{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:58:57Z","timestamp":1783007937426,"version":"3.54.5"},"reference-count":35,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T00:00:00Z","timestamp":1624492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["101017109"],"award-info":[{"award-number":["101017109"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This problem is even worse in new standards, such as 802.11n\/ac, where new features such as Channel Bonding (CB) are introduced to increase network capacity but at the cost of using wider spectrum channels. Finding the best channel assignment in dense deployments under dynamic environments with CB is challenging, given its combinatorial nature. Therefore, the use of analytical or system models to predict Wi-Fi performance after potential changes (e.g., dynamic channel selection with CB, and the deployment of new devices) are not suitable, due to either low accuracy or high computational cost. This paper presents a novel, data-driven approach to speed up this process, using a Graph Neural Network (GNN) model that exploits the information carried in the deployment\u2019s topology and the intricate wireless interactions to predict Wi-Fi performance with high accuracy. The evaluation results show that preserving the graph structure in the learning process obtains a 64% increase versus a naive approach, and around 55% compared to other Machine Learning (ML) approaches when using all training features.<\/jats:p>","DOI":"10.3390\/s21134321","type":"journal-article","created":{"date-parts":[[2021,6,24]],"date-time":"2021-06-24T23:22:14Z","timestamp":1624576934000},"page":"4321","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5906-6424","authenticated-orcid":false,"given":"Paola","family":"Soto","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Antwerp\u2014imec, 2000 Antwerp, Belgium"},{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8152-7143","authenticated-orcid":false,"given":"Miguel","family":"Camelo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp\u2014imec, 2000 Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4812-4841","authenticated-orcid":false,"given":"Kevin","family":"Mets","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp\u2014imec, 2000 Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesc","family":"Wilhelmi","sequence":"additional","affiliation":[{"name":"Centre Tecnol\u00f2gic de Telecomunicacions de Catalunya, 08860 Castelldefels, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"G\u00f3ez","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1294-137X","authenticated-orcid":false,"given":"Luis A.","family":"Fletscher","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natalia","family":"Gaviria","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Hellinckx","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp\u2014imec, 2000 Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7072-8924","authenticated-orcid":false,"given":"Juan F.","family":"Botero","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Latr\u00e9","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp\u2014imec, 2000 Antwerp, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,24]]},"reference":[{"key":"ref_1","unstructured":"CISCO (2020). CISCO Annual Internet Report (2018\u20132023) White Paper, CISCO."},{"key":"ref_2","unstructured":"IEEE (2021). IEEE 802.11ax-2021\u2014IEEE Standard for Information Technology\u2014Telecommunications and Information Exchange between Systems Local and Metropolitan Area Networks\u2014Specific Requirements Part 11: Wireless LAN Medium Access Control (MAC) and Physical Layer (PHY) Specifications Amendment 1: Enhancements for High-Efficiency WLAN, IEEE. Draft."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1242","DOI":"10.1109\/TMC.2013.73","article-title":"Intelligent channel bonding in 802.11 n WLANs","volume":"13","author":"Deek","year":"2013","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Park, M. (2011, January 5\u20139). IEEE 802.11 ac: Dynamic bandwidth channel access. Proceedings of the 2011 IEEE International Conference on Communications (ICC), Kyoto, Japan.","DOI":"10.1109\/icc.2011.5963089"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Qiu, L., Zhang, Y., Wang, F., Han, M.K., and Mahajan, R. (2007, January 9\u201314). A general model of wireless interference. Proceedings of the 13th Annual ACM International Conference on Mobile Computing and Networking, Montreal, QC, Canada.","DOI":"10.1145\/1287853.1287874"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1109\/49.840210","article-title":"Performance analysis of the IEEE 802.11 distributed coordination function","volume":"18","author":"Bianchi","year":"2000","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/MWC.001.2000206","article-title":"Usage of Network Simulators in Machine-Learning-Assisted 5G\/6G Networks","volume":"28","author":"Wilhelmi","year":"2021","journal-title":"IEEE Wirel. Commun."