Context-aware prediction of access points demand in Wi-Fi networks

We present a methodology based on matrix factorization and gradient descent to predict the number of sessions established in the access points of a Wi-Fi network according to the users behavior. As the network considered in this work is monitored and controlled by software in order to manage users and resources in real time, we may consider it as a cyber-physical system that interacts with the physical world through access points, whose demands can be predicted according to users activity. These predictions are useful for relocating or reinforcing some access points according to the changing physical environment. In this work we propose a prediction model based on machine learning techniques, which is validated by comparing the prediction results with real users activity. Our experiments collected the activity of 1095 users demanding 26,673 network sessions during one month in a Wi-Fi network composed of 10 access points, and the results are qualitatively valid with regard to the previous knowledge. We can conclude that our proposal is suitable for predicting the demand of sessions in access points when some devices are removed taking into account the usual activity of the network users.

[1]  Jerome A. Rolia,et al.  Workload Analysis and Demand Prediction of Enterprise Data Center Applications , 2007, 2007 IEEE 10th International Symposium on Workload Characterization.

[2]  Paolo Spagnolo,et al.  Human Behavior Understanding in Networked Sensing , 2014, Springer International Publishing.

[3]  Kun Yang,et al.  Multi-objective K-connected Deployment and Power Assignment in WSNs using a problem-specific constrained evolutionary algorithm based on decomposition , 2011, Comput. Commun..

[4]  N. K. Shankaranarayanan,et al.  Modeling and characterization of large-scale Wi-Fi traffic in public hot-spots , 2011, 2011 Proceedings IEEE INFOCOM.

[5]  Juan Antonio Gómez Pulido,et al.  Assuming multiobjective metaheuristics to solve a three-objective optimisation problem for Relay Node deployment in Wireless Sensor Networks , 2015, Appl. Soft Comput..

[6]  Paolo Spagnolo,et al.  Human Behavior Understanding in Networked Sensing: Theory and Applications of Networks of Sensors , 2014 .

[7]  Kenji Ishida,et al.  Improvement of Throughput Prediction Method for Access Point in Multi-rate WLANs Considering Media Access Control and Frame Collision , 2015, 2015 Third International Symposium on Computing and Networking (CANDAR).

[8]  Yehuda Koren,et al.  Factor in the neighbors: Scalable and accurate collaborative filtering , 2010, TKDD.

[9]  Chong Wang,et al.  An Adaptive Learning Rate for Stochastic Variational Inference , 2013, ICML.

[10]  Stefano Basagni,et al.  Heuristics for Lifetime Maximization in Wireless Sensor Networks with Multiple Mobile Sinks , 2009, 2009 IEEE International Conference on Communications.

[11]  Ahmed Helmy,et al.  Structural Analysis of User Association Patterns in University Campus Wireless LANs , 2012, IEEE Transactions on Mobile Computing.

[12]  Yuan Xue,et al.  Integrating Traffic Estimation and Routing Optimization for Multi-Radio Multi-Channel Wireless Mesh Networks , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[13]  Gerhard Friedrich,et al.  Recommender Systems - An Introduction , 2010 .

[14]  Xiaoli Chu,et al.  Coexistence of Wi-Fi and heterogeneous small cell networks sharing unlicensed spectrum , 2015, IEEE Communications Magazine.

[15]  Mohamed F. Younis,et al.  Strategies and techniques for node placement in wireless sensor networks: A survey , 2008, Ad Hoc Networks.

[16]  Junichi Suzuki,et al.  Evolutionary constraint-based multiobjective adaptation for self-organizing wireless sensor networks , 2007, 2007 2nd Bio-Inspired Models of Network, Information and Computing Systems.

[17]  Rajeev Kumar,et al.  Multiobjective network design for realistic traffic models , 2007, GECCO '07.

[18]  Weiguo Gong,et al.  An Adaptive Learning Rate Method for Improving Adaptability of Background Models , 2013, IEEE Signal Processing Letters.

[19]  Insup Lee,et al.  Cyber-physical systems: The next computing revolution , 2010, Design Automation Conference.

[20]  Yun Chi,et al.  Packing light: Portable workload performance prediction for the cloud , 2013, 2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW).

[21]  Guy Leduc,et al.  AP and MN-Centric Mobility Prediction: A Comparative Study Based on Wireless Traces , 2007, Networking.

[22]  Ivan Vilovic,et al.  Location Optimization of WLAN Access Points Based on a Neural Network Model and Evolutionary Algorithms , 2014 .

[23]  Lars Schmidt-Thieme,et al.  Factorization Techniques for Predicting Student Performance , 2012 .

[24]  Lin X. Cai,et al.  Proportional Fairness-Based Resource Allocation for LTE-U Coexisting With Wi-Fi , 2017, IEEE Access.

[25]  Cecilia Mascolo,et al.  NextPlace: A Spatio-temporal Prediction Framework for Pervasive Systems , 2011, Pervasive.

[26]  Patrick Seemann,et al.  Matrix Factorization Techniques for Recommender Systems , 2014 .

[27]  Chunxiao Jiang,et al.  Pricing equilibrium for data redistribution market in wireless networks with matching methodology , 2015, 2015 IEEE International Conference on Communications (ICC).

[28]  Domonkos Tikk,et al.  Scalable Collaborative Filtering Approaches for Large Recommender Systems , 2009, J. Mach. Learn. Res..

[29]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[30]  Lars Schmidt-Thieme,et al.  Online-updating regularized kernel matrix factorization models for large-scale recommender systems , 2008, RecSys '08.