aiOS: An Intelligence Layer for SD-WLANs

Software-Defined Networking promises to deliver a more manageable network whose behaviour could be easily changed using applications written in high-level declarative languages running on top of a logically centralized control plane resulting, on the one hand, in the mushrooming of complex point solutions to very specific problems and, on the other hand, in the creation of a multitude of network configuration options. This fact is especially true for 802.11-based Software-Defined WLANs (SD-WLANs). It is our standpoint that to tame this increase in complexity, future SD-WLANs must follow an Artificial Intelligence (AI) native approach. In this paper we present aiOS, an AI-based Operating System for SD-WLANs. Then, we use aiOS to implement several Machine Learning (ML) models for user-adaptive frame length selection in SD-WLANs. An extensive performance evaluation carried out on a real-world testbed shows that this approach improves the aggregated network throughput by up to 55%. Finally, we release the entire implementation including the controller, the ML models, and the programmable data-path under a permissive license for academic use.

[1]  Mohd Dani Baba,et al.  Performance analysis of fair scheduler for A-MSDU aggregation in IEEE802.11n wireless networks , 2014, 2014 2nd International Conference on Electrical, Electronics and System Engineering (ICEESE).

[2]  Mugen Peng,et al.  Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues , 2018, IEEE Communications Surveys & Tutorials.

[3]  Georgios Kambourakis,et al.  Intrusion Detection in 802.11 Networks: Empirical Evaluation of Threats and a Public Dataset , 2016, IEEE Communications Surveys & Tutorials.

[4]  Young-Tak Kim,et al.  QoS-aware adaptive A-MPDU aggregation scheduler for enhanced VoIP capacity over aggregation-enabled WLANs , 2018, NOMS 2018 - 2018 IEEE/IFIP Network Operations and Management Symposium.

[5]  Gautam D. Bhanage.  AMSDU vs AMPDU: A Brief Tutorial on WiFi Aggregation Support , 2017, ArXiv.

[6]  Mahesh K. Marina,et al.  Characterization of 802.11n wireless LAN performance via testbed measurements and statistical analysis , 2013, 2013 IEEE International Conference on Sensing, Communications and Networking (SECON).

[7]  Paola Zuccolotto,et al.  Variable Selection Using Random Forests , 2006 .

[8]  Steven D. Blostein,et al.  Joint rate adaptation, frame aggregation and MIMO mode selection for IEEE 802.11ac , 2016, 2016 IEEE Wireless Communications and Networking Conference.

[9]  David Walker,et al.  Languages for software-defined networks , 2013, IEEE Communications Magazine.

[10]  Lotfi Kamoun,et al.  Dynamic frame aggregation scheduler for multimedia applications in IEEE 802.11n networks , 2017, Trans. Emerg. Telecommun. Technol..

[11]  Hsiao-Hwa Chen,et al.  IEEE 802.11n MAC frame aggregation mechanisms for next-generation high-throughput WLANs , 2008, IEEE Wireless Communications.

[12]  Vincent W. S. Wong,et al.  WSN01-1: Frame Aggregation and Optimal Frame Size Adaptation for IEEE 802.11n WLANs , 2006, IEEE Globecom 2006.

[13]  Jose Miguel Villalón Millán,et al.  Lasagna: Programming Abstractions for End-to-End Slicing in Software-Defined WLANs , 2018, 2018 IEEE 19th International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM).

[14]  F.Y. Li,et al.  Link adaptation with combined optimal frame size and rate selection in error-prone 802.11n networks , 2008, 2008 IEEE International Symposium on Wireless Communication Systems.

[15]  Mohamed Othman,et al.  A Reliable A-MSDU Frame Aggregation Scheme in 802.11n Wireless Networks , 2013, EUSPN/ICTH.

[16]  Klaus David,et al.  6G Vision and Requirements: Is There Any Need for Beyond 5G? , 2018, IEEE Vehicular Technology Magazine.

[17]  Hyuck M. Kwon,et al.  PHY-Supported Frame Aggregation for Wireless Local Area Networks , 2014, IEEE Transactions on Mobile Computing.

