pith. sign in

arxiv: 2605.30079 · v1 · pith:C4SDDC7Dnew · submitted 2026-05-28 · 💻 cs.NI · cs.ET

Intent-Based Orchestration in Open RAN: An ns-3 Simulation Framework

Pouya Agheli , Gr\'egoire Lefebvre This is my paper

Pith reviewed 2026-06-29 00:27 UTC · model grok-4.3

classification 💻 cs.NI cs.ET
keywords Open RANintent-based orchestrationns-3 simulationradio resource managementRICdAppsIntent Satisfaction Score
0
0 comments X

The pith

Intent-based radio resource management in Open RAN improves intent satisfaction while reducing resource usage and overhead.

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

This paper introduces an ns-3 simulation framework designed to evaluate intent-based control in Open RAN networks. The framework supports integration with external controllers and internal dApps for semantics-aware orchestration across different timescales. Through a radio resource management use case, it defines an Intent Satisfaction Score to assess how well high-level intents are fulfilled under limited observability. The simulations indicate that this approach enhances the satisfaction score and cuts down on radio resources and computation, though it slightly lowers packet delivery and throughput compared to traditional methods.

Core claim

The paper presents an extensible ns-3-based simulation framework for intent-based, semantics-aware control in Open RAN. It integrates external RIC components and supports dApps for fine-grained control. In the RRM use case, scheduling uses realistic KPMs and a new Intent Satisfaction Score combining distortion- and perception-oriented measures. Results show intent-based RRM improves ISS while significantly reducing radio resource usage and computational overhead, at the cost of moderate reductions in packet delivery ratio and throughput.

What carries the argument

The Intent Satisfaction Score (ISS), a metric that quantifies delivery of intent-relevant information by combining distortion- and perception-oriented measures, used within the ns-3 framework to guide dApp decisions.

If this is right

  • Intent-based RRM can operate effectively with the limited key performance measurements available to dApps.
  • Orchestration across timescales becomes feasible while preserving standardized network behavior.
  • Trade-offs between intent delivery and conventional performance metrics must be considered in deployment.
  • Simulation enables testing before real-world implementation of RIC and dApp components.

Where Pith is reading between the lines

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

  • The framework may support evaluation of intent-based methods in additional RAN functions such as mobility management or interference coordination.
  • Validation against physical testbeds would strengthen confidence in the observed trade-offs.
  • Adoption could influence how intents are standardized in Open RAN specifications.

Load-bearing premise

The ns-3 model and the chosen key performance measurements accurately capture the observability constraints and behavior of real Open RAN dApps and RIC components.

What would settle it

Running the same intent-based RRM policy on a real Open RAN testbed and comparing the resulting Intent Satisfaction Score, resource usage, and throughput to the simulation outputs.

Figures

Figures reproduced from arXiv: 2605.30079 by Gr\'egoire Lefebvre, Pouya Agheli.

Figure 1
Figure 1. Figure 1: Open RAN logical architecture with intent support. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Interactions between the network simulation environment and control [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Time-based message exchange among the near-RT RIC, eNodeB dApp [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Comparison of intent-based (IB) and intent-agnostic UE selection [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Average resource usage and decision time under different UE selection [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
read the original abstract

This paper presents an extensible ns-3-based simulation framework for evaluating intent-based, semantics-aware control in Open RAN architectures. The framework integrates external Radio Access Network (RAN) Intelligent Controller (RIC) components and supports fine-grained control via internal distributed applications (dApps), enabling intent-based RAN orchestration across different timescales while maintaining standardized network behavior. As an illustrative use case, we implement an intent-based dApp for radio resource management (RRM) under realistic observability constraints. The scheduling problem is formulated using realistic key performance measurements (KPMs) available to dApps, together with a newly introduced Intent Satisfaction Score (ISS), which quantifies the delivery of intent-relevant information by combining distortion- and perception-oriented measures. Simulation results show that intent-based RRM can improve ISS while significantly reducing radio resource usage and computational overhead, at the cost of a moderate reduction in packet delivery ratio and throughput.

