German Svistunov

Azim Akhtarshenas, German Svistunov, Matteo Bernabè et al.

High-Altitude Platform Stations (HAPS) offer a promising solution for wide-area wireless coverage in maritime regions lacking terrestrial infrastructure. However, maintaining reliable performance is challenging due to dynamic ship mobility and atmospheric disturbances, particularly stratospheric wind effects on HAPS positioning. This paper proposes a deep reinforcement learning (DRL)-based framework for dynamic positioning of wind-disturbed HAPS-mounted base stations in maritime networks. A centralized DRL agent deployed on a coordinator HAPS controls multiple serving HAPS using radio measurements and network feedback, capturing realistic channel conditions and user mobility. A Proximal Policy Optimization (PPO) algorithm is employed to learn robust positioning policies that enhance coverage stability and system throughput under wind disturbances. Simulation results show that the proposed approach effectively mitigates wind-induced positioning deviations while ensuring reliable wide-area connectivity for maritime users.

German Svistunov, Matteo Bernabe, David Lopez-Perez

The increasing demand for ubiquitous, highcapacity mobile connectivity has driven cellular systems to explore beyond-terrestrial deployments. In this paper, we present a system-level performance evaluation of fifth-generation (5G) non-terrestrial network (NTN) enabled by high-altitude platform station (HAPS)-based base stations (BSs) equipped with tri-sectoral reflector antennas against fourth-generation (4G) terrestrial network (TN) and 5G TN deployments in a multicell dense urban environment. Using the simulation results comprising the average effective downlink signal-to-interference-plus-noise ratio (SINR) and the average user throughput, along with the subsequent interference analysis, we demonstrate that the reflector-based HAPS architecture is primarily constrained by inter-cell interference, while the combination of reflector configuration and deployment altitude represents a key design parameter.