Better Together: Leveraging Multiple Digital Twins for Deployment Optimization of Airborne Base Stations

TL;DR

This work tackles the problem of deploying airborne base stations under UAV time constraints in urban settings by introducing a Multi-DT framework that jointly leverages Sionna's differentiable ray tracing and AODT's system-level simulation. It enables gradient-based ABS location, orientation, and power optimization with cross-validation between DTs via a Shared Data Layer, and proposes a resilience mechanism for mission-critical coverage through bi-directional DT information flow. The results show fast convergence for location optimization, substantial SIR gains and fairness improvements for orientation/power optimization, and robust cross-DT validation across AOIs, demonstrating practical gains for deployment planning and disaster response. Overall, the framework illustrates the feasibility and benefits of combining multiple digital twins to tackle complex, real-world wireless deployment and resilience problems at city scale.

Abstract

Airborne Base Stations (ABSs) allow for flexible geographical allocation of network resources with dynamically changing load as well as rapid deployment of alternate connectivity solutions during natural disasters. Since the radio infrastructure is carried by unmanned aerial vehicles (UAVs) with limited flight time, it is important to establish the best location for the ABS without exhaustive field trials. This paper proposes a digital twin (DT)-guided approach to achieve this through the following key contributions: (i) Implementation of an interactive software bridge between two open-source DTs such that the same scene is evaluated with high fidelity across NVIDIA's Sionna and Aerial Omniverse Digital Twin (AODT), highlighting the unique features of each of these platforms for this allocation problem, (ii) Design of a back-propagation-based algorithm in Sionna for rapidly converging on the physical location of the UAVs, orientation of the antennas and transmit power to ensure efficient coverage across the swarm of the UAVs, and (iii) numerical evaluation in AODT for large network scenarios (50 UEs, 10 ABS) that identifies the environmental conditions in which there is agreement or divergence of performance results between these twins. Finally, (iv) we propose a resilience mechanism to provide consistent coverage to mission-critical devices and demonstrate a use case for bi-directional flow of information between the two DTs.

Figures (12)

• Figure 1: Overview of proposed optimization and validation framework for Airborne Base Stations (ABSs) deployment using Multiple Digital Twins.
• Figure 2: Multi-DT framework showing task separation: Sionna (left) performs gradient-based optimization, AODT (right) handles validation and mobility simulation, and the Shared Data Layer enables bidirectional communication through standardized data exchange (3D models, ABS configurations, User Equipment (UE) trajectories and simulation results). Arrows demonstrate the synergistic information flow between platforms at each computation step.
• Figure 3: The same Tokyo 3D map from high-detail PLATEAU dataset loaded in Sionna and AODT, used to demonstrate the proposed approaches for Multi-DT framework. (a) shows a path gain Coverage Map computed with Sionna and (b) presents a simulation frame from AODT multi-UE simulation in the same map location.
• Figure 4: Visualization of loss function terms $\gamma P_a + \eta P_b$ projected over the 2D ground-plane of a 3D map of Tokyo for a sample AOI (delimited by the yellow circle) and considering ABSs' elevation of $h = 70$m. In this visualization, only one ABS is considered and loss values are clipped in the range $[0,2000]$.
• Figure 5: AOI satisfaction metric for all combinations of $M$ AOIs taken in groups of $m=\{1, 2, 3, 4, 5\}$. Each combination is averaged over 50 runs with semi-random initial ABS deployment, for a total of $\{250, 500, 500, 250, 50\}$ runs each.