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.

Referee Report

3 major / 1 minor

Summary. The paper presents an extensible ns-3 simulation framework for intent-based, semantics-aware orchestration in Open RAN, integrating external RIC components with internal dApps to enable control across timescales. As an illustrative use case, it formulates an intent-based RRM dApp using realistic KPMs and introduces a new Intent Satisfaction Score (ISS) that combines distortion- and perception-oriented measures; simulation results claim that this approach improves ISS while reducing radio resource usage and computational overhead, at the cost of moderate reductions in packet delivery ratio and throughput.

Significance. If the ns-3 model faithfully captures O-RAN observability constraints, the framework would provide a reproducible environment for evaluating intent-based RRM, and the ISS metric would offer a useful composite for quantifying intent delivery. The work credits the integration of standardized network behavior with external controllers and the use of available KPMs rather than idealized assumptions.

major comments (3)
  1. [Simulation results] The simulation results (abstract and results section) report ISS gains and resource reductions without error bars, baseline comparisons to non-intent RRM schedulers, or statistical tests, leaving the magnitude and robustness of the claimed trade-offs difficult to evaluate.
  2. [ns-3 framework and dApp implementation] The framework description provides no hardware-in-the-loop validation, trace replay from live O-RAN deployments, or sensitivity analysis to E2 interface latency and RIC subscription granularity; because the central performance claims rest on the modeled observability constraints, this omission is load-bearing for transferability.
  3. [Intent-based RRM use case] The ISS definition (use-case section) is introduced as a new composite without explicit validation against operator intent or comparison to existing satisfaction metrics, so the reported improvements cannot be assessed independently of the simulation outputs.
minor comments (1)
  1. [Introduction and framework] Notation for KPMs and dApp/RIC interfaces should be defined consistently in a table or early section to aid readability.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major comment below and indicate where revisions will be incorporated.

read point-by-point responses

  1. Referee: [Simulation results] The simulation results (abstract and results section) report ISS gains and resource reductions without error bars, baseline comparisons to non-intent RRM schedulers, or statistical tests, leaving the magnitude and robustness of the claimed trade-offs difficult to evaluate.

    Authors: We agree that the results would be strengthened by error bars from multiple runs, explicit comparisons to non-intent RRM schedulers such as proportional fair, and statistical tests. In the revision we will re-execute the simulations across multiple random seeds, add the requested baseline comparisons, and include statistical significance analysis. revision: yes

  2. Referee: [ns-3 framework and dApp implementation] The framework description provides no hardware-in-the-loop validation, trace replay from live O-RAN deployments, or sensitivity analysis to E2 interface latency and RIC subscription granularity; because the central performance claims rest on the modeled observability constraints, this omission is load-bearing for transferability.

    Authors: The work presents an ns-3 simulation framework; hardware-in-the-loop validation and live trace replay are therefore outside its scope. We will, however, add a dedicated sensitivity analysis varying E2 latency and RIC subscription granularity to better substantiate transferability of the observability modeling. revision: partial

  3. Referee: [Intent-based RRM use case] The ISS definition (use-case section) is introduced as a new composite without explicit validation against operator intent or comparison to existing satisfaction metrics, so the reported improvements cannot be assessed independently of the simulation outputs.

    Authors: ISS is proposed as a novel composite tailored to intent semantics. Direct validation against operator intent requires industry data not available here; we will nevertheless expand the section with explicit comparisons to existing satisfaction metrics (e.g., throughput- or latency-only scores) and additional justification of the chosen components. revision: partial

Circularity Check

0 steps flagged

No circularity: simulation outputs and new composite metric are independent of inputs

full rationale

The paper describes an ns-3 simulation framework that implements intent-based RRM using KPMs and a newly defined ISS metric (combining distortion- and perception-oriented measures). Reported gains in ISS, resource usage, and overhead are direct simulation outputs under the modeled constraints; no equations, fitted parameters, or self-citations reduce these results to the inputs by construction. The derivation chain consists of model implementation followed by execution, which is self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