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Barrachina-Munoz, S., Wilhelmi, F., Selinis, I., and Bellalta, B. (2019, January 24\u201326). Komondor: A wireless network simulator for next-generation high-density WLANs. Proceedings of the 2019 Wireless Days (WD), Manchester, UK.","DOI":"10.1109\/WD.2019.8734225"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"8330","DOI":"10.1109\/TWC.2020.3021597","article-title":"A Deep Probabilistic Control Machinery for Auto-Configuration of WiFi Link Parameters","volume":"19","author":"Karmakar","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Daldoul, Y., Meddour, D.E., and Ksentini, A. (2017, January 21\u201325). IEEE 802.11 ac: Effect of channel bonding on spectrum utilization in dense environments. Proceedings of the 2017 IEEE International Conference on Communications (ICC), Paris, France.","DOI":"10.1109\/ICC.2017.7997013"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2118","DOI":"10.1109\/TMC.2016.2615305","article-title":"Analysis of dynamic channel bonding in dense networks of WLANs","volume":"16","author":"Faridi","year":"2016","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1109\/TMC.2019.2899835","article-title":"Dynamic Channel Bonding in Spatially Distributed High-Density WLANs","volume":"19","author":"Wilhelmi","year":"2020","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102499","DOI":"10.1016\/j.jnca.2019.102499","article-title":"Real-time throughput prediction for cognitive Wi-Fi networks","volume":"150","author":"Khan","year":"2020","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Herzen, J., Lundgren, H., and Hegde, N. (2015, January 22\u201325). Learning wi-fi performance. Proceedings of the 2015 12th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON), Seattle, WA, USA.","DOI":"10.1109\/SAHCN.2015.7338298"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"11868","DOI":"10.1109\/TVT.2020.3006218","article-title":"Learning to Bond in Dense WLANs With Random Traffic Demands","volume":"69","author":"Luo","year":"2020","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/MWC.2016.7422404","article-title":"IEEE 802.11 ax: High-efficiency WLANs","volume":"23","author":"Bellalta","year":"2016","journal-title":"IEEE Wirel. Commun."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/MCOM.001.1900338","article-title":"IEEE 802.11 be extremely high throughput: The next generation of Wi-Fi technology beyond 802.11 ax","volume":"57","author":"Kasslin","year":"2019","journal-title":"IEEE Commun. Mag."},{"key":"ref_18","unstructured":"ITU-T (2019). ITU-T Y.3172-Series\u2014Architectural Framework for Machine Learning in Future Networks Including IMT-2020, ITU-T. Recommendation."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_20","unstructured":"Fey, M., and Lenssen, J.E. (2019). Fast Graph Representation Learning with PyTorch Geometric. arXiv."},{"key":"ref_21","unstructured":"Bello, I., Pham, H., Le, Q.V., Norouzi, M., and Bengio, S. (2016). Neural combinatorial optimization with reinforcement learning. arXiv."},{"key":"ref_22","unstructured":"Battaglia, P.W., Hamrick, J.B., Bapst, V., Sanchez-Gonzalez, A., Zambaldi, V., Malinowski, M., Tacchetti, A., Raposo, D., Santoro, A., and Faulkner, R. (2018). Relational inductive biases, deep learning, and graph networks. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rusek, K., Su\u00e1rez-Varela, J., Mestres, A., Barlet-Ros, P., and Cabellos-Aparicio, A. (2019, January 3). Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN. Proceedings of the 2019 ACM Symposium on SDN Research, San Jose, CA, USA.","DOI":"10.1145\/3314148.3314357"},{"key":"ref_24","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_25","unstructured":"Wilhelmi, F. (2020, December 06). [ITU-T AI Challenge] Input\/Output of Project \u201cImproving the Capacity of IEEE 802.11 WLANs through Machine Learning. Available online: https:\/\/zenodo.org\/record\/4106127#.YNBwAJMzZB0."},{"key":"ref_26","unstructured":"Barrachina-Mu\u00f1oz, S., and Wilhelmi, F. (2021, June 21). Komondor: An IEEE 802.11ax Simulator. Available online: https:\/\/github.com\/wn-upf\/Komondor."},{"key":"ref_27","first-page":"527","article-title":"Network simulations with the ns-3 simulator","volume":"14","author":"Henderson","year":"2008","journal-title":"SIGCOMM Demonstr."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Bellalta, B., Zocca, A., Cano, C., Checco, A., Barcelo, J., and Vinel, A. (2014). Throughput analysis in CSMA\/CA networks using continuous time Markov networks: A tutorial. Wirel. Netw. Mov. Obj., 115\u2013133.","DOI":"10.1007\/978-3-319-14116-9_7"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Barrachina-Mu\u00f1oz, S., Bellalta, B., and Knightly, E. (2020, January 21). Wi-Fi All-Channel Analyzer. Proceedings of the 14th International Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization (WiNTECH), London, UK.","DOI":"10.1145\/3411276.3412190"},{"key":"ref_30","unstructured":"IEEE (2021, June 15). TGax Simulation Scenarios. Doc.: IEEE 802.11-14\/0980r16. Available online: https:\/\/mentor.ieee.org\/802.11\/dcn\/14\/11-14-0980-16-00ax-simulation-scenarios.docx."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Adame, T., Carrascosa, M., and Bellalta, B. (2019, January 24\u201326). The TMB path loss model for 5 GHz indoor WiFi scenarios: On the empirical relationship between RSSI, MCS, and spatial streams. Proceedings of the 2019 Wireless Days (WD), Manchester, UK.","DOI":"10.1109\/WD.2019.8734243"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Deek, L., Garcia-Villegas, E., Belding, E., Lee, S.J., and Almeroth, K. (2011, January 6\u20139). The impact of channel bonding on 802.11 n network management. Proceedings of the 7th Conference on emerging Networking Experiments and Technologies, Tokyo, Japan.","DOI":"10.1145\/2079296.2079307"},{"key":"ref_33","unstructured":"IETF (2019). Intent-Based Networking\u2013Concepts and Overview, IETF."},{"key":"ref_34","unstructured":"ETSI (2020). Zero-Touch Network and Service Management (ZSM): Means of Automation, ETSI."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4321\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:23:00Z","timestamp":1760163780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,24]]},"references-count":35,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["s21134321"],"URL":"https:\/\/doi.org\/10.3390\/s21134321","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,24]]}}}