Abstract
Fixed Wireless Networks (FWNs) provide an alternative means for internet connectivity in rural and harsh propagation environments. Intensive technical expertise is therefore crucial for the planning and the optimization of such wireless links, as multiple difficult to estimate parameters are involved. It should be noted that a connection to a convenient Access Point (AP) is necessary to the establishment of efficient communication services in FWN. In this paper, we propose two algorithms that predict the success of a user association to FWN via the analysis of user feedback and subscription status, in combination with radio frequency parameters. These approaches are based on supervised machine learning where data is collected from a wide Canadian FWN. The first algorithm is based on the Nearest Neighbor concept, for which a new distance function is proposed. In the second algorithm, named Deep Nearest Neighbor, we extract the distance function with an artificial neural network. The accuracy of each of these algorithms is 86%. Additionally, we develop an AP selection scheme based on deep imitation learning to predict the success of a user-AP association. This model has a better accuracy of 94% since it combines a wide variety of parameters, use cases and conditions.

















































Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Sun, Y., Peng, M., Y. Zhou, Huang, Y. & Mao S. (Fourth quarter 2019). Application of machine learning in wireless networks: Key techniques and open issues, IEEE Communications Surveys and Tutorials, 21(4), 3072–3108.
El Khaled, Z. & Mcheick, H. (2019). Case studies of communications systems during harsh environments: A review of approaches, weaknesses, and limitations to improve quality of service. International Journal of Distributed Sensor Networks, 15(2).
El Khaled, Z., Mcheick, H., & Ajami, H. (2016). Wide range WiFi network formal design model for ubiquitous emergency events, In Proc. of Int. Conf. on Future Nets. and Comm., Montreal, Canada.
Bell Canada (2021). https://www.bell.ca/Bell_Internet/promotions/wireless-home-internet.
Mishra, A. (2018). Radio network planning and optimization. In Fundamentals of network planning and optimization: 2G/3G/4G... Evolution to 5G, Wiley, 2nd ed.
Zappone, A., Di Renzo, M., & Debbah, M. (2019). Wireless networks design in the era of deep learning: Model-Based, AI-Based, or Both? IEEE Transactions on Communications, 67(10), 7331–7376.
Maghsudi, S., & Hossain, E. (2017). Distributed UA in energy harvesting dense small cell networks: A mean-field multi-armed bandit approach. IEEE Access, 5, 3513–3523.
Li, Z., Wang, C., & Jiang, C. J. (2017). UA for load balancing in vehicular networks: An online reinforcement learning approach. IEEE Transactions on Intelligent Transportation Systems, 18(8), 2217–2228.
Zhao, N., Liang, Y., Niyato, D., Pei, Y., Wu, M., & Jiang, Y. (2019). Deep reinforcement learning for user association and resource allocation in heterogeneous cellular networks. IEEE Transactions on Wireless Communications, 18(11), 5141–5152. https://doi.org/10.1109/TWC.2019.2933417
Kim, H., de Veciana, G., Yang, X., & Venkatachalam, M. (2012). Distributed α-Optimal UA and cell load balancing in wireless networks. IEEE/ACM Transactions on Networking, 20(1), 177–190.
Attiah, M. L., Isa, A. A. M., Zakaria, Z., et al. (2020). A survey of mmWave UA mechanisms and spectrum sharing approaches: An overview, open issues and challenges, future research trends. Wireless Networks, 26, 2487–2514.
Carrascosa, M., Bellalta, B. Multi-Armed Bandits for Decentralized AP selection in Enterprise WLANs, arXiv preprint arXiv:2001.00392
Tan, J., Xiao, S., Han, S., Liang, Y., & Leung, V. C. M. (2019). QoS-Aware UA and resource allocation in LAA-LTE/WiFi coexistence systems. IEEE Transactions on Wireless Communications, 18(4), 2415–2430.
Xu, C., Wang, J., Zhu, Z., & Niyato, D. (2019). Energy-efficient WLANs with resource and re-association scheduling optimization. IEEE Transactions on Network and Service Management, 16(2), 563–577.
Kafi, M. A., Mouradian, A., & Vèque, V.: Online Client Association Scheme Based on Reinforcement Learning for WLAN Networks" In Proc. of IEEE Wireless Comm. and Net. Conf. (WCNC), Marrakesh, Morocco, 2019, pp. 1–7.