The central claim rests on the realism of the ns-3 model and the validity of the newly introduced ISS; no free parameters, standard axioms, or externally validated invented entities are described in the abstract.

invented entities (1)
  • Intent Satisfaction Score (ISS) no independent evidence
    purpose: Quantifies delivery of intent-relevant information by combining distortion- and perception-oriented measures
    Newly defined composite metric introduced for the RRM dApp use case

pith-pipeline@v0.9.1-grok · 5684 in / 1100 out tokens · 23527 ms · 2026-06-29T00:27:23.538739+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

25 extracted references · 1 canonical work pages

  1. [1]

    C. E. Shannon and W. Weaver,The Mathematical Theory of Communi- cation. University of Illinois Press, Urbana, 1949

    1949

  2. [2]

    A survey on intent-based networking,

    A. Leivadeas and M. Falkner, “A survey on intent-based networking,” IEEE Commun. Surveys Tuts., vol. 25, no. 1, 2022

    2022

  3. [3]

    O-RAN architecture description,

    O-RAN Alliance, “O-RAN architecture description,” O-RAN Alliance, Technical Specification v14.01, 2025

    2025

  4. [4]

    dApps: Distributed applications for real-time inference and control in O-RAN,

    S. D’Oro, M. Polese, L. Bonati, H. Cheng, and T. Melodia, “dApps: Distributed applications for real-time inference and control in O-RAN,” IEEE Commun. Mag., vol. 60, no. 11, 2022

    2022

  5. [5]

    dApps for real-time RAN control: Use cases and requirements,

    O.-R. A. N. G. R. G. (nGRG), “dApps for real-time RAN control: Use cases and requirements,”ORAN-WG3. Tech. Spec., 2024

    2024

  6. [6]

    dApps: Enabling real-time AI-based Open RAN control,

    A. Lacava, L. Bonati, N. Mohamadi, R. Gangula, F. Kaltenberger, P. Johari, S. D’Oro, F. Cuomo, M. Polese, and T. Melodia, “dApps: Enabling real-time AI-based Open RAN control,”Computer Networks, 2025

    2025

  7. [7]

    The ns-3 network simulator,

    G. F. Riley and T. R. Henderson, “The ns-3 network simulator,” in Modeling and Tools for Network Simulation. Springer, 2010, pp. 15–34

    2010

  8. [8]

    ns-O-RAN: Simulating O-RAN 5G systems in ns-3,

    A. Lacava, M. Bordin, M. Polese, R. Sivaraj, T. Zugno, F. Cuomo, and T. Melodia, “ns-O-RAN: Simulating O-RAN 5G systems in ns-3,” in Proc. ACM Wkshp. ns-3, 2023

    2023

  9. [9]

    O-RAN with machine learning in ns-3,

    W. Garey, T. Ropitault, R. Rouil, E. Black, and W. Gao, “O-RAN with machine learning in ns-3,” inProc. ACM Wkshp. ns-3, 2023

    2023

  10. [10]

    Evolving 5G-LENA towards 6G: Integrating AI for intelligent scheduling of multi- flow traffic,

    H. Kim, K. Koutlia, B. Bojovi ´c, A. Ashtari, and G. Ferreira, “Evolving 5G-LENA towards 6G: Integrating AI for intelligent scheduling of multi- flow traffic,” inProc. Int. Conf. ns-3, 2025

    2025

  11. [11]

    ns-3 meets OpenAI Gym: The playground for machine learning in networking research,

    P. Gawłowicz and A. Zubow, “ns-3 meets OpenAI Gym: The playground for machine learning in networking research,” inProc. ACM Int. Conf. Model., Anal. Simul. Wireless Mobile Syst., 2019

    2019

  12. [12]

    Open RAN meets semantic communications: A synergistic match for open, intelligent, and knowledge-driven 6G,

