pith. sign in

arxiv: 2605.22306 · v1 · pith:MJIBYMDTnew · submitted 2026-05-21 · 💻 cs.MA · cs.AI

ACCoRD: Actor-Critic Conflict Resolution with Deep learning for O-RAN xApps

Cezary Adamczyk , Adrian Kliks This is my paper

Pith reviewed 2026-05-22 02:12 UTC · model grok-4.3

classification 💻 cs.MA cs.AI
keywords O-RANconflict resolutionreinforcement learningxAppsartificial neural networksnetwork managementPPO algorithmRAN intelligent controller
0
0 comments X

The pith

An actor-critic neural network resolves O-RAN control conflicts more efficiently than rule-based methods.

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

The paper aims to show that an artificial neural network trained with reinforcement learning can resolve conflicts between xApp control decisions in O-RAN's Near-Real-Time RAN Intelligent Controller more effectively than rule-based methods. By analyzing network data and conflicting decisions, the network infers optimal resolution actions and updates its parameters based on post-resolution network feedback. Simulations demonstrate significant reductions in negative network events, particularly under medium and high traffic loads. The work also introduces a new way to evaluate conflict resolution performance. If correct, this would support more reliable operation of open radio access networks with multiple intelligent controllers.

Core claim

The proposed ACCoRD method uses an ANN trained with PPO-Clip to infer optimal conflict resolution actions from network and decision data, leading to improved efficiency over rule-based approaches through significant reductions in negative network events in medium and high traffic scenarios, as evaluated in simulations with a new CR evaluation methodology.

What carries the argument

Actor-Critic Conflict Resolution Agent implemented as an Artificial Neural Network trained via the PPO-Clip reinforcement learning algorithm to select optimal actions for resolving detected control conflicts.

If this is right

  • Reduces negative network events caused by conflicting control decisions significantly in medium and high traffic scenarios compared to rule-based methods.
  • Uses network feedback after each resolution to evaluate efficiency and update ANN weights during batch training.
  • Proposes a new methodology for evaluating conflict resolution solutions.
  • The ANN infers optimal CR actions by analyzing data about the network and conflicting control decisions.

Where Pith is reading between the lines

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

  • Successful deployment in real O-RAN could allow for more dynamic and self-optimizing network management without manual rule tuning.
  • Similar reinforcement learning approaches might apply to conflict resolution in other multi-agent network systems like 5G core or edge computing.
  • The batch training aspect opens possibilities for periodic retraining to adapt to changing network conditions over time.
  • Integrating this with existing O-RAN interfaces could accelerate adoption in commercial deployments.

Load-bearing premise

The simulation environment and traffic models used for training and evaluation accurately capture the dynamics and conflict patterns of real O-RAN deployments.

What would settle it

Observing the reduction in negative network events when applying the trained model to a physical O-RAN testbed or real-world deployment under comparable traffic conditions.

Figures

Figures reproduced from arXiv: 2605.22306 by Adrian Kliks, Cezary Adamczyk.

Figure 1
Figure 1. Figure 1: Detailed data flow for ACCoRD operation 2) Validity mask: Because the ANN utilizes a fixed number of decision heads (NConfDec) to process a variable number of conflicting decisions, not all output heads produce valid data for every inference step. To address this, the ANN outputs a validity mask—a boolean tensor of dimension NConfDec. This mask corresponds to the input slots and identifies which decision h… view at source ↗
Figure 2
Figure 2. Figure 2: Structure of the actor-critic ANN implemented in ACCoRD [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Data flow for ACCoRD’s RL training training by utilizing a clipped surrogate objective function L CLIP [8], defined as: L CLIP (θ) = Eˆ t h min(rt(θ)Aˆ t, clip(rt(θ), 1 − ϵ, 1 + ϵ)Aˆ t) i (2) where rt(θ) is the probability ratio between new and old policies, Aˆ t is the estimated advantage, and ϵ is the clipping hyperparameter. The flow of state, action, and reward data during the training phase is depicte… view at source ↗
read the original abstract

