Machine Learning-based Wi-Fi Optimization (ML4WiFi)

Institutions

  • TU Berlin
  • AGH University of Science and Technology

Team @ TKN

Funding

  • DFG (Deutsche Forschungsgemeinschaft)

Project Time

  • 12/2021 - 05/2026 (first funding period)
  • 07/2026 - 06/2029 (follow-up project

Description

The project Machine Learning-based Wi-Fi Optimization (ML4WiFi) continues the successful collaboration between Technische Universität Berlin and AGH University of Krakow to advance the application of artificial intelligence in next-generation IEEE 802.11 networks. Building on the achievements of the first ML4WiFi project, including foundational surveys, reinforcement-learning-based coordination schemes, and experimental testbeds, this second phase focuses on integrating generative AI (GAI) and ensuring fair coexistence between ML-controlled and legacy Wi-Fi devices. The central research objectives are: (O1) to quantify and improve the coexistence of ML-enabled and non-ML nodes; (O2) to explore and apply GAI for PHY- and MAC-layer optimization (e.g., channel modeling, beamforming, resource scheduling); and (O3) to create experimental and synthetic open datasets supporting AI-native Wi-Fi research.

Methodologically, ML4WiFi2 combines simulation and real-world experimentation through enhanced ns-3 + Sionna frameworks and extended SDR/COTS testbeds, enabling reproducible evaluation of both discriminative and generative models. Six tightly coupled work packages address coexistence analysis and mitigation, development of GAI-based PHY/MAC algorithms, and evolution of simulation and hardware environments. Expected outcomes include new coexistence-aware ML policies, lightweight and interpretable GAI models deployable on access points, and publicly available datasets and software. The project will thus provide fundamental insights and practical tools for the transition toward intelligent, AI-native, and standards-compliant Wi-Fi networks.

Selected Publications

2026

Journals and Magazines

  1. Doğanalp Ergenç, Tobias Reisinger and Falko Dressler, "Redundancy in WiFi 7: Combining Multi-link Operation with IEEE 802.1CB FRER," Elsevier Computer Communications, vol. 247, February 2026. [DOI, BibTeX, More details]

Conferences and Workshops

  1. Doğanalp Ergenç, Mateusz Zakrzewski and Falko Dressler, "Multi-Link Scheduling with Restricted Target Wake Time in Wi-Fi 7," Proceedings of 21th IEEE/IFIP Wireless On-demand Network systems and Services Conference (WONS 2026), Crans-Montana, Switzerland, March 2026, pp. 89–96. [DOI, BibTeX, More details]
  2. Anatolij Zubow, Sascha Rösler and Falko Dressler, "Ns3Sionna: Realistic Wireless Network Simulation with Ray Tracing in ns-3," Proceedings of IEEE International Conference on Computing, Networking and Communications (ICNC 2026), Maui, HI, February 2026, pp. 1–7. [DOI, BibTeX, More details]

2025

Journals and Magazines

  1. Maksymilian Wojnar, Wojciech Ciezobka, Artur Tomaszewski, Piotr Chołda, Krzysztof Rusek, Katarzyna Kosek-Szott, Jetmir Haxhibeqiri, Jeroen Hoebeke, Boris Bellalta, Anatolij Zubow, Falko Dressler and Szymon Szott, "Coordinated Spatial Reuse Scheduling With Machine Learning in IEEE 802.11 MAPC Networks," IEEE Journal on Selected Areas in Communications, vol. 43 (11), pp. 3666–3682, November 2025. [DOI, BibTeX, More details]
  2. Jamshid Bacha, Anatolij Zubow, Szymon Szott, Katarzyna Kosek-Szott and Falko Dressler, "Deep Reinforcement Learning based Interference Optimization for Coordinated Beamforming in Ultra-Dense Wi-Fi Networks," Elsevier Computer Communications, vol. 242, pp. 108286, October 2025. [DOI, BibTeX, More details]

Conferences and Workshops

  1. Jamshid Bacha, Anatolij Zubow and Falko Dressler, "Multi-Agent Reinforcement Learning Approach for Interference Optimization in Wi-Fi 8," Proceedings of IEEE Middle East Conference on Communications and Networking (MECOM 2025), Cairo, Egypt, November 2025. [DOI, BibTeX, More details]
  2. Simon Wolfgang Schmitz-Heinen, Anatolij Zubow, Christos Laskos and Falko Dressler, "Ce-Fi: Centralized Wi-Fi over Packet-Fronthaul," Proceedings of 50th IEEE Conference on Local Computer Networks (LCN 2025), Sydney, Australia, October 2025, pp. 1–9. [DOI, BibTeX, More details]
  3. Lorenz Julius Pusch, Anatolij Zubow and Falko Dressler, "Passive Detection of Fat Users in WiFi Networks using Thompson Sampling," Proceedings of 23rd IEEE Mediterranean Communication and Computer Networking Conference (MedComNet 2025), Cagliari, Italy, June 2025. [DOI, BibTeX, More details]
  4. Anatolij Zubow, Christos Laskos, Sascha Rösler, Gerhard Wunder and Falko Dressler, "Wi-Fi Ranging under Interference," Proceedings of IEEE International Conference on Computing, Networking and Communications (ICNC 2025), Honolulu, HI, February 2025, pp. 533–537. [DOI, BibTeX, More details]