    P. Li and A. Aijaz, “Open RAN meets semantic communications: A synergistic match for open, intelligent, and knowledge-driven 6G,” in Proc. IEEE Conf. Standards Commun. Netw., 2023

    2023

  13. [13]

    SEM- O-RAN: Semantic O-RAN slicing for mobile edge offloading of com- puter vision tasks,

    C. Puligheddu, J. Ashdown, C. F. Chiasserini, and F. Restuccia, “SEM- O-RAN: Semantic O-RAN slicing for mobile edge offloading of com- puter vision tasks,”IEEE Trans. Mob. Comput., vol. 23, no. 7, 2023

    2023

  14. [14]

    Semantic non-terrestrial communications with open ran-enabled 6G,

    E. Zeydan, L. Blanco, C. J. Vaca-Rubio, M. Caus, and K. Dev, “Semantic non-terrestrial communications with open ran-enabled 6G,” IEEE Commun. Stand. Mag., 2025

    2025

  15. [15]

    ALLSTaR: Automated LLM-driven scheduler generation and testing for intent- based RAN,

    M. Elkael, M. Polese, R. Prasad, S. Maxenti, and T. Melodia, “ALL- STaR: Automated LLM-driven scheduler generation and testing for intent-based RAN,”arXiv:2505.18389, 2025

    work page arXiv 2025

  16. [16]

    ns3-ai: Fostering artificial intelligence algorithms for networking research,

    H. Yin, P. Liu, K. Liu, L. Cao, L. Zhang, Y . Gao, and X. Hei, “ns3-ai: Fostering artificial intelligence algorithms for networking research,” in Proc. ACM Wkshp. ns-3, 2020, p. 57–64

    2020

  17. [17]

    Rethinking lossy compression: The rate- distortion-perception tradeoff,

    Y . Blau and T. Michaeli, “Rethinking lossy compression: The rate- distortion-perception tradeoff,” inProc. PMLR Int. Conf. Mach. Learn., 2019

    2019

  18. [18]

    Learning transferable visual models from natural language supervision,

    A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clarket al., “Learning transferable visual models from natural language supervision,” inProc. PMLR Int. Conf. Mach. Learn., 2021

    2021

  19. [19]

    Image quality assessment: from error visibility to structural similarity,

    Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,”IEEE Trans. Image Process., vol. 13, no. 4, 2004

    2004

  20. [20]

    SSIMULACRA 2: Structural similarity unveiling local and compression related artifacts,

    J. Sneyers, “SSIMULACRA 2: Structural similarity unveiling local and compression related artifacts,” github.com/cloudinary/ssimulacra2, 2023, accessed: Jan. 2026

    2023

  21. [21]

    Evolved Universal Terrestrial Radio Access (E-UTRA); Physical layer procedures,

    3GPP, “Evolved Universal Terrestrial Radio Access (E-UTRA); Physical layer procedures,” 3rd Generation Partnership Project (3GPP), Tech. Rep. ETSI TS 136 213, 2018

    2018

  22. [22]

    Multidimensional knapsack problems,

    H. Kellerer, U. Pferschy, and D. Pisinger, “Multidimensional knapsack problems,” inKnapsack problems. Springer, 2004

    2004

  23. [23]

    E-UTRA; User Equipment radio transmission and reception,

    3GPP, “E-UTRA; User Equipment radio transmission and reception,” 3rd Generation Partnership Project (3GPP), Tech. Rep. ETSI TS 36.101, 2018

    2018

  24. [24]

    HybridBuildings Propagation Loss Model,

    ns-3 Project, “HybridBuildings Propagation Loss Model,” https://www. nsnam.org, ns-3 LTE Module Doc

  25. [25]

    Further Advancements for E-UTRA Physical Layer Aspects,

    3GPP, “Further Advancements for E-UTRA Physical Layer Aspects,” 3rd Generation Partnership Project (3GPP), Tech. Rep. TR 36.814, 2010

    2010