Conflict Mitigation (ConMit) is a crucial part of intelligent network control in Open Radio Access Networks (O-RAN). In this paper, we propose a method named ACCoRD to resolve detected control conflicts in Near-Real Time RAN Intelligent Controller using a Conflict Resolution (CR) Agent with an Artificial Neural Network (ANN) trained with a reinforcement learning algorithm PPO-Clip. The implemented ANN analyzes data about the network and conflicting control decisions to infer optimal CR actions. The CR Agent gathers feedback from the network after each resolved conflict to assess its efficiency and adjust the ANN's weights during batch training. The evaluation of the proposed approach is based on simulation data. A new methodology for evaluating CR solutions is proposed. Results show that the proposed ANN-based method improves on the efficiency of rule-based approaches by significantly reducing negative network events caused by conflicting control decisions in medium and high traffic scenarios.

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

2 major / 2 minor

Summary. The paper proposes ACCoRD, an Actor-Critic Conflict Resolution method for O-RAN xApps that uses an Artificial Neural Network trained via the PPO-Clip reinforcement learning algorithm to resolve detected control conflicts in the Near-RT RIC. The CR Agent collects network feedback after each resolution to update the ANN weights in batch training. A new evaluation methodology is introduced, and simulation results are reported to show that the ANN-based approach significantly reduces negative network events relative to rule-based baselines, particularly in medium- and high-traffic scenarios.

Significance. If the simulation environment faithfully reproduces real O-RAN conflict dynamics, traffic patterns, and xApp timing, the work would demonstrate a viable learned policy for conflict mitigation that outperforms static rules under load. The introduction of a dedicated CR evaluation methodology is a positive contribution to the O-RAN control literature. However, the absence of any cross-validation against real traces or testbed data means the reported gains remain conditional on unverified modeling assumptions.

major comments (2)
  1. [Evaluation] Evaluation section: the central claim that the PPO-Clip ANN reduces negative events versus rule-based methods rests entirely on simulation results, yet no quantitative comparison of the simulator's conflict arrival process, interference correlation, or Near-RT RIC decision timing against real O-RAN traces or testbed measurements is provided. This is load-bearing for the generalization statement.
  2. [Methodology] Methodology section: the new CR evaluation methodology is introduced but lacks explicit statistical tests (e.g., confidence intervals or hypothesis testing on the reduction in negative events) and details on baseline rule implementations, making it impossible to judge whether the reported improvement is robust or an artifact of the chosen generative model.
minor comments (2)
  1. [ACCoRD Architecture] Clarify the exact state representation fed to the ANN and the action space for conflict resolution; current description is high-level.
  2. [Results] Add a table or figure comparing the number of negative events, throughput, and latency metrics across traffic loads for all methods.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive and detailed comments. We address each major comment below, indicating where revisions will be made to the manuscript.

read point-by-point responses

  1. Referee: [Evaluation] Evaluation section: the central claim that the PPO-Clip ANN reduces negative events versus rule-based methods rests entirely on simulation results, yet no quantitative comparison of the simulator's conflict arrival process, interference correlation, or Near-RT RIC decision timing against real O-RAN traces or testbed measurements is provided. This is load-bearing for the generalization statement.

    Authors: We acknowledge that the evaluation relies on simulation and does not include direct quantitative validation against real O-RAN traces or testbed data. Public datasets capturing fine-grained conflict arrival processes, interference correlations, and Near-RT RIC timing are not available, which is a recognized limitation in current O-RAN research. Our simulator follows O-RAN specifications for traffic generation, interference modeling, and control loop timing. In the revision we will expand the simulation description to explicitly map each modeling choice to the relevant O-RAN technical reports and add a dedicated limitations subsection that qualifies the generalization claims. This will make the conditional nature of the results transparent without requiring data we do not possess. revision: partial

  2. Referee: [Methodology] Methodology section: the new CR evaluation methodology is introduced but lacks explicit statistical tests (e.g., confidence intervals or hypothesis testing on the reduction in negative events) and details on baseline rule implementations, making it impossible to judge whether the reported improvement is robust or an artifact of the chosen generative model.

