arxiv: 2601.16559 · v2 · submitted 2026-01-23 · 💻 cs.NI

Predicting Networks Before They Happen: Experimentation on a Real-Time V2X Digital Twin

Roberto Pegurri , Habu Shintaro , Francesco Linsalata , Wang Kui , Tao Yu , Eugenio Moro , Maiya Igarashi , Antonio Capone

show 1 more author

Kei Sakaguchi

This is my paper

Pith reviewed 2026-05-16 12:12 UTC · model grok-4.3

classification 💻 cs.NI

keywords V2Xdigital twinray tracingnetwork prediction60 GHzLoS forecastingreal-time simulationvehicle-to-everything

0 comments

The pith

A real-time V2X digital twin predicts 60 GHz signal strength and line-of-sight changes with 1.01 dB average error before physical events occur.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that linking live vehicle trajectory forecasts from a mobility digital twin to a ray-tracing channel simulator lets networks forecast received signal strength and line-of-sight status ahead of time. This matters for safety-critical V2X uses because proactive adaptation can replace reactive responses to rapid environmental shifts. The Tokyo deployment on 60 GHz links achieves these predictions with maximum average end-to-end latency of 250 ms while trading off model detail against speed. A reader would care because the results indicate high-fidelity physical modeling can still run under real-time limits in actual urban traffic.

Core claim

By coupling the Tokyo Mobility Digital Twin, which supplies live sensing and trajectory forecasting, with VaN3Twin, a full-stack ray-tracing simulator, the framework predicts RSSI with a maximum average error of 1.01 dB and reliably forecasts LoS transitions within a maximum average end-to-end system latency of 250 ms, depending on ray-tracing detail level.

What carries the argument

The end-to-end real-time V2X Digital Twin that integrates live mobility tracking with deterministic ray-tracing channel simulation.

If this is right

Networks can adapt to environmental changes proactively rather than after they happen.
Quantifiable trade-offs exist between digital model fidelity, computational latency, and prediction horizon length.
High-fidelity ray tracing remains compatible with real-time operation for urban 60 GHz V2X links.
LoS transition forecasts become reliable inputs for higher-layer network decisions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same coupling could be tested at other frequencies or in different cities to check how much the accuracy depends on the specific urban layout.
Predicted connectivity drops could feed directly into routing or handover algorithms to reduce packet loss during vehicle motion.
Extending the horizon beyond current limits would require faster ray-tracing approximations or more accurate long-term trajectory models.

Load-bearing premise

Live trajectory forecasts from the mobility digital twin are accurate enough and the ray-tracing model correctly captures 60 GHz propagation effects in the tested urban environment.

What would settle it

Measure actual RSSI and LoS status on the vehicles in real time during the same runs and compare against the twin's predictions; consistent average errors above 1 dB or frequent missed LoS transitions would falsify the performance claims.

Figures

Figures reproduced from arXiv: 2601.16559 by Antonio Capone, Eugenio Moro, Francesco Linsalata, Habu Shintaro, Kei Sakaguchi, Maiya Igarashi, Roberto Pegurri, Tao Yu, Wang Kui.

**Figure 2.** Figure 2: End-to-end communication workflow. network-enabled positioning techniques [21]. Using this information, it continuously maintains and forecasts the mobility state of all dynamic elements in the scenario. Mobility updates are processed at a fixed, pre-defined rate, and predictions are generated for a single, short-term horizon h, selected to remain compatible with the end-to-end latency budget of the syste… view at source ↗

**Figure 3.** Figure 3: Real picture (a), the corresponding VaN3Twin ray tracing representation (b), and an example of the computed propagation [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

**Figure 4.** Figure 4: Distribution of the measured end-to-end latency [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

