{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T18:28:25Z","timestamp":1780338505432,"version":"3.54.1"},"reference-count":78,"publisher":"Association for Computing Machinery (ACM)","issue":"CoNEXT1","license":[{"start":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T00:00:00Z","timestamp":1741132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF","doi-asserted-by":"publisher","award":["2212200"],"award-info":[{"award-number":["2212200"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Netw."],"published-print":{"date-parts":[[2025,3,5]]},"abstract":"<jats:p>Wi-Fi is an integral part of today's Internet infrastructure, enabling a diverse range of applications and services. Prior approaches to Wi-Fi resource allocation optimized Quality of Service (QoS) metrics, which often do not accurately reflect the user's Quality of Experience (QoE). To address the gap between QoS and QoE, we introduce Maestro, an adaptive method that formulates the Wi-Fi resource allocation problem as a partially observable Markov decision process (PO-MDP) to maximize the overall system QoE and QoE fairness. Maestro estimates QoE without using any application or client data; instead, it treats them as black boxes and leverages temporal dependencies in network telemetry data. Maestro dynamically adjusts policies to handle different classes of applications and variable network conditions. Additionally, Maestro uses a simulation environment for practical training. We evaluate Maestro in an enterprise-level Wi-Fi testbed with a variety of applications, and find that Maestro achieves up to 25\u00d7 and 78% improvement in QoE and fairness, respectively, compared to the widely-deployed Wi-Fi Multimedia (WMM) policy. Compared to the state-of-the-art learning approach QFlow, Maestro increases QoE by up to 69%. Unlike QFlow which requires modifications to clients, we demonstrate that Maestro improves QoE of popular over-the-top services with unseen traffic without control over clients or servers.<\/jats:p>","DOI":"10.1145\/3709371","type":"journal-article","created":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T12:15:54Z","timestamp":1741263354000},"page":"1-24","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Maestro: QoE-Aware Dynamic Resource Allocation in Wi-Fi Networks"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9452-4504","authenticated-orcid":false,"given":"Umakant","family":"Kulkarni","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, IN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1986-5104","authenticated-orcid":false,"given":"Khaled","family":"Diab","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3408-9050","authenticated-orcid":false,"given":"Lianjie","family":"Cao","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0688-6394","authenticated-orcid":false,"given":"Faraz","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7190-5478","authenticated-orcid":false,"given":"Shivang","family":"Aggarwal","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4594-8164","authenticated-orcid":false,"given":"Puneet","family":"Sharma","sequence":"additional","affiliation":[{"name":"Hewlett Packard Labs, Milpitas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-7166","authenticated-orcid":false,"given":"Sonia","family":"Fahmy","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,6]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEEESTD.2021.9363693"},{"key":"e_1_2_1_2_1","unstructured":"8i 2024. 8i Voxelized Surface Light Field (8iVSLF) Dataset. https:\/\/mpeg-pcc.org\/index.php\/pcc-content-database\/8ivoxelized-surface-light-field-8ivslf-dataset\/."},{"key":"e_1_2_1_3_1","unstructured":"Air Slice 2024. Air Slice. https:\/\/www.arubanetworks.com\/techdocs\/ArubaOS_8.11.0_Web_Help\/Content\/arubaossolutions\/access-points\/airslice.htm."},{"key":"e_1_2_1_4_1","unstructured":"Wi-Fi Alliance. 2024. WMM. https:\/\/www.wi-fi.org\/discover-wi-fi\/specifications."},{"key":"e_1_2_1_5_1","unstructured":"AStream 2024. AStream: A rate adaptation model for DASH. https:\/\/github.com\/pari685\/AStream."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2017.2669216"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3106675"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2890955.2890972"},{"key":"e_1_2_1_9_1","volume-title":"Wireless On-Demand Network Systems","author":"Bruno Raffaele","unstructured":"Raffaele Bruno, Marco Conti, and Enrico Gregori. 2004. Throughput Evaluation and Enhancement of TCP Clients in Wi-Fi Hot Spots. In Wireless On-Demand Network Systems, Roberto Battiti, Marco Conti, and Renato Lo Cigno (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 73--86."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.003.2300264"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2518025.2518033"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2999572.2999597"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2012.6477773"},{"key":"e_1_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Xi Chen Zonghang Li Yupeng Zhang Ruiming Long Hongfang Yu Xiaojiang Du and Mohsen Guizani. 