    Authors: We agree that greater statistical rigor and transparency on the baselines will strengthen the paper. In the revised manuscript we will report confidence intervals for the reduction in negative events across all traffic scenarios and include hypothesis testing (paired t-tests or Wilcoxon tests) on the differences versus the rule-based baselines. We will also add an appendix subsection that fully specifies the rule-based conflict resolution logic, including the exact priority ordering, threshold values, and tie-breaking rules used in each baseline. revision: yes

standing simulated objections not resolved
  • Direct quantitative comparison of the simulator against real O-RAN traces or testbed measurements, as no such public datasets with the required granularity are available to the authors.

Circularity Check

0 steps flagged

No circularity: empirical results from held-out simulation data after RL training

full rationale

The paper describes training an ANN policy with PPO-Clip on network simulation traces to select conflict-resolution actions, then measures reduction in negative events on separate evaluation scenarios. This is a standard train-then-test workflow with no equations or claims that reduce the reported performance metric to the training inputs by construction. No self-citations, uniqueness theorems, or ansatzes are invoked as load-bearing steps in the derivation. The central claim therefore remains an independent empirical observation rather than a tautology.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The method relies on standard reinforcement learning assumptions and simulation-based validation; no new entities or ad-hoc parameters are introduced beyond typical PPO hyperparameters.

axioms (1)
  • domain assumption Network state transitions can be treated as a Markov Decision Process suitable for PPO training.
    Invoked implicitly when applying actor-critic RL to the conflict resolution task.

pith-pipeline@v0.9.0 · 5681 in / 1172 out tokens · 41147 ms · 2026-05-22T02:12:03.922343+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

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

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

155 extracted references · 155 canonical work pages · 2 internal anchors

  1. [1]

    2023 , volume=

    Adamczyk, Cezary and Kliks, Adrian , journal=. 2023 , volume=

    work page 2023

  2. [2]

    2023 , volume=

    Adamczyk, Cezary and Kliks, Adrian , booktitle=. 2023 , volume=

    work page 2023

  3. [3]

    2023 , volume=

    Adamczyk, Cezary , booktitle=. 2023 , volume=

    work page 2023

  4. [4]

    2024 , volume=

    Hoffmann, Marcin and Janji, Salim and Samorzewski, Adam and Kułacz,. 2024 , volume=

    work page 2024

  5. [5]

    2025 , volume=

    Sultana, Abida and Adamczyk, Cezary and Chowdhury, Mayukh Roy and Kliks, Adrian and Silva, Aloizio Da , booktitle=. 2025 , volume=

    work page 2025

  6. [6]

    doi:10.5281/zenodo.17752108 , note=

    Adamczyk, Cezary and Kliks, Adrian , year=. doi:10.5281/zenodo.17752108 , note=. , archivePrefix=

    work page doi:10.5281/zenodo.17752108

  7. [7]

    Przegląd Telekomunikacyjny - Wiadomości Telekomunikacyjne

    Adamczyk, Cezary and Kliks, Adrian , title=". Przegląd Telekomunikacyjny - Wiadomości Telekomunikacyjne. 2022. doi:10.15199/59.2022.4.68

    work page doi:10.15199/59.2022.4.68 2022

  8. [8]

    doi:10.1002/9780470978238 , url=

    Sauter, Martin , year=. doi:10.1002/9780470978238 , url=

    work page doi:10.1002/9780470978238

  9. [9]

    2008 , publisher=

    Ebersp. 2008 , publisher=

    work page 2008

  10. [10]

    and Seidenberg, P

    Walke, B.H. and Seidenberg, P. and Althoff, M.P. , isbn=. 2003 , publisher=

    work page 2003

  11. [11]

    2000 , publisher=

    Richardson, KW , journal=. 2000 , publisher=

    work page 2000

  12. [12]

    and Toskala, A

    Holma, H. and Toskala, A. , isbn=. 2007 , publisher=

    work page 2007

  13. [13]

    2019 , volume=

    Zhang, Shunliang , journal=. 2019 , volume=

    work page 2019

  14. [14]

    2012 , publisher=

    H. 2012 , publisher=

    work page 2012

  15. [15]