**Figure 5.** Figure 5: Experimental RSSI RMSE (blue) and LoS Prediction [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

read the original abstract

Emerging safety-critical Vehicle-to-Everything (V2X) applications require networks to proactively adapt to rapid environmental changes rather than merely reacting to them. While Network Digital Twins (NDTs) offer a pathway to such predictive capabilities, existing solutions typically struggle to reconcile high-fidelity physical modeling with strict real-time constraints. This paper presents a novel, end-to-end real-time V2X Digital Twin framework that integrates live mobility tracking with deterministic channel simulation. By coupling the Tokyo Mobility Digital Twin-which provides live sensing and trajectory forecasting-with VaN3Twin-a full-stack simulator with ray tracing-we enable the prediction of network performance before physical events occur. We validate this approach through an experimental proof-of-concept deployed in Tokyo, Japan, featuring connected vehicles operating on 60 GHz links. Our results demonstrate the system's ability to predict Received Signal Strength (RSSI) with a maximum average error of 1.01 dB and reliably forecast Line-of-Sight (LoS) transitions within a maximum average end-to-end system latency of 250 ms, depending on the ray tracing level of detail. Furthermore, we quantify the fundamental trade-offs between digital model fidelity, computational latency, and trajectory prediction horizons, proving that high-fidelity and predictive digital twins are feasible in real-world urban environments.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper shows a deployed Tokyo V2X digital twin that predicts RSSI to 1.01 dB error and LoS changes inside 250 ms latency by linking live mobility forecasts to ray-tracing simulation.

read the letter

The main thing to know is that the authors ran a real experiment coupling the Tokyo Mobility Digital Twin for vehicle trajectories with VaN3Twin ray-tracing to forecast 60 GHz link performance before events occur. They report a maximum average RSSI error of 1.01 dB and end-to-end latency around 250 ms depending on model detail, plus some quantification of the fidelity-latency trade-off in an urban testbed with actual connected vehicles. That integration and the concrete numbers from a live city-scale setup are the new pieces. Most digital-twin work stays offline or lacks the predictive mobility component, so this moves the needle on proactive V2X control. The experimental grounding is a plus and the trade-off analysis gives practical insight into where the limits sit. The soft spots are in the validation details. The abstract does not break out whether the 1.01 dB figure comes from direct comparison against measured vehicle RSSI or from internal simulator consistency, nor does it show sensitivity of the error to trajectory forecast horizon length. If the mobility predictions drift or the ray-tracer misses real 60 GHz effects like reflections in Tokyo geometry, the reported performance becomes optimistic. These are standard points that need checking in the full methods and data. This paper is for people working on network digital twins or safety-critical V2X who want to see a working prototype rather than pure theory. It has enough experimental substance and novelty to deserve a serious referee, even if the validation section will likely need expansion.

Referee Report

2 major / 1 minor

Summary. The paper presents a real-time V2X Digital Twin framework that integrates the Tokyo Mobility Digital Twin (providing live sensing and trajectory forecasting) with the VaN3Twin full-stack simulator using ray tracing. It claims to enable prediction of network performance metrics such as RSSI and LoS transitions before physical events occur, validated via a deployed experiment in Tokyo on 60 GHz links. The central quantitative results are a maximum average RSSI prediction error of 1.01 dB and reliable LoS transition forecasting with maximum average end-to-end system latency of 250 ms (varying with ray-tracing detail), along with quantified trade-offs between model fidelity, computational latency, and prediction horizons.

Significance. If the validation holds, this would demonstrate the practical feasibility of high-fidelity predictive digital twins for safety-critical V2X applications in urban environments, moving beyond reactive networking. The concrete experimental numbers on error and latency, plus the fidelity-latency trade-off analysis, could inform deployment guidelines; the work's strength lies in its end-to-end real-world integration rather than purely theoretical modeling.

major comments (2)

[Abstract] Abstract: the reported maximum average RSSI error of 1.01 dB is presented as evidence of predictive capability, but the text provides no explicit breakdown of whether this metric compares simulator outputs against real-vehicle RSSI measurements or against internal simulator self-consistency; without this, it is unclear whether the result demonstrates external validity or merely internal consistency of the VaN3Twin model.
[Experimental validation] Experimental validation: no sensitivity analysis is shown for how RSSI error and end-to-end latency scale with trajectory forecast horizon length. Given that the Tokyo Mobility Digital Twin forecasts are a load-bearing input, this omission leaves open whether position errors dominate the 1.01 dB budget at operationally relevant horizons.