2018. Reinforcement Learning based QoS\/QoE-aware Service Function Chaining in Software-Driven 5G Slices. arXiv:1804.02099 [cs.NI]","DOI":"10.1002\/ett.3477"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2018.8463409"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2602281"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604822"},{"key":"e_1_2_1_19_1","volume-title":"Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, and Rishabh Agarwal.","author":"Farebrother Jesse","year":"2024","unstructured":"Jesse Farebrother, Jordi Orbay, Quan Vuong, Adrien Ali Taiga, Yevgen Chebotar, Ted Xiao, Alex Irpan, Sergey Levine, Pablo Samuel Castro, Aleksandra Faust, Aviral Kumar, and Rishabh Agarwal. 2024. Stop Regressing: Training Value Functions via Classification for Scalable Deep RL. arXiv:2403.03950"},{"key":"e_1_2_1_20_1","volume-title":"Telecommunications Commission, and Heavy Reading","author":"Finnie G.","year":"2009","unstructured":"G. Finnie, Canadian Radio-Television, Telecommunications Commission, and Heavy Reading (Organization). 2009. ISP Traffic Management Technologies: The State of the Art : Report. Canadian Radio Television and Telecommunications Commission. https:\/\/books.google.com\/books?id=zUisDAEACAAJ"},{"key":"e_1_2_1_21_1","unstructured":"Google 2024. WebRTC. https:\/\/webrtc.org\/"},{"key":"e_1_2_1_22_1","doi-asserted-by":"crossref","unstructured":"DSP Group Graham Smith. 2008. 802.11 QoS Tutorial. https:\/\/ieee802.org\/1\/files\/public\/docs2008\/avb-gs-802--11-qostutorial-1108.pdf.","DOI":"10.1038\/ngeo343"},{"key":"e_1_2_1_23_1","unstructured":"Gymnasium 2024. Gymnasium. https:\/\/gymnasium.farama.org\/."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2018.2805718"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2616342"},{"key":"e_1_2_1_27_1","unstructured":"HPE Aruba Networking 2024. Aruba 550 Series Indoor Access Points. https:\/\/www.arubanetworks.com\/products\/wireless\/access-points\/indoor-access-points\/550-series\/."},{"key":"e_1_2_1_28_1","unstructured":"HPE Aruba Networking 2024. Aruba 7000 Series Mobility Controllers and Gateways. https:\/\/www.arubanetworks.com\/products\/wireless\/gateways-and-controllers\/7000-series\/."},{"key":"e_1_2_1_29_1","unstructured":"HPE Aruba Networking 2024. HPE Aruba Networking Mobility Conductor. https:\/\/www.arubanetworks.com\/resource\/hpe-aruba-networking-mobility-conductor\/."},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2019.109439"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOTEH51037.2021.9400661"},{"key":"e_1_2_1_33_1","volume-title":"Martin Mladenov, Vihan Jain, Sanmit Narvekar, Jing Wang, Rui Wu, and Craig Boutilier.","author":"Ie Eugene","year":"2019","unstructured":"Eugene Ie, Chih wei Hsu, Martin Mladenov, Vihan Jain, Sanmit Narvekar, Jing Wang, Rui Wu, and Craig Boutilier. 2019. RecSim: A Configurable Simulation Platform for Recommender Systems. arXiv:1909.04847"},{"key":"e_1_2_1_34_1","unstructured":"iperf 2024. iPerf3. https:\/\/iperf.fr\/."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2016.7841518"},{"key":"e_1_2_1_36_1","first-page":"1","article-title":"A quantitative measure of fairness and discrimination. Eastern Research Laboratory, Digital Equipment Corporation, Hudson","volume":"21","author":"Jain Rajendra K","year":"1984","unstructured":"Rajendra K Jain, Dah-MingWChiu, William R Hawe, et al. 1984. A quantitative measure of fairness and discrimination. Eastern Research Laboratory, Digital Equipment Corporation, Hudson, MA 21 (1984), 1.","journal-title":"MA"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/645526.657142"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPSR57248.2023.10147938"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3609395.3610599"},{"key":"e_1_2_1_40_1","volume-title":"Austin Reiter, and Gregory D. Hager","author":"Lea Colin","year":"2016","unstructured":"Colin Lea, Ren\u00e9 Vidal, Austin Reiter, and Gregory D. Hager. 2016. Temporal Convolutional Networks: A Unified Approach to Action Segmentation. In Computer Vision -- ECCV 2016 Workshops, Gang Hua and Herv\u00e9 J\u00e9gou (Eds.). Springer International Publishing, Cham, 47--54."},{"key":"e_1_2_1_41_1","volume-title":"Zhaoran Wang, and Jian Guo.","author":"Liu Xiao-Yang","year":"2022","unstructured":"Xiao-Yang Liu, Ziyi Xia, Jingyang Rui, Jiechao Gao, Hongyang Yang, Ming Zhu, Christina Dan Wang, Zhaoran Wang, and Jian Guo. 2022. FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning. NeurIPS (2022)."},{"key":"e_1_2_1_42_1","unstructured":"Maestro project. 2025. Telemetry Data Items. https:\/\/gist.github.com\/UmakantKulkarni\/1fe2ac6f82fdc65d6e9e87e9ca1ebd83."