    2013 , volume=

    Aliu, Osianoh Glenn and Imran, Ali and Imran, Muhammad Ali and Evans, Barry , journal=. 2013 , volume=

    work page 2013

  16. [16]

    2024 , volume=

    Chen, Jiacheng and Liang, Xiaohu and Xue, Jianzhe and Sun, Yu and Zhou, Haibo and Shen, Xuemin , journal=. 2024 , volume=

    work page 2024

  17. [17]

    2024 , volume=

    Polese, Michele and Dohler, Mischa and Dressler, Falko and Erol-Kantarci, Melike and Jana, Rittwik and Knopp, Raymond and Melodia, Tommaso , journal=. 2024 , volume=

    work page 2024

  18. [18]

    and Lozano, Angel and Marzetta, Thomas L

    Boccardi, Federico and Heath, Robert W. and Lozano, Angel and Marzetta, Thomas L. and Popovski, Petar , journal=. 2014 , volume=

    work page 2014

  19. [19]

    and Mir, Talha and Mir, Usama , TITLE =

    Sufyan, Ali and Khan, Khan Bahadar and Khashan, Osama A. and Mir, Talha and Mir, Usama , TITLE =. Electronics , VOLUME =. 2023 , NUMBER =

    work page 2023

  20. [20]

    2020 , volume=

    Giordani, Marco and Polese, Michele and Mezzavilla, Marco and Rangan, Sundeep and Zorzi, Michele , journal=. 2020 , volume=

    work page 2020

  21. [21]

    and Yan, Ying and Scolari, Lara and Kardaras, Georgios and Berger, Michael S

    Checko, Aleksandra and Christiansen, Henrik L. and Yan, Ying and Scolari, Lara and Kardaras, Georgios and Berger, Michael S. and Dittmann, Lars , journal=. 2015 , volume=

    work page 2015

  22. [22]

    2024 , volume=

    Kassi, Mihia and Hamouda, Soumaya , journal=. 2024 , volume=

    work page 2024

  23. [23]

    Frauendorf, Jose Luiz N and Souza, Erika , year =

    work page

  24. [24]

    Hasabelnaby and Mohanad Obeed and Mohammed Saif and Anas Chaaban and M

    Mahmoud A. Hasabelnaby and Mohanad Obeed and Mohammed Saif and Anas Chaaban and M. J. Hossain , year=. doi:10.48550/arXiv.2411.12166 , note=. 2411.12166 , archivePrefix=

    work page doi:10.48550/arxiv.2411.12166

  25. [25]

    Larsen and Henrik L

    Line M.P. Larsen and Henrik L. Christiansen and Sarah Ruepp and Michael S. Berger , keywords =. 2024 , issn =. doi:10.1016/j.comnet.2024.110292 , url =

    work page doi:10.1016/j.comnet.2024.110292 2024

  26. [26]

    Sensors , VOLUME =

    Azariah, Wilfrid and Bimo, Fransiscus Asisi and Lin, Chih-Wei and Cheng, Ray-Guang and Nikaein, Navid and Jana, Rittwik , TITLE =. Sensors , VOLUME =. 2024 , NUMBER =

    work page 2024

  27. [27]

    2025 , volume=

    Agarwal, Bharat and Irmer, Ralf and Lister, David and Muntean, Gabriel-Miro , journal=. 2025 , volume=

    work page 2025

  28. [28]

    doi:10.48550/arXiv.2301.06713 , note=

    Prabhu Kaliyammal Thiruvasagam and Chandrasekar T and Vinay Venkataram and Vivek Raja Ilangovan and Maneesha Perapalla and Rajisha Payyanur and Senthilnathan M D and Vishal Kumar and Kokila J , year=. doi:10.48550/arXiv.2301.06713 , note=. 2301.06713 , archivePrefix=

    work page doi:10.48550/arxiv.2301.06713

  29. [29]

    2023 , month =

    Coletti, Claudio and Diego, William and Duan, Ran and Ghassemzadeh, Saeed and Gupta, Dhruv and Huang, Jinri and Joshi, Kaustubh and Matsukawa, Ryusuke and Suciu, Lucian and Sun, Junshuai and Sun, Qi and Umesh, Anil and Yan, Kai , journal =. 2023 , month =

    work page 2023

  30. [30]