minor comments (1)

[Abstract] The abstract mentions 'depending on the ray tracing level of detail' for the latency figure but does not define the specific levels or their computational costs; a table or figure quantifying these would improve clarity.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and clarify the validation approach while agreeing to strengthen the presentation where needed.

read point-by-point responses

Referee: [Abstract] Abstract: the reported maximum average RSSI error of 1.01 dB is presented as evidence of predictive capability, but the text provides no explicit breakdown of whether this metric compares simulator outputs against real-vehicle RSSI measurements or against internal simulator self-consistency; without this, it is unclear whether the result demonstrates external validity or merely internal consistency of the VaN3Twin model.

Authors: The 1.01 dB figure is obtained by comparing the digital twin's predicted RSSI (generated from live Tokyo Mobility Digital Twin trajectories fed into VaN3Twin ray-tracing) against actual RSSI measurements collected from the deployed 60 GHz V2X links in our Tokyo field experiment. This constitutes external validation against real hardware, as described in the experimental setup and results sections. We agree the abstract is insufficiently explicit on this distinction and will revise it to state that the error is measured against real-vehicle RSSI ground truth. revision: yes
Referee: [Experimental validation] Experimental validation: no sensitivity analysis is shown for how RSSI error and end-to-end latency scale with trajectory forecast horizon length. Given that the Tokyo Mobility Digital Twin forecasts are a load-bearing input, this omission leaves open whether position errors dominate the 1.01 dB budget at operationally relevant horizons.

Authors: The manuscript does quantify trade-offs among model fidelity, computational latency, and prediction horizons, but we acknowledge that an explicit sensitivity plot or table isolating RSSI error growth versus forecast horizon length is not presented. Because the Tokyo Mobility Digital Twin forecasts are indeed central, we will add a dedicated sensitivity analysis in the revised version (using the existing experimental traces) to show how RSSI error and latency scale with horizon and to clarify the contribution of position prediction error to the overall 1.01 dB budget. revision: yes

Circularity Check

0 steps flagged

No circularity: experimental validation against real measurements, not derivation-by-construction

full rationale

The paper's central claims (1.01 dB RSSI prediction error and 250 ms LoS forecast latency) are obtained by feeding live trajectories from the Tokyo Mobility Digital Twin into the VaN3Twin ray-tracer and comparing outputs to observed 60 GHz link metrics in a Tokyo deployment. No equations, fitted parameters, or self-citations are presented that reduce these quantitative results to the inputs by construction. The work is framed as an experimental proof-of-concept whose error figures are measured externally rather than derived internally; the load-bearing assumptions (model fidelity and trajectory accuracy) are acknowledged as external and falsifiable, not smuggled in via definition or prior self-citation chains. This is the normal non-circular case for an empirical systems paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No new free parameters, axioms, or invented entities are introduced in the abstract; the work relies on pre-existing mobility and channel simulators whose accuracy is taken as given for the reported experiment.

pith-pipeline@v0.9.0 · 5560 in / 1157 out tokens · 30919 ms · 2026-05-16T12:12:30.805917+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

end-to-end real-time V2X Digital Twin framework that integrates live mobility tracking with deterministic channel simulation... maximum average error of 1.01 dB... 250 ms
IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

Ray Tracing Detail Index (DI)... τ_rt increases monotonically with the DI level

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

23 extracted references · 23 canonical work pages · 1 internal anchor

[1]

Can vehicles foresee communication disruptions?: Feasibility of v2x network digital twin,

T. Higuchi, M. Takanashi, K. Sasaki, Y . Taguchi, and K. Sanda, “Can vehicles foresee communication disruptions?: Feasibility of v2x network digital twin,” in2025 IEEE International Conference on Pervasive Computing and Communications Workshops and other Affiliated Events (PerCom Workshops), 2025, pp. 633–636

work page 2025
[2]

