Q-Learning Based Predictive Relay Selection for Optimal Relay Beamforming

Wireless Autonomous Networks are expected to support communication between a source and a receiver, by constantly self-adapting to changes in their communication environment. This paper considers a scenario of relay beamforming, in which relays collaboratively retransmit the source signal so that they maximize the average signal-to-interference+noise ratio (SINR) at the destination. The relays are grouped into clusters, with each cluster having a single active relay at a time. The system evolves in time slots; in each time slot the clusters beamform to the destination, and at the same time, each cluster selects the relay to be active in the subsequent time slot. Relay selection is performed locally within each cluster, using a reinforcement learning approach, namely Q-learning. Compared to prior methods, the proposed scheme does not require any statistical knowledge on the channels, and achieves similar average SINR performance while involving lower complexity.

[1]  Norman C. Beaulieu,et al.  Dual-hop Vs multihop AF relaying systems , 2013, 2013 IEEE Global Communications Conference (GLOBECOM).

[2]  Abbas Jamalipour,et al.  Wireless communications , 2005, GLOBECOM '05. IEEE Global Telecommunications Conference, 2005..

[3]  Urbashi Mitra,et al.  Optimal UAV Relay Placement for Single User Capacity Maximization over Terrain with Obstacles , 2019, 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[4]  Jie Xu,et al.  Reinforcement Learning for Maneuver Design in UAV-Enabled NOMA System with Segmented Channel , 2019, ArXiv.

[5]  Athina Petropulu,et al.  Optimal Mobile Relay Beamforming Via Reinforcement Learning , 2019, 2019 IEEE 29th International Workshop on Machine Learning for Signal Processing (MLSP).

[6]  Tharmalingam Ratnarajah,et al.  On the Performance of Relay Aided Millimeter Wave Networks , 2016, IEEE Journal of Selected Topics in Signal Processing.

[7]  Athina P. Petropulu,et al.  Cooperative Beamforming With Predictive Relay Selection for Urban mmWave Communications , 2019, IEEE Access.

[8]  Xingqin Lin,et al.  Optimal Relay Probing in Millimeter-Wave Cellular Systems With Device-to-Device Relaying , 2015, IEEE Transactions on Vehicular Technology.

[9]  Alexander Shapiro,et al.  Lectures on Stochastic Programming: Modeling and Theory , 2009 .

[10]  Zhi-Quan Luo,et al.  Distributed Beamforming for Relay Networks Based on Second-Order Statistics of the Channel State Information , 2008, IEEE Transactions on Signal Processing.

[11]  Sunghwan Kim,et al.  Relay selection Algorithm for wireless cooperative networks: a learning-based approach , 2017, IET Commun..

[12]  Xiaojiang Du,et al.  Cooperative Communications With Relay Selection Based on Deep Reinforcement Learning in Wireless Sensor Networks , 2019, IEEE Sensors Journal.

[13]  Mehrzad Malmirchegini,et al.  On the Spatial Predictability of Communication Channels , 2012, IEEE Transactions on Wireless Communications.

[14]  Won-Joo Hwang,et al.  Proportional Selection of Mobile Relays in Millimeter-Wave Heterogeneous Networks , 2018, IEEE Access.

[15]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[16]  Athina P. Petropulu,et al.  Spatially Controlled Relay Beamforming , 2018, IEEE Transactions on Signal Processing.

[17]  Mustafa Cenk Gursoy,et al.  Energy Efficiency in Relay-Assisted mmWave Cellular Networks , 2016, 2016 IEEE 84th Vehicular Technology Conference (VTC-Fall).

[18]  Jeffrey G. Andrews,et al.  Connectivity of Millimeter Wave Networks With Multi-Hop Relaying , 2014, IEEE Wireless Communications Letters.

[19]  Long Zhang,et al.  A Survey on 5G Millimeter Wave Communications for UAV-Assisted Wireless Networks , 2019, IEEE Access.

[20]  Ainslie,et al.  CORRELATION MODEL FOR SHADOW FADING IN MOBILE RADIO SYSTEMS , 2004 .