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.23919\/TMA.2018.8506519"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3204949.3204956"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2342541.2342548"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2012.6364944"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","unstructured":"Fatemeh Shah Mohammadi and Andres Kwasinski. 2018. QoE-Driven Integrated Heterogeneous Traffic Resource Allocation Based on Cooperative Learning for 5G Cognitive Radio Networks. In 2018 IEEE 5G World Forum (5GWF). 244--249. https:\/\/doi.org\/10.1109\/5GWF.2018.8516939","DOI":"10.1109\/5GWF.2018.8516939"},{"key":"e_1_2_1_48_1","unstructured":"C. Molnar. 2020. Interpretable Machine Learning. Leanpub. https:\/\/books.google.com\/books?id=jBm3DwAAQBAJ"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.02.032"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2814204.2814205"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/SEC.2018.00011"},{"key":"e_1_2_1_52_1","unstructured":"Peach Open Movie Project 2024. Big Buck Bunny. https:\/\/media.xiph.org\/video\/derf\/\/y4m\/big_buck_bunny_1080p24.y4m.xz."},{"key":"e_1_2_1_53_1","unstructured":"Quantile Transformer 2024. QuantileTransformer: Transform features using quantiles information. https:\/\/scikitlearn.org\/stable\/modules\/generated\/sklearn.preprocessing.QuantileTransformer.html."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-020-01441-z"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2012.120806"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS54207.2022.9789864"},{"key":"e_1_2_1_57_1","volume-title":"Potree: Rendering Large Point Clouds in Web Browsers. Master's thesis","author":"Schutz Markus","year":"2016","unstructured":"Markus Schutz. 2016. Potree: Rendering Large Point Clouds in Web Browsers. Master's thesis. Institute of Computer Graphics and Algorithms, Vienna University of Technology."},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/2620728.2620766"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618257.3624828"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2927588"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177012580"},{"key":"e_1_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2018.1800022"},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849366"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2012.6364307"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.10.016"},{"key":"e_1_2_1_66_1","unstructured":"WebRTC Samples 2024. WebRTC Samples. https:\/\/github.com\/webrtc\/samples."},{"key":"e_1_2_1_67_1","unstructured":"WebRTC Stats 2024. Identifiers for WebRTC's Statistics API. https:\/\/w3c.github.io\/webrtc-stats\/."},{"key":"e_1_2_1_68_1","volume-title":"NIC 2024","author":"Wireless","year":"2048","unstructured":"Wireless NIC 2024. Intel Wi-Fi 6E AX210. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/204836\/intel-wifi- 6e-ax210-gig\/specifications.html."},{"key":"e_1_2_1_69_1","unstructured":"WMM Traffic Management 2024. WMM Traffic Management. https:\/\/www.arubanetworks.com\/techdocs\/Instant_85_WebHelp\/Content\/instant-ug\/voice-and-video\/wmm-traffic-mgmt.htm."},{"key":"e_1_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2014.7037549"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2015.7417656"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/2829988.2787486"},{"key":"e_1_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2014.6953124"},{"key":"e_1_2_1_74_1","unstructured":"YouTube 2024. Talking Head. https:\/\/www.youtube.com\/watch?v=hWTT4J_xNwY."},{"key":"e_1_2_1_75_1","unstructured":"YouTube Video 2024. YouTube Video. https:\/\/www.youtube.com\/watch?v=X1oyKzWAwYU."},{"key":"e_1_2_1_76_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Zhang Jia","year":"2023","unstructured":"Jia Zhang, Yixuan Zhang, Enhuan Dong, Yan Zhang, Shaorui Ren, Zili Meng, Mingwei Xu, Xiaotian Li, Zongzhi Hou, Zhicheng Yang, and Xiaoming Fu. 2023. Bridging the Gap between QoE and QoS in Congestion Control: A Large-scale Mobile Web Service Perspective. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). USENIX Association, Boston, MA, 553--569. https:\/\/www.usenix.org\/conference\/atc23\/presentation\/zhang-jia"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00051"},{"key":"e_1_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2019.8756710"}],"container-title":["Proceedings of the ACM on Networking"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709371","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T18:41:42Z","timestamp":1755974502000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,5]]},"references-count":78,"journal-issue":{"issue":"CoNEXT1","published-print":{"date-parts":[[2025,3,5]]}},"alternative-id":["10.1145\/3709371"],"URL":"https:\/\/doi.org\/10.1145\/3709371","relation":{},"ISSN":["2834-5509"],"issn-type":[{"value":"2834-5509","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,5]]},"assertion":[{"value":"2025-03-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}