Xu, W., Hua, C., & Huang, A. (2011). Channel Assignment and UA Game in Dense 802.11 Wireless Networks, In proc. of IEEE Int. Conf. on Comm. (ICC), Kyoto, pp. 1–5
Klaine, P. V., Jaber, M., Souza, R. D., & Imran, M. A. (2019). Backhaul aware user-specific cell association using Q-learning. IEEE Transactions on Wireless Communications, 18(7), 3528–3541.
Ha, D. T. (2019). Optimized resource allocation and user/cell association for future dense networks, Networking and Internet Architecture [cs.NI], Université Paris-Saclay. English. NNT: 2019SACLS290, Tel-02341472
Lyu, F., Fang, L., Xue, G., Xue, H., & Li, M. (2019). Large-scale full wifi coverage: Deployment and management strategy based on user Spatio-Temporal association analytics. IEEE Internet of Things Journal, 6(6), 9386–9398.
Kim, S., Lee, K., Kim, Y., Shin, J., Shin, S., & Chong, S. (2020). Dynamic control for on-demand interference-managed WLAN infrastructures. IEEE/ACM Transactions on Networking, 28(1), 84–97.
Dwijaksara, M. H., Jeon, W. S., & Jeong, D. G. (2019). UA for load balancing and energy saving in enterprise WLANs. IEEE Systems Journal, 13(3), 2700–2711.
Anany, M., Elmesalawy, M. M., & Abd El-Haleem, A. M. (2019). Matching game-based cell association in Multi-RAT HetNet considering device requirements, In IEEE Internet of Things Journal, 6(6), 9774–9782
Elmosilhy, N. A., Elmesalawy, M. M., & Abd Elhaleem, A. M. (2019). UA With Mode Selection in LWA-Based Multi-RAT HetNet, In IEEE Access, 7, 158623–158633.
Bojovic, B., Baldo, N., Nin-Guerrero, J., Dini, P. (2011). A supervised learning approach to cognitive access point selection, In Proceedings of IEEE GLOBECOM Workshops (GC Wkshps), Houston, TX, pp. 1100–1105
Tang, H., Yang, L., Dong, J., et al. (2016). Throughput optimization via association control in wireless LANs. Mobile Networks and Applications, 21, 453–466.
Carrascosa, M., & Bellalta, B. (2019). Decentralized APS using Multi-Armed Bandits: Opportunistic ε-Greedy with Stickiness, arXiv, arXiv:1903.00281
Raschellà, A., Bouhafs, F., Mackay, M., Shi, Q., Ortin, J., Gallego, J. R., Canales, M. (2020). A dynamic access point allocation algorithm for dense wireless lans using potential game. Computer Networks, 167.
Zheng, R., Hua, C. (2016). Channel Selection and UA in WiFi Networks. In: Sequential Learning and Decision-Making in Wireless Resource Management. Wireless Networks. Springer
Khalili, A., Akhlaghi, S., Tabassum, H., & Ng, D. W. K. (2020). Joint user association and resource allocation in the uplink of heterogeneous networks. IEEE Wireless Communications Letters, 9(6), 804–808. https://doi.org/10.1109/LWC.2020.2970696
Chaieb, C., Mlika, Z., Abdelkefi, F. & Ajib, W. On the optimization of user association and resource allocation in HetNets with mm-wave base stations, In IEEE Systems Journal, https://doi.org/10.1109/JSYST.2020.2984596
Zhang, H., Zhang, H., Long, K., & Karagiannidis, G. Deep learning based radio resource management in NOMA Networks: User Association, Subchannel and Power Allocation, In IEEE Transactions on Network Science and Engineering, https://doi.org/10.1109/TNSE.2020.3004333
Huang, X., Xu, W., Xie, G., Jin, S., & You, X. (2018). Learning oriented cross-entropy approach to user association in load-balanced HetNet. IEEE Wireless Communications Letters, 7(6), 1014–1017. https://doi.org/10.1109/LWC.2018.2846610
El Khaled, Z., Mcheick, H., & Petrillo, F., (2019). Wifi coverage range characterization for smart space applications. In Proceedings of the 1st International Workshop on Software Engineering Research and Practices for the Internet of Things (SERP4IoT’19). IEEE Press, 61–68. https://doi.org/10.1109/SERP4IoT.2019.00018.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, É. (2011). Scikit-learn: Machine learning in python. Journal of Machine Learning Research, 12, 2825–2830.
