Hierarchical Meta-learning Models with Deep Neural Networks for Spectrum Assignment

In this paper we consider a data-driven approach and apply machine learning methods to facilitate frequency assignment. Specifically, a hierarchical meta-learning architecture that harnesses the predictive capability of both statistical and deep learning approaches is proposed to predict a diverse range of spectrum usage patterns. Using spectrum measurements, network simulations are conducted to evaluate the effectiveness of the proposed architecture. It is shown that the hierarchical meta- learning models with deep recurrent neural networks have great potential for predicting spectrum usage patterns to facilitate multi-tier spectrum assignments.

[1]  Sana Salous,et al.  Spectrum Occupancy Statistics and Time Series Models for Cognitive Radio , 2011, J. Signal Process. Syst..

[2]  Chung K. Kim,et al.  Adaptive Listen-Before-Talk (LBT) scheme for LTE and Wi-Fi systems coexisting in unlicensed band , 2016, 2016 13th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[3]  Kareem E. Baddour,et al.  Spectrum Occupancy Prediction for Land Mobile Radio Bands Using a Recommender System , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[4]  Robert J. Inkol,et al.  Upper and Lower Bounds for the Threshold of the FFT Filter Bank-Based Summation CFAR Detector , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[5]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[6]  Li Li,et al.  A cloud-based spectrum environment awareness system , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Tanim M. Taher,et al.  Long-term spectral occupancy findings in Chicago , 2011, 2011 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[10]  Klaus Moessner,et al.  Licensed Spectrum Sharing Schemes for Mobile Operators: A Survey and Outlook , 2016, IEEE Communications Surveys & Tutorials.

[11]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[12]  Shuo Liu,et al.  Dynamic Spectrum Assignment for Land Mobile Radio with Deep Recurrent Neural Networks , 2018, 2018 IEEE International Conference on Communications Workshops (ICC Workshops).

[13]  Sneha A. Dalvi,et al.  Internet of Things for Smart Cities , 2017 .

[14]  Benjamin Letham,et al.  Forecasting at Scale , 2018, PeerJ Prepr..

[15]  Kareem E. Baddour,et al.  Spectrum sharing opportunities in land mobile radio bands: A data-driven approach , 2017, 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC).

[16]  Rob J. Hyndman,et al.  Large-Scale Unusual Time Series Detection , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[17]  Miguel López-Benítez,et al.  Empirical Time-Dimension Model of Spectrum Use Based on a Discrete-Time Markov Chain With Deterministic and Stochastic Duty Cycle Models , 2011, IEEE Transactions on Vehicular Technology.

[18]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.