Unsupervised Learning for Passive Beamforming

Reconfigurable intelligent surface (RIS) has recently emerged as a promising candidate to improve the energy and spectral efficiency of wireless communication systems. However, the unit modulus constraint on the phase shift of reflecting elements makes the design of optimal passive beamforming solution a challenging issue. The conventional approach is to find a suboptimal solution using the semi-definite relaxation (SDR) technique, yet the resultant suboptimal iterative algorithm usually incurs high complexity, hence is not amenable for real-time implementation. Motivated by this, we propose a deep learning approach for passive beamforming design in RIS-assisted systems. In particular, a customized deep neural network is trained offline using the unsupervised learning mechanism, which is able to make real-time prediction when deployed online. Simulation results show that the proposed approach maintains most of the performance while significantly reduces computation complexity when compared with SDR-based approach.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Qingqing Wu,et al.  Intelligent Reflecting Surface Enhanced Wireless Networks: Two-Timescale Beamforming Optimization , 2021, IEEE Transactions on Wireless Communications.

[3]  Chau Yuen,et al.  Indoor Signal Focusing with Deep Learning Designed Reconfigurable Intelligent Surfaces , 2019, 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[4]  Giuseppe Aceto,et al.  MIMETIC: Mobile encrypted traffic classification using multimodal deep learning , 2019, Comput. Networks.

[5]  Chau Yuen,et al.  Achievable Rate Maximization by Passive Intelligent Mirrors , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Jun Fang,et al.  Intelligent Reflecting Surface-Assisted Millimeter Wave Communications: Joint Active and Passive Precoding Design , 2019, IEEE Transactions on Vehicular Technology.

[7]  Qingqing Wu,et al.  Beamforming Optimization for Wireless Network Aided by Intelligent Reflecting Surface With Discrete Phase Shifts , 2019, IEEE Transactions on Communications.

[8]  Nikos D. Sidiropoulos,et al.  Learning to optimize: Training deep neural networks for wireless resource management , 2017, 2017 IEEE 18th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[9]  Mérouane Debbah,et al.  Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? , 2019, IEEE Transactions on Communications.

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

[11]  Mohamed-Slim Alouini,et al.  Smart Radio Environments Empowered by AI Reconfigurable Meta-Surfaces: An Idea Whose Time Has Come , 2019, ArXiv.

[12]  Qingqing Wu,et al.  Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming , 2018, IEEE Transactions on Wireless Communications.

[13]  Pavel Pechac,et al.  Intelligent walls as autonomous parts of smart indoor environments , 2012, IET Commun..

[14]  Qingqing Wu,et al.  Intelligent Reflecting Surface Enhanced Wireless Network: Joint Active and Passive Beamforming Design , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[15]  Chau Yuen,et al.  Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication , 2018, IEEE Transactions on Wireless Communications.

[16]  Woongsup Lee,et al.  Transmit Power Control Using Deep Neural Network for Underlay Device-to-Device Communication , 2018, IEEE Wireless Communications Letters.

[17]  Beixiong Zheng,et al.  Intelligent Reflecting Surface-Enhanced OFDM: Channel Estimation and Reflection Optimization , 2020, IEEE Wireless Communications Letters.

[18]  Giuseppe Aceto,et al.  Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and Challenges , 2019, IEEE Transactions on Network and Service Management.

[19]  Yu Zhu,et al.  Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning , 2019, IEEE Wireless Communications Letters.

[20]  A.A.M. Saleh,et al.  A Statistical Model for Indoor Multipath Propagation , 1987, IEEE J. Sel. Areas Commun..

[21]  Mohamed-Slim Alouini,et al.  Smart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come , 2019, EURASIP Journal on Wireless Communications and Networking.

[22]  Qingqing Wu,et al.  Beamforming Optimization for Intelligent Reflecting Surface with Discrete Phase Shifts , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).