Digital twin for networking: A data-driven performance modeling perspective,

L. Hui, M. Wang, L. Zhang, L. Lu, and Y . Cui, “Digital twin for networking: A data-driven performance modeling perspective,”IEEE Network, vol. 37, no. 3, pp. 202–209, 2023

work page 2023
[3]

Digital twin networks: A survey,

Y . Wu, K. Zhang, and Y . Zhang, “Digital twin networks: A survey,”IEEE Internet of Things Journal, vol. 8, no. 18, pp. 13 789–13 804, 2021

work page 2021
[4]

Smart mobility digital twin based automated vehicle navigation system: A proof of concept,

K. Wang, Z. Li, K. Nonomura, T. Yu, K. Sakaguchi, O. Hashash, and W. Saad, “Smart mobility digital twin based automated vehicle navigation system: A proof of concept,”IEEE Transactions on Intelligent Vehicles, vol. 9, no. 3, pp. 4348–4361, 2024

work page 2024
[5]

VaN3Twin: the Multi-Technology V2X Digital Twin with Ray-Tracing in the Loop

R. Pegurri, D. Gasco, F. Linsalata, M. Rapelli, E. Moro, F. Raviglione, and C. Casetti, “Van3twin: the multi-technology v2x digital twin with ray-tracing in the loop,” 2025. [Online]. Available: https://arxiv.org/abs/2505.14184

work page internal anchor Pith review Pith/arXiv arXiv 2025
[6]

ms-van3t: An integrated multi-stack framework for virtual validation of V2X communication and services,

F. Raviglione, C. R. Carletti, M. Malinverno, C. Casetti, and C. Chiasserini, “ms-van3t: An integrated multi-stack framework for virtual validation of V2X communication and services,”Computer Communications, vol. 217, pp. 70–86, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0140366424000227

work page 2024
[7]

Sionna: An Open-Source Library for Next-Generation Physical Layer Research,

J. Hoydis, S. Cammerer, F. Ait Aoudia, A. Vem, N. Binder, G. Marcus, and A. Keller, “Sionna: An Open-Source Library for Next-Generation Physical Layer Research,”arXiv preprint, Mar. 2022

work page 2022
[8]

Digital twin-enabled blockage-aware dynamic mmwave multi-hop v2x communication,

S. Roongpraiwan, Z. Li, T. Yu, and K. Sakaguchi, “Digital twin-enabled blockage-aware dynamic mmwave multi-hop v2x communication,”

work page
[9]

Available: https://arxiv.org/abs/2503.03590

[Online]. Available: https://arxiv.org/abs/2503.03590

work page arXiv
[10]

A multi-modal simulation framework to enable digital twin-based v2x communications in dynamic environments,

L. Cazzella, F. Linsalata, M. Magarini, M. Matteucci, and U. Spagnolini, “A multi-modal simulation framework to enable digital twin-based v2x communications in dynamic environments,” in2024 IEEE 100th Vehicular Technology Conference (VTC2024-Fall), 2024, pp. 1–6

work page 2024
[11]

Mobile RF Scenario Design for Massive-Scale Wireless Channel Emulators,

R. Rusca, F. Raviglione, C. Casetti, P. Giaccone, and F. Restuccia, “Mobile RF Scenario Design for Massive-Scale Wireless Channel Emulators,” in2023 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), 2023, pp. 675– 680

work page 2023
[12]

Accurate simulation of wireless vehicular networks based on ray tracing and physical layer simulation,

T. Gaugel, L. Reichardt, J. Mittag, T. Zwick, and H. Hartenstein, “Accurate simulation of wireless vehicular networks based on ray tracing and physical layer simulation,” inHigh Performance Computing in Science and Engineering’11: Transactions of the High Performance Computing Center, Stuttgart (HLRS) 2011. Springer, 2012, pp. 619– 630

work page 2011
[13]

A 3D simulation framework with ray- tracing propagation for LoRaW AN communication,