Technical Reports and Regional Workshops

  1. Maksymilian Wojnar, Wojciech Ciezobka, Artur Tomaszewski, Piotr Chołda, Krzysztof Rusek, Katarzyna Kosek-Szott, Jetmir Haxhibeqiri, Jeroen Hoebeke, Boris Bellalta, Anatolij Zubow, Falko Dressler and Szymon Szott, "Coordinated Spatial Reuse Scheduling With Machine Learning in IEEE 802.11 MAPC Networks," arXiv, cs.NI, 2505.07278, May 2025. [DOI, BibTeX, More details]

2024

Journals and Magazines

  1. Wojciech Ciezobka, Maksymilian Wojnar, Krzysztof Rusek, Katarzyna Kosek-Szott, Szymon Szott, Anatolij Zubow and Falko Dressler, "Using Ranging for Collision-Immune IEEE 802.11 Rate Selection with Statistical Learning," Elsevier Computer Communications, vol. 225, pp. 10–26, September 2024. [DOI, BibTeX, More details]

Conferences and Workshops

  1. Christos Laskos, Sigrid Dimce, Anatolij Zubow and Falko Dressler, "Towards Virtual to Real-world Transfer Learning for Mobile mmWave Beam Tracking," Proceedings of IEEE Global Communications Conference (GLOBECOM 2024), Cape Town, South Africa, December 2024, pp. 2684–2689. [DOI, BibTeX, More details]
  2. Anatolij Zubow, Muhammad Elhwawshy, Sascha Rösler, Lorenz Julius Pusch, Adam Wolisz and Falko Dressler, "SensingWall: Ultra-low Cost WiFi Wireless Sensing," Proceedings of 43rd IEEE International Conference on Computer Communications (INFOCOM 2024), Demo Session, Vancouver, Canada, May 2024. [DOI, BibTeX, PDF, More details]

Technical Reports and Regional Workshops

  1. Anatolij Zubow, Yannik Pilz, Sascha Rösler and Falko Dressler, "Ns3 meets Sionna: Using Realistic Channels in Network Simulation," arXiv, cs.NI, 2412.20524, December 2024. [DOI, BibTeX, More details]

2023

Conferences and Workshops

  1. Piotr Gawłowicz, Anatolij Zubow and Falko Dressler, "Matryoshka: Single RF Chain Multi-user Transmission through WiFi-in-WiFi Signal Emulation using COTS Hardware," Proceedings of 29th ACM International Conference on Mobile Computing and Networking (MobiCom 2023), 17th ACM International Workshop on Wireless Network Testbeds, Experimental evaluation and Characterization (WINTECH 2023), Madrid, Spain, October 2023, pp. 96–103. [DOI, BibTeX, PDF, More details]
  2. Wojciech Ciezobka, Maksymilian Wojnar, Katarzyna Kosek-Szott, Szymon Szott and Krzysztof Rusek, "FTMRate: Collision-Immune Distance-based Data Rate Selection for IEEE 802.11 Networks," Proceedings of 24th IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM 2023), Boston, MA, June 2023. [DOI, BibTeX, More details]

2022

Journals and Magazines

  1. Katarzyna Kosek-Szott, Szymon Szott and Falko Dressler, "Improving IEEE 802.11ax UORA Performance: Comparison of Reinforcement Learning and Heuristic Approaches," IEEE Access, vol. 10, pp. 120285–120295, November 2022. [DOI, BibTeX, PDF, More details]
  2. Szymon Szott, Katarzyna Kosek-Szott, Piotr Gawłowicz, Jorge Torres Gómez, Boris Bellalta, Anatolij Zubow and Falko Dressler, "Wi-Fi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning," IEEE Communications Surveys & Tutorials, vol. 24 (3), pp. 1843–1893, July 2022. VDE ITG Preis 2023 [DOI, BibTeX, PDF, More details]

2021

Technical Reports and Regional Workshops

  1. Szymon Szott, Katarzyna Kosek-Szott, Piotr Gawłowicz, Jorge Torres Gómez, Boris Bellalta, Anatolij Zubow and Falko Dressler, "WiFi Meets ML: A Survey on Improving IEEE 802.11 Performance with Machine Learning," arXiv, cs.NI, 2109.04786, September 2021. [DOI, BibTeX, PDF, More details]