Khaled, Z. E., Ajib, W., & Mcheick, H. (2020). An accurate empirical path loss model for heterogeneous fixed wireless networks below 5.8 GHz frequencies. IEEE Access, 8, 182755–182775. https://doi.org/10.1109/ACCESS.2020.3023141
Wolpert, D. H., & Macready, W. G. (2005). Coevolutionary free lunches. IEEE Transactions on Evolutionary Computation, 9(6), 721–735.
Cover, T. M., & Hart, P. E. (1967). Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, IT-13, 21–27.
Walters-Williams, J., & Li, Y. (2010). Comparative study of distance functions for nearest neighbors, Advanced Techniques in Computing Sciences and Soft. Engineering, K. Elleithy, Springer, pp. 79–84
Bhatia, N. Survey of nearest neighbor techniques, arXiv 2010, arXiv:1007.0085.
Choudhury, T., Quigley, A., Strang, T., Suginuma, K. (2009). Location and Context Awareness in proceedings of International Symposium, LoCA 2009, Tokyo, Japan.
Gagn, C., & Parizeau, M. (2007). Coevolution of nearest neighbor classifiers. International Journal of Pattern Recognition and Artificial Intelligence, 21(5), 921–946.
Gou, J., Du, L., Zhang, Y., & Xiaong, T. (2012). A new distance-weighted k-nearest neighbor classifier. Journal of Information and Computational Science, 9(6), 1429–1436.
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359–366.
You, K., Long, M., Jordan, M. I., How does learning rate decay help modern neural networks, arXiv:1908.01878
Zhang, N., Wei, Wu., & Zheng, G. (2006). Convergence of gradient method with momentum for two-Layer feedforward neural networks. IEEE Transactions on Neural Networks, 17(2), 522–525. https://doi.org/10.1109/TNN.2005.863460
Polycarpou, M. M., & Ioannou, P. A. (1992). Learning and convergence analysis of neural-type structured networks. IEEE Transactions on Neural Networks, 3(1), 39–50. https://doi.org/10.1109/72.105416
Bienstock, D., Muñoz and Sebastian Pokutta, G. (2018). “Principled Deep Neural Network Training through Linear Programming.” ArXiv abs/1810.03218 n. pag.
Mismar, F. B., & Evans, B. L. (2019). Deep learning in downlink coordinated multipoint in new radio heterogeneous networks. IEEE Wireless Communications Letters, 8(4), 1040–1043. https://doi.org/10.1109/LWC.2019.2904686
Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford University Press.
Sontag, E. D. (1992). Feedback stabilization using two-hidden-layer nets. IEEE Transactions on Neural Networks, 3(6), 981–990.
Zhang T. et al. (2018). Deep Imitation Learning for Complex Manipulation Tasks From Virtual Reality Teleoperation, Proceedings 2018 IEEE Int’l. Conference Robotics and Automation, pp. 1–8.
Lee, M., Yu, G., Li, G. Y. (2019). Accelerating resource allocation for D2D communications using imitation learning, 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall), Honolulu, HI, USA, pp. 1–5, https://doi.org/10.1109/VTCFall.2019.8891075.
Yu, S., Chen, X., Yang, L., Wu, D., Bennis, M., & Zhang, J. (2020). Intelligent edge: Leveraging deep imitation learning for mobile edge computation offloading. IEEE Wireless Communications, 27(1), 92–99. https://doi.org/10.1109/MWC.001.1900232
van der Maaten, L. J. P., & Hinton, G. E. (2008). Visualizing high-dimensional data using t-SNE. Journal of Machine Learning Research, 9, 2579–2605.
Last, E., Douzas, G., Bacao, F., “Oversampling for Imbalanced Learning Based on K-Means and SMOTE” https://arxiv.org/abs/1711.00
Acknowledgements
We would like to thank Digicom Technologies Inc. for providing the datasets.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
El Khaled, Z., Mcheick, H. & Ajib, W. Machine learning-based approaches for user association and access point selection in heterogeneous fixed wireless networks. Wireless Netw 28, 3503–3524 (2022). https://doi.org/10.1007/s11276-022-03053-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11276-022-03053-2