A. Ruz-Nieto, E. Egea-Lopez, J.-M. Molina-Garcıa-Pardo, and J. Santa, “A 3D simulation framework with ray- tracing propagation for LoRaW AN communication,”Internet of Things, vol. 24, p. 100964, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2542660523002871

work page 2023
[14]

Toward real-time digital twins of em environments: Computational benchmark for ray launching software,

M. Zhu, L. Cazzella, F. Linsalata, M. Magarini, M. Matteucci, and U. Spagnolini, “Toward real-time digital twins of em environments: Computational benchmark for ray launching software,”IEEE Open Journal of the Communications Society, 2024

work page 2024
[15]

Ns3 meets Sionna: Using Realistic Channels in Network Simulation,

A. Zubow, Y . Pilz, S. R ¨osler, and F. Dressler, “Ns3 meets Sionna: Using Realistic Channels in Network Simulation,” arXiv, cs.NI 2412.20524, 12 2024

work page arXiv 2024
[16]

Toward digital network twins: Integrating sionna RT in ns-3 for 6G Multi-RAT networks simulations,

R. Pegurri, F. Linsalata, E. Moro, J. Hoydis, and U. Spagnolini, “Toward digital network twins: Integrating sionna RT in ns-3 for 6G Multi-RAT networks simulations,” inIEEE INFOCOM WKSHPS: Digital Twins over NextG Wireless Networks (DTWIN 2025) (INFOCOM DTWIN 2025), London, United Kingdom (Great Britain), May 2025, p. 5.88

work page 2025
[17]

DT-CoVeSS: Advancing NextG C-V2X Security Evaluation through High-Fidelity Digital Twinning,

G. Twardokus and H. Rahbari, “DT-CoVeSS: Advancing NextG C-V2X Security Evaluation through High-Fidelity Digital Twinning,” inIEEE INFOCOM WKSHPS: Digital Twins over NextG Wireless Networks (DTWIN 2025) (INFOCOM DTWIN 2025), London, United Kingdom (Great Britain), May 2025

work page 2025
[18]

Digital- twin-empowered interference management for multihop internet of ve- hicles networks over millimeter wave bands,

M. Elloumi, G. Kaddoum, M. Zoheb Hassan, and B. Selim, “Digital- twin-empowered interference management for multihop internet of ve- hicles networks over millimeter wave bands,”IEEE Internet of Things Journal, vol. 12, no. 11, pp. 17 807–17 827, 2025

work page 2025
[19]

A digital twin paradigm: Vehicle-to-cloud based advanced driver assistance systems,

Z. Wang, X. Liao, X. Zhao, K. Han, P. Tiwari, M. J. Barth, and G. Wu, “A digital twin paradigm: Vehicle-to-cloud based advanced driver assistance systems,” in2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1–6

work page 2020
[20]

Vehicular traffic simulation in the city of turin from raw data,

M. Rapelli, C. Casetti, and G. Gagliardi, “Vehicular traffic simulation in the city of turin from raw data,”IEEE Transactions on Mobile Computing, vol. 21, no. 12, pp. 4656–4666, 2022

work page 2022
[21]

Content sharing in pedestrian-based micro clouds,

M. Rapelli, G. S. Pannu, F. Dressler, and C. Casetti, “Content sharing in pedestrian-based micro clouds,” in2022 IEEE 95th Vehicular Tech- nology Conference: (VTC2022-Spring), 2022, pp. 1–6

work page 2022
[22]

A tutorial on 5g positioning,

L. Italiano, B. Camajori Tedeschini, M. Brambilla, H. Huang, M. Nicoli, and H. Wymeersch, “A tutorial on 5g positioning,”IEEE Communica- tions Surveys & Tutorials, vol. 27, no. 3, pp. 1488–1535, 2025

work page 2025
[23]

Effects of building materials and structures on ra- diowave propagation above about 100 MHz,

ITU-R P.2040-1, “Effects of building materials and structures on ra- diowave propagation above about 100 MHz,” Jul. 2015

work page 2040