Deep Learning Meets Cognitive Radio: Predicting Future Steps

Learning the channel occupancy patterns to reuse the underutilised spectrum frequencies without interfering with the incumbent is a promising approach to overcome the spectrum limitations. In this work we proposed a Deep Learning (DL) approach to learn the channel occupancy model and predict its availability in the next time slots. Our results show that the proposed DL approach outperforms existing works by 5%. We also show that our proposed DL approach predicts the availability of channels accurately for more than one time slot.

[1]  Yunfei Chen,et al.  Analysis of Spectrum Occupancy Using Machine Learning Algorithms , 2015, IEEE Transactions on Vehicular Technology.

[2]  Richard Socher,et al.  Regularizing and Optimizing LSTM Language Models , 2017, ICLR.

[3]  Jin Wei,et al.  Deep learning-based automated modulation classification for cognitive radio , 2016, 2016 IEEE International Conference on Communication Systems (ICCS).

[4]  Yonghong Zeng,et al.  Sensing-Throughput Tradeoff for Cognitive Radio Networks , 2008, IEEE Transactions on Wireless Communications.

[5]  Luiz A. DaSilva,et al.  The effect of the spectrum opportunities diversity on opportunistic access , 2013, 2013 IEEE International Conference on Communications (ICC).

[6]  Petri Mähönen,et al.  Lessons Learned from an Extensive Spectrum Occupancy Measurement Campaign and a Stochastic Duty Cycle Model , 2009, 2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities and Workshops.

[7]  Amy Loutfi,et al.  A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[8]  Luiz A. DaSilva,et al.  Complexity of Spectrum Activity and Benefits of Reinforcement Learning for Dynamic Channel Selection , 2013, IEEE Journal on Selected Areas in Communications.

[9]  Guan Gui,et al.  Deep Learning-Inspired Message Passing Algorithm for Efficient Resource Allocation in Cognitive Radio Networks , 2019, IEEE Transactions on Vehicular Technology.

[10]  Jeffrey G. Andrews,et al.  What Will 5G Be? , 2014, IEEE Journal on Selected Areas in Communications.

[11]  Ming Xiao,et al.  A Survey of Advanced Techniques for Spectrum Sharing in 5G Networks , 2017, IEEE Wireless Communications.

[12]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[13]  Ian F. Akyildiz,et al.  A survey on spectrum management in cognitive radio networks , 2008, IEEE Communications Magazine.

[14]  Christophe Moy,et al.  Aggregation of multi-armed bandits learning algorithms for opportunistic spectrum access , 2018, 2018 IEEE Wireless Communications and Networking Conference (WCNC).

[15]  Luiz A. DaSilva,et al.  Context-aware cognitive radio using deep learning , 2017, 2017 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[16]  Justin Tallon,et al.  Coexistence through adaptive sensing and Markov chains , 2015, 2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN).

[17]  Jürgen Schmidhuber,et al.  LSTM: A Search Space Odyssey , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Jian Yang,et al.  Spectrum Prediction Based on Taguchi Method in Deep Learning With Long Short-Term Memory , 2018, IEEE Access.

[19]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[20]  Sebastian Müller,et al.  DySPAN Spectrum Challenge: Situational Awareness and Opportunistic Spectrum Access Benchmarked , 2017, IEEE Transactions on Cognitive Communications and Networking.

[21]  Yong Huat Chew,et al.  Predictive opportunistic spectrum access using learning based hidden Markov models , 2011, 2011 IEEE 22nd International Symposium on Personal, Indoor and Mobile Radio Communications.

[22]  Alagan Anpalagan,et al.  Advanced spectrum sharing in 5G cognitive heterogeneous networks , 2016, IEEE Wireless Communications.

[23]  J. Yosinski,et al.  Time-series Extreme Event Forecasting with Neural Networks at Uber , 2017 .

[24]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[25]  Yifan Guo,et al.  Spectrum availability prediction in cognitive aerospace communications: A deep learning perspective , 2017, 2017 Cognitive Communications for Aerospace Applications Workshop (CCAA).

[26]  Lajos Hanzo,et al.  Spectrum Inference in Cognitive Radio Networks: Algorithms and Applications , 2018, IEEE Communications Surveys & Tutorials.

[27]  Luiz A. DaSilva,et al.  Fungible Orthogonal Channel Sets for Multi-User Exploitation of Spectrum , 2015, IEEE Transactions on Wireless Communications.