[18]  Xiaoli Zhou,et al.  AFLAS: An Adaptive Frame Length Aggregation Scheme for Vehicular Networks , 2017, IEEE Transactions on Vehicular Technology.

[19]  Özgür Gürbüz,et al.  QoS based aggregation in high speed IEEE802.11 wireless networks , 2016, 2016 Mediterranean Ad Hoc Networking Workshop (Med-Hoc-Net).

[20]  David Walker,et al.  Frenetic: a network programming language , 2011, ICFP.

[21]  Liljana Gavrilovska,et al.  Learning and Reasoning in Cognitive Radio Networks , 2013, IEEE Communications Surveys & Tutorials.

[22]  PROPAGATION DATA AND PREDICTION METHODS FOR THE PLANNING OF INDOOR RADIOCOMMUNICATION SYSTEMS AND RADIO LOCAL AREA NETWORKS IN THE FREQUENCY RANGE 900 MHz TO 100 GHz , 1997 .

[23]  David Malone,et al.  Aggregation With Fragment Retransmission for Very High-Speed WLANs , 2009, IEEE/ACM Transactions on Networking.

[24]  Sunghyun Choi,et al.  MoFA: Mobility-aware Frame Aggregation in Wi-Fi , 2014, CoNEXT.

[25]  Ho Young Hwang,et al.  A-MPDU aggregation with optimal number of MPDUs for delay requirements in IEEE 802.11ac , 2019, PloS one.

[26]  Ursula Challita,et al.  Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial , 2017, IEEE Communications Surveys & Tutorials.

[27]  Eun-Chan Park,et al.  Adaptive Two-Level Frame Aggregation for Fairness and Efficiency in IEEE 802.11n Wireless LANs , 2015, Mob. Inf. Syst..

[28]  Qi Hao,et al.  Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey , 2018, IEEE Communications Surveys & Tutorials.

[29]  R. A. Rahman,et al.  A-MSDU real time traffic scheduler for IEEE802.11n WLANs , 2012, 2012 IEEE Symposium on Wireless Technology and Applications (ISWTA).

[30]  Changle Li,et al.  An efficient adaptive frame aggregation scheme in vehicular Ad Hoc networks , 2017, 2017 9th International Conference on Wireless Communications and Signal Processing (WCSP).

[31]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[32]  Jose Saldana,et al.  Frame Aggregation in Central Controlled 802.11 WLANs: The Latency Versus Throughput Tradeoff , 2017, IEEE Communications Letters.

[33]  Wei Chen,et al.  The Roadmap to 6G: AI Empowered Wireless Networks , 2019, IEEE Communications Magazine.

[34]  Mahesh K. Marina,et al.  Programming Abstractions for Software-Defined Wireless Networks , 2015, IEEE Transactions on Network and Service Management.

[35]  Qiang Fu,et al.  Evaluation of the Minstrel rate adaptation algorithm in IEEE 802.11g WLANs , 2013, 2013 IEEE International Conference on Communications (ICC).

[36]  Sunshin An,et al.  Throughput enhancement by Dynamic Frame Aggregation in multi-rate WLANs , 2012, 2012 19th IEEE Symposium on Communications and Vehicular Technology in the Benelux (SCVT).

[37]  Hyuncheol Park,et al.  Adaptive frame size estimation using extended Kalman filter for high-stressed WLANs , 2012, 2012 IEEE 23rd International Symposium on Personal, Indoor and Mobile Radio Communications - (PIMRC).

[38]  Xin Jin,et al.  SoftCell: scalable and flexible cellular core network architecture , 2013, CoNEXT.

[39]  Evgeny Khorov,et al.  A Tutorial on IEEE 802.11ax High Efficiency WLANs , 2019, IEEE Communications Surveys & Tutorials.

[40]  Gérard Biau,et al.  Analysis of a Random Forests Model , 2010, J. Mach. Learn. Res..

[41]  Thierry Turletti,et al.  IEEE 802.11 rate adaptation: a practical approach , 2004, MSWiM '04.