Joint active and passive beamforming optimization of IRS-assisted vehicular system with IA-GNN

Abstract

The implementation of an effective intelligent reflecting surface (IRS) assisted millimeter-wave (mmWave) vehicular system critically depends on the proper beamforming design exploiting accurate channel state information (CSI). However, it is difficult to obtain accurate CSI due to the passive characteristics of reflective elements and the high-speed movement of vehicle user equipment (VUE). Furthermore, the channel estimation requires a tremendous amount of pilot overhead. In this paper, an instantaneous CSI aware graph neural network (IA-GNN) model based on unsupervised deep learning (DL) was proposed to implicitly learn the channel features and capture the relationship between the IRS and VUEs for IRS-assisted vehicle-to-infrastructure (V2I) links. The graph attention (GAT) mechanism is introduced to better integrate the correlation of node features into the IA-GNN model and improve the accuracy of mapping relationships. By using the IA-GNN model, different utility functions are taken as system objectives for joint active and passive beamforming optimization. Numerical results demonstrate that the proposed beamforming optimization scheme using the IA-GNN model has significant advantages over the existing schemes in terms of generalization and low pilot overhead.

Keywords

intelligent reflecting surface (IRS) / vehicle-to-infrastructure (V2I) / beamforming / instantaneous CSI aware graph neural network (IA-GNN) / graph attention (GAT)

References

[1] PALA S, SAIKIA P, SINGH S K, et al. Design of RIS-assisted full duplex 6G-V2X communications. Proceedings of the 2023 IEEE Wireless Communications and Networking Conference (WCNC'23), 2023, Mar 26 - 20, Glasgow, UK. Piscataway, NJ, USA: IEEE, 2023: 6p.

[2] LI C Y, FANG Y F, YU L J, et al. A 5G mmWave communication framework in vehicle-road cooperative system. Proceedings of the 8th Annual International Conference on Network and Information Systems for Computers (ICNISC'22), 2022, Sep 16 - 18, Hangzhou, China. Piscataway, NJ, USA: IEEE, 2022: 46-49.

[3] PAN S, ZHANG X M, Sung D K. Intelligent reflecting surface-aided centralized scheduling for mmWave V2V networks. Proceedings of the 2022 International Conference on Computer Communications and Networks (ICCCN'22), 2022, Jul 25 - 27, Honolulu, HI, USA. Piscataway, NJ, USA: IEEE, 2022: 10p.

[4] WU Q Q, GUAN X R, ZHANG R . Intelligent reflecting surface-aided wireless energy and information transmission: an overview. Proceedings of the IEEE, 2022, 110(1): 150-170.

[5] HUANG C W, HU S, ALEXANDROPOULOS G C, et al. Holographic MIMO surfaces for 6G wireless networks: opportunities, challenges, and trends. IEEE Wireless Communications, 2020, 27(5): 118-125.

[6] TAGLIAFERRI D, MIZMIZI M, AYOUBI R A, et al. Conformal intelligent reflecting surfaces for 6G V2V communications. Proceedings of the 2022 1st International Conference on 6G Networking (6GNet'22), 2022, Jul 6 - 8, Paris, France. Piscataway, NJ, USA: IEEE, 2022: 8p.

[7] WU W, WANG H, WANG W N, et al. Doppler mitigation method aided by reconfigurable intelligent surfaces for high-speed channels. IEEE Wireless Communications Letters, 2022, 11(3): 627-631.

[8] DANG J, ZHANG Z C, WU L . Joint beamforming for intelligent reflecting surface aided wireless communication using statistical CSI. China Communications, 2020, 17(8): 147-157.

[9] LI Q, WANG S L, WANG Y Y . Rank-two multicast beamforming for multiuser MISO downlink with intelligent reflecting surface. IEEE Transactions on Vehicular Technology, 2022, 71(6): 6722-6726.

[10] PAPAZAFEIROPOULOS A, PAN C H, KOURTESSIS P S. et al. Intelligent reflecting surface-assisted MU-MISO systems with imperfect hardware: channel estimation and beamforming design. IEEE Transactions on Wireless Communications, 2022, 21(3): 2077-2092.

[11] LIN S E, ZHENG B X, Alexandropoulos G C, et al. Reconfigurable intelligent surfaces with reflection pattern modulation: beamforming design and performance analysis. IEEE Transactions on Wireless Communication, 2021, 20(2): 741-754.

[12] ZHENG B X, ZHANG R . Intelligent reflecting surface-enhanced OFDM: channel estimation and reflection optimization. IEEE Wireless Communications Letters, 2020, 9(4): 518-522.

[13] WU T T, ZHU L B, XU W C, et al. IRS aided beamforming design of millimeter wave vehicle networking system. Proceedings of the 5th International Conference on Artificial Intelligence and Computer Applications (ICAICA'23), 2023, Nov 28 - 30, Dalian, China. Piscataway, NJ, USA: IEEE, 2023: 831-835.

[14] SONG H B, ZHANG M Y, GAO