Predicting a user's next cell with supervised learning based on channel states

Knowing a user's next cell allows more efficient resource allocation and enables new location-aware services. To anticipate the cell a user will hand-over to, we introduce a new machine learning based prediction system. Therein, we formulate the prediction as a classification problem based on information that is readily available in cellular networks. Using only Channel State Information (CSI) and handover history, we perform classification by embedding Support Vector Machines (SVMs) into an efficient pre-processing structure. Simulation results from a Manhattan Grid scenario and from a realistic radio map of downtown Frankfurt show that our system provides timely prediction at high accuracy.

[1]  Stathes Hadjiefthymiades,et al.  Enhanced path prediction for network resource management in wireless LANs , 2003, IEEE Wireless Communications.

[2]  David Tse,et al.  Fundamentals of Wireless Communication , 2005 .

[3]  Stathes Hadjiefthymiades,et al.  Path Prediction through Data Mining , 2007, IEEE International Conference on Pervasive Services.

[4]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[5]  Stefan Valentin,et al.  Context-aware resource allocation for cellular wireless networks , 2012, EURASIP J. Wirel. Commun. Netw..

[6]  Richard P. Martin,et al.  The limits of localization using signal strength: a comparative study , 2004, 2004 First Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, 2004. IEEE SECON 2004..

[7]  Joonhyuk Kang,et al.  A novel location finding system for 3GPP LTE , 2009, 2009 IEEE 20th International Symposium on Personal, Indoor and Mobile Radio Communications.

[8]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[9]  John Bigham,et al.  Outdoor Location Estimation Using Received Signal Strength Feedback , 2012, IEEE Communications Letters.

[10]  Duc A. Tran,et al.  Localization In Wireless Sensor Networks Based on Support Vector Machines , 2008, IEEE Transactions on Parallel and Distributed Systems.