Breakage Prediction with Directionality (ALBP-D) method, which exploits the high directional gain of directional antennas to extend link lifetime and improve network performance. We compare ALBP-D with two baseline methods, the Periodic Link Maintenance (PLM) method and the Residual Path Lifetime (RPL) method, through extensive simulations. The results show that ALBP-D achieves superior performance, with approximately a 10-fold improvement in both link lifetime and network connectivity duration compared to the baseline methods. In addition, ALBP-D exhibits significant improvements in maintenance overhead efficiency, especially at higher max range adjustment count, achieving a 5 to 7-fold improvement over baseline methods. These results highlight the effectiveness of ALBP-D in directional antenna-based FANETs. We also implemented a prototype system consisting of a directional antenna node and an omnidirectional antenna node using realistic UAV trajectory data. Experimental results show that the prediction models agree well with the real link disconnection data, confirming the practical feasibility and accuracy of the proposed method.