    2023 , volume=

    Polese, Michele and Bonati, Leonardo and D’Oro, Salvatore and Basagni, Stefano and Melodia, Tommaso , journal=. 2023 , volume=

    work page 2023

  31. [31]

    and Singh, Sukhdeep and Banerji, Rahul and Reed, Jeffery H

    Niknam, Solmaz and Roy, Abhishek and Dhillon, Harpreet S. and Singh, Sukhdeep and Banerji, Rahul and Reed, Jeffery H. and Saxena, Navrati and Yoon, Seungil , booktitle=. 2022 , volume=

    work page 2022

  32. [32]

    2024 , volume=

    Marinova, Simona and Leon-Garcia, Alberto , journal=. 2024 , volume=

    work page 2024

  33. [33]

    2022 , volume=

    Giannopoulos, Anastasios and Spantideas, Sotirios and Kapsalis, Nikolaos and Gkonis, Panagiotis and Sarakis, Lambros and Capsalis, Christos and Vecchio, Massimo and Trakadas, Panagiotis , journal=. 2022 , volume=

    work page 2022

  34. [34]

    Dryjański, Robert , year=

    work page

  35. [35]

    2022 , volume=

    D'Oro, Salvatore and Polese, Michele and Bonati, Leonardo and Cheng, Hai and Melodia, Tommaso , journal=. 2022 , volume=

    work page 2022

  36. [36]

    Computer Networks , volume =

    Andrea Lacava and Leonardo Bonati and Niloofar Mohamadi and Rajeev Gangula and Florian Kaltenberger and Pedram Johari and Salvatore D’Oro and Francesca Cuomo and Michele Polese and Tommaso Melodia , keywords =. Computer Networks , volume =. 2025 , issn =. doi:10.1016/j.comnet.2025.111342 , url =

    work page doi:10.1016/j.comnet.2025.111342 2025

  37. [37]

    Yungaicela-Naula and Vishal Sharma and Sandra Scott-Hayward , keywords =

    Noe M. Yungaicela-Naula and Vishal Sharma and Sandra Scott-Hayward , keywords =. Computer Networks , volume =. 2024 , issn =. doi:10.1016/j.comnet.2024.110455 , url =

    work page doi:10.1016/j.comnet.2024.110455 2024

  38. [38]

    2024 , month=

    Corici, Marius and Modroiu, Ramona and Eichhorn, Fabian and Troudt, Eric and Magedanz, Thomas , title=. 2024 , month=. doi:10.1007/s12243-024-01036-2 , url=

    work page doi:10.1007/s12243-024-01036-2 2024

  39. [39]

    2023 , volume=

    Sapavath, Naveen Naik and Kim, Brian and Chowdhury, Kaushik and Shah, Vijay K , booktitle=. 2023 , volume=

    work page 2023

  40. [40]

    preprint , url=

    Elyasi, Arman and Ashdown, Andrew and Rumman, KM and Restuccia, Francesco , year=. preprint , url=

    work page

  41. [41]

    2020 , volume=

    Preciado Rojas, Diego Fernando and Nazmetdinov, Faiaz and Mitschele-Thiel, Andreas , booktitle=. 2020 , volume=

    work page 2020

  42. [42]

    2013 , volume=

    Tsagkaris, Kostas and Koutsouris, Nikos and Demestichas, Panagiotis and Combes, Richard and Altman, Zwi , booktitle=. 2013 , volume=

    work page 2013

  43. [43]

    2014 , volume=

    Iacoboaiea, Ovidiu and Sayrac, Berna and Ben Jemaa, Sana and Bianchi, Pascal , booktitle=. 2014 , volume=

    work page 2014

  44. [44]

    2015 , volume=

    Iacoboaiea, Ovidiu and Sayrac, Berna and Ben Jemaa, Sana and Bianchi, Pascal , booktitle=. 2015 , volume=

    work page 2015

  45. [45]

    and Bettstetter, C

    Prehofer, C. and Bettstetter, C. , journal=. 2005 , volume=

    work page 2005

  46. [46]

