Non-terrestrial networks (NTNs) leverage low Earth orbit (LEO) satellite constellation (LSC) to provide wide-area and seamless connectivity. However, regional traffic demand is highly differentiated, and a conventional single-layer constellation cannot satisfy on-demand coverage and high uplink-capacity requirements under deployment-cost constraints, thereby limiting NTN performance. This paper proposes an optimization framework for multi-layer LEO constellation design tailored to differentiated regional traffic. A spatio-temporal graph (STG) representation is introduced to capture the time-varying connectivity of ground-to-satellite links (GSLs) and inter-satellite links (ISLs), and an invulnerability model is developed to characterize the reliability and service continuity of the satellite network under disturbances. In addition, a terrain-aware terminal distribution and regional traffic model is incorporated to analyze the average uplink capacity. Building on these models, a four-objective constellation design problem is formulated to maximize the average multiple coverage ratio, uplink capacity, and invulnerability, while minimizing deployment cost. To solve this problem, an FCNN-surrogate-assisted Stage-Aware Dynamic Adaptive NSGA-III (FCNN-SADANSGA-III) optimization method is developed. Simulation results demonstrate that the proposed framework achieves improved multi-objective trade-offs and enables constellation configurations that better matches regional traffic demand.

To meet the energy-saving requirements of user equipment (UE) operating in Radio Resource Control idle/inactive states (RRC_IDLE/RRC_INACTIVE) in the 3rd-Generation Partnership Project (3GPP) 5G-Advanced (5G-A) networks, the New Radio (NR) downlink paging procedure relies on periodic monitoring and frequent synchronization signal block (SSB) measurements, which wastes energy when no paging arrivals occur. Meanwhile, heterogeneous Quality of Service (QoS) constraints make it difficult for fixed-parameter Idle Discontinuous Reception and Paging Early Indication mechanisms (IDRX/PEI) to balance energy, delay, and reliability. This paper develops a UAV-assisted 5G-A paging control framework that maps services into multiple QoS classes and models QoS violation risk and system energy consumption under unified accounting, including UE monitoring/reception energy and unmanned aerial vehicle (UAV) forwarding energy. We then propose a QoS-aware risk-driven paging strategy: an offline Long Short-Term Memory (LSTM) predictor is trained to estimate the time-to-next-arrival (TTNA) of paging events and produce a bounded urgency/risk signal to initialize class-dependent thresholds, while online triggering and QoS-feedback-based threshold adaptation regulate the empirical violation rate toward target constraints under varying loads, enabling a controllable energy–delay trade-off. A simulation-based evaluation is conducted to compare the proposed method with representative baselines (Enhanced Paging Monitoring (EPM), Split Paging Occasion (SPOP), and Predicted Paging Early Indication (PPEI)) and to examine the impact of SSB overhead and UAV relaying on the energy–delay–reliability trade-offs.