数字孪生卫星网络：智能、高效与弹性运行的范式
Digital Twin Satellite Networks: A Paradigm for Intelligent, Efficient, and Resilient Operations
浏览论文内容
中文总结 AI 辅助
针对低轨巨型卫星星座运行面临的挑战，提出数字孪生卫星网络（DTSN）框架，结合多技术实现卫星网络的智能管理，经仿真验证可保障服务不中断与网络弹性。
中文摘要 AI 辅助
低轨（LEO）巨型卫星星座正成为下一代非地面网络的重要组成部分，但其运行仍面临挑战，原因在于网络拓扑快速变化、星间链路间歇性中断、硬件干扰以及严格的尺寸、重量和功率（SWaP）约束。现有基于数字孪生（DT）、数字孪生网络（DTN）、软件定义网络（SDN）和开放无线接入网（O-RAN）的方法为智能卫星组网提供了有用的构建模块，但它们并未完全支持实时、预测性和平台感知的网络运行。本文提出数字孪生卫星网络（DTSN）框架，作为低轨卫星星座可靠智能管理的闭环架构。该框架将物理卫星网络与同步虚拟孪生体连接，融合实时遥测、集成感知与通信（ISAC）、预测智能以及面向弹性的控制。为验证该概念，我们利用NASA 42航天器模拟器和基于Python的低轨星座数字孪生桥开发了星座规模的跨域协同仿真。在600秒的飞行窗口内，数字孪生持续接入物理遥测数据，以管理涵盖运动学漂移、硬件故障和对抗性干扰的多域威胁环境。通过利用预测前瞻机制和指数传感器恢复模型，该框架成功隔离受损节点并触发主动网络重配置，从而确保服务不中断和网络具备动态弹性。这些结果表明，DTSN具备支持预测性和面向弹性的卫星网络运行的潜力。
英文摘要
Satellite mega-constellations in Low Earth Orbit (LEO) are becoming an important part of next-generation non-terrestrial networks, but their operation remains challenging because of fast network topology variation, intermittent inter-satellite links, hardware disturbances, and strict Size, Weight, and Power (SWaP) constraints. Existing approaches based on Digital Twin (DT), Digital Twin Network (DTN), Software-Defined Networking (SDN), and Open Radio Access Network (O-RAN) provide useful building blocks for intelligent satellite networking, but they do not fully support real-time, predictive, and platform-aware network operation. In this paper, we propose a Digital Twin Satellite Network (DTSN) framework as a closed-loop architecture for reliable and intelligent management of LEO satellite constellations. The proposed framework connects the physical satellite network with a synchronized virtual twin and combines real-time telemetry, Integrated Sensing and Communication (ISAC), predictive intelligence, and resilience-oriented control. To validate the concept, we develop a constellation-scale cross-domain co-simulation using the NASA 42 spacecraft simulator and a Python-based DT bridge for a LEO constellation. The DT continuously ingests physical telemetry to manage a multi-domain threat environment, encompassing kinematic drift, hardware failures, and adversarial jamming over a 600-second flight window. By leveraging a predictive lookahead mechanism and an exponential sensor recovery model, the framework successfully isolates compromised nodes and triggers proactive network reconfiguration, thereby ensuring uninterrupted service and dynamic network resilience. These results show the potential of DTSN to support predictive and resilience-oriented satellite network operations.
