{"ID":22952670,"CreatedAt":"2026-09-17T02:12:05.498442134Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.18704","arxiv_id":"2609.18704","title":"Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study","abstract":"Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely on entire topology representations, which are inherently monolithic and lack reusability under topological or traffic changes in the network. This paper introduces a composable NDT approach that decomposes networks into subgraphs represented by reusable unit twins that capture subgraph structure, configuration and traffic behaviours. A lightweight composer aggregates unit twin combinations to create NDTs that predict per-route end-to-end latency through an overall topology. Evaluation across controlled synthetic topologies and diverse traffic scenarios, real-world Topology Zoo topologies, and a public NDT challenge dataset demonstrates that the composable NDTs achieve high in-distribution accuracy while remaining stable under out-of-distribution scenarios. Comparison with monolithic full topology NDTs demonstrates that our composable approach achieves reusability, while achieving comparable or superior accuracy.","short_abstract":"Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely...","url_abs":"https://arxiv.org/abs/2609.18704","url_pdf":"https://arxiv.org/pdf/2609.18704v1","authors":"[\"Shenjia Ding\",\"David Flynn\",\"Paul Harvey\"]","published":"2026-09-16T14:12:46Z","proceeding":"cs.NI","tasks":"[\"cs.NI\",\"cs.LG\"]","methods":"[]","has_code":false}