Cell Association via Boundary Detection: A Scalable Approach Based on Data-Driven Random Features

The problem of cell association is considered for cellular users present in the field. This has become a challenging problem with the deployment of 5G networks which will share the sub-6 GHz bands with the legacy 4G networks. Instead of taking a network-controlled approach, which may not be scalable with the number of users and may introduce extra delays into the system, we propose a scalable solution in the physical layer by utilizing data that can be collected by a large number of spectrum sensors deployed in the field. More specifically, we model the cell association problem as a nonlinear boundary detection problem and focus on solving this problem using randomized shallow networks for determining the boundaries for location of users associated to each cell. We exploit the power of data-driven modeling to reduce the computational cost of training in the proposed solution for the cell association problem. This is equivalent to choosing the right basis functions in the shallow architecture such that the detection is done with minimal error. Our experiments demonstrate the superiority of this method compared to its data-independent counterparts as well as its computational advantage over kernel methods.

[1]  Peter L. Bartlett,et al.  Rademacher and Gaussian Complexities: Risk Bounds and Structural Results , 2003, J. Mach. Learn. Res..

[2]  Satoshi Nagata,et al.  Investigation on Cell Selection Methods Associated with Inter-cell Interference Coordination in Heterogeneous Networks for LTE-Advanced Downlink , 2011, EW.

[3]  Ekram Hossain,et al.  Evolution toward 5G multi-tier cellular wireless networks: An interference management perspective , 2014, IEEE Wireless Communications.

[4]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[5]  Amir Ghasemi,et al.  Spectrum sensing in cognitive radio networks: requirements, challenges and design trade-offs , 2008, IEEE Communications Magazine.

[6]  R.W. Brodersen,et al.  Implementation issues in spectrum sensing for cognitive radios , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[7]  Shahin Shahrampour,et al.  A General Scoring Rule for Randomized Kernel Approximation with Application to Canonical Correlation Analysis , 2019, ArXiv.

[8]  Xingqin Lin,et al.  Debunking Seven Myths about 5G New Radio , 2019, ArXiv.

[9]  Benjamin Recht,et al.  Random Features for Large-Scale Kernel Machines , 2007, NIPS.

[10]  Qian Zhang,et al.  Cooperative Boundary Detection for Spectrum Sensing Using Dedicated Wireless Sensor Networks , 2010, 2010 Proceedings IEEE INFOCOM.

[11]  Vahid Tarokh,et al.  On Data-Dependent Random Features for Improved Generalization in Supervised Learning , 2017, AAAI.

[12]  Youngnam Han,et al.  Cell selection for range expansion with almost blank subframe in heterogeneous networks , 2012, 2012 IEEE 23rd International Symposium on Personal, Indoor and Mobile Radio Communications - (PIMRC).

[13]  Qihui Wu,et al.  Kernel-Based Learning for Statistical Signal Processing in Cognitive Radio Networks: Theoretical Foundations, Example Applications, and Future Directions , 2013, IEEE Signal Processing Magazine.

[14]  Jie Gao,et al.  Boundary recognition in sensor networks by topological methods , 2006, MobiCom '06.

[15]  Lorenzo Rosasco,et al.  Generalization Properties of Learning with Random Features , 2016, NIPS.

[16]  Michael Rabadi,et al.  Kernel Methods for Machine Learning , 2015 .

[17]  Ismail Güvenç,et al.  Capacity and Fairness Analysis of Heterogeneous Networks with Range Expansion and Interference Coordination , 2011, IEEE Communications Letters.

[18]  Sanjiv Kumar,et al.  Orthogonal Random Features , 2016, NIPS.

[19]  AI Koan,et al.  Weighted Sums of Random Kitchen Sinks: Replacing minimization with randomization in learning , 2008, NIPS.

[20]  Quanfu Fan,et al.  Random Laplace Feature Maps for Semigroup Kernels on Histograms , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Kamran Entesari,et al.  A CMOS Spectrum Sensor Based on Quasi-Cyclostationary Feature Detection for Cognitive Radios , 2015, IEEE Transactions on Microwave Theory and Techniques.

[22]  Benjamin Recht,et al.  Weighted Sums of Random Kitchen Sinks: Replacing minimization with randomization in learning , 2008, NIPS.