    , booktitle=

    C, Vaishnavi and A.R., Ashok Kumar and G, Selvakumar and Chaudhari, Shashikant Y. , booktitle=. 2019 , volume=

    work page 2019

  47. [47]

    2016 , volume=

    Ali-Tolppa, Janne and Tsvetkov, Tsvetko , booktitle=. 2016 , volume=

    work page 2016

  48. [48]

    2012 , volume=

    Vlacheas, Panagiotis and Thomatos, Evangelos and Tsagkaris, Kostas and Demestichas, Panagiotis , booktitle=. 2012 , volume=

    work page 2012

  49. [49]

    2022 , volume=

    Stamatelatos, Gerasimos and Sgora, Aggeliki and Alonistioti, Nancy , booktitle=. 2022 , volume=

    work page 2022

  50. [50]

    and Carle, Georg , title =

    Banerjee, Anubhab and Mwanje, Stephen S. and Carle, Georg , title =. 2020 , isbn =. doi:10.5555/3427510.3427548 , publisher =

    work page doi:10.5555/3427510.3427548 2020

  51. [51]

    2014 , volume=

    Tall, Abdoulaye and Combes, Richard and Altman, Zwi and Altman, Eitan , journal=. 2014 , volume=

    work page 2014

  52. [52]

    2023 , volume=

    Cinemre, Idris and Mehmood, Kashif and Kralevska, Katina and Mahmoodi, Toktam , booktitle=. 2023 , volume=. doi:10.48550/arXiv.2401.08341 , isbn=

    work page doi:10.48550/arxiv.2401.08341 2023

  53. [53]

    2024 , volume=

    Akbas, Ayhan and Foh, Chuan Heng and Alimohammadi, Hamed and Seyed, Ahmad Sulaymani and Mayhoub, Samara and Abdulkareem, Sulyman and Leow, Chee Yen and Sojafar, Mohammad , booktitle=. 2024 , volume=

    work page 2024

  54. [54]

    2018 , volume=

    Moysen, Jessica and Garcia-Lozano, Mario and Giupponi, Lorenza and Ruiz, Silvia , journal=. 2018 , volume=

    work page 2018

  55. [55]

    and Tsagkaris, K

    Koutsouris, N. and Tsagkaris, K. and Demestichas, P. and Altman, Z. and Combes, R. and Peloso, P. and Ciavaglia, L. and Mamatas, L. and Clayman, S. and Galis, A. , booktitle=. 2013 , volume=

    work page 2013

  56. [56]

    and Tsagkaris, Kostas and Demestichas, Panagiotis and Altman, Z

    Koutsouris, N. and Tsagkaris, Kostas and Demestichas, Panagiotis and Altman, Z. and Combes, R. and Mamatas, Lefteris and Clayman, Stuart and Galis, Alex and Peloso, Pierre and Ciavaglia, Laurent , year =. Conflict free coordination of SON functions in a Unified Management Framework: Demonstration of a proof of concept prototyping platform , isbn =

    work page

  57. [57]

    and Mitschele-Thiel, Andreas , booktitle=

    Mwanje, Stephen S. and Mitschele-Thiel, Andreas , booktitle=. 2015 , volume=

    work page 2015

  58. [58]

    2023 , volume=

    Bag, Tanmoy and Garg, Sharva and Parameswaran, Sriram and Preciado, Diego and Mitschele-Thiel, Andreas , booktitle=. 2023 , volume=

    work page 2023

  59. [59]

    2023 , volume=

    Tu, Yi-Hao and Ma, Yi-Wei and Li, Zhi-Xiang and Chen, Jiann-Liang and Tsukamoto, Kazuya , booktitle=. 2023 , volume=

    work page 2023

  60. [60]

    2011 , volume=

    Bandh, Tobias and Sanneck, Henning and Romeikat, Raphael , booktitle=. 2011 , volume=

    work page 2011

  61. [61]

    2024 , volume=

    Lee, Eunsok and Kim, Kihoon and Han, Subin and Pack, Sangheon , booktitle=. 2024 , volume=

    work page 2024

  62. [62]

    and Mitschele-Thiel, Andreas , booktitle=

    Zia, Nauman and Mwanje, Stephen S. and Mitschele-Thiel, Andreas , booktitle=. 2014 , volume=

    work page 2014

  63. [63]

    2011 , volume=

    Gelabert, Xavier and Sayrac, Berna and Jemaa, Sana Ben , booktitle=. 2011 , volume=

    work page 2011

  64. [64]

    2013 , volume=

    Lateef, Hafiz Yasar and Imran, Ali and Abu-dayya, Adnan , booktitle=. 2013 , volume=

    work page 2013

  65. [65]

    2011 , volume=

    Schmelz, Lars Christoph and Amirijoo, Mehdi and Eisenblaetter, Andreas and Litjens, Remco and Neuland, Michaela and Turk, John , booktitle=. 2011 , volume=

    work page 2011

  66. [66]

    2012 , volume=

    Li, Yun and Li, Man and Cao, Bin and Liu, Wenjing , booktitle=. 2012 , volume=

    work page 2012

  67. [67]

    2010 , volume=

    Liu, Zhiqiang and Hong, Peilin and Xue, Kaiping and Peng, Min , booktitle=. 2010 , volume=

    work page 2010

  68. [68]

    2018 , doi =

    Miaona Huang and Jun Chen , title =. 2018 , doi =

    work page 2018

  69. [69]

    2015 , volume=

    Lateef, Hafiz Yasar and Imran, Ali and Imran, Muhammad Ali and Giupponi, Lorenza and Dohler, Mischa , journal=. 2015 , volume=

    work page 2015

  70. [70]

    Policy-driven Workflows for Mobile Network Management Automation , doi =

    Romeikat, Raphael and Bauer, Bernhard and Bandh, Tobias and Carle, Georg and Sanneck, Henning and Schmelz, Lars , booktitle =. Policy-driven Workflows for Mobile Network Management Automation , doi =. 2010 , month =

    work page 2010

  71. [71]

    2011 , volume=

    Bandh, Tobias and Romeikat, Raphael and Sanneck, Henning and Haitao Tang , booktitle=. 2011 , volume=

    work page 2011

  72. [72]

    2025 , volume=

    Zafar, Hammad and Tohidi, Ehsan and Kasparick, Martin and Stańczak, Sławomir , booktitle=. 2025 , volume=

    work page 2025

  73. [73]

    2025 , volume=

    Hou, Qiushuo and Park, Sangwoo and Zecchin, Matteo and Cai, Yunlong and Yu, Guanding and Simeone, Osvaldo , journal=. 2025 , volume=

    work page 2025

  74. [74]

    2024 , volume=

    Armstrong, Joss and Fallon, Enda and Fallon, Sheila , booktitle=. 2024 , volume=

    work page 2024

  75. [75]

    2023 , volume=

    Wadud, Abdul and Golpayegani, Fatemeh and Afraz, Nima , booktitle=. 2023 , volume=

    work page 2023

  76. [76]

    2025 , volume=

    Prever, Pietro Brach del and D'Oro, Salvatore and Bonati, Leonardo and Polese, Michele and Tsampazi, Maria and Lehmann, Heiko and Melodia, Tommaso , journal=. 2025 , volume=

    work page 2025

  77. [77]

    2024 , volume=

    Sultana, Abida and Bashar, Fahim and Chowdhury, Mayukh Roy and Da Silva, Aloizio Pereira , booktitle=. 2024 , volume=

    work page 2024

  78. [78]

    2024 , volume=

    Wadud, Abdul and Golpayegani, Fatemeh and Afraz, Nima , journal=. 2024 , volume=

    work page 2024

  79. [79]

    and DaSilva, Luiz A

    Zolghadr, Arshia and Santos, Joao F. and DaSilva, Luiz A. and Kibilda, Jacek , booktitle=. 2025 , volume=

    work page 2025

  80. [80]

    and Spantideas, Sotirios T

    Giannopoulos, Anastasios E. and Spantideas, Sotirios T. and Levis, George and Kalafatelis, Alexandros S. and Trakadas, Panagiotis , journal=. 2025 , volume=

    work page 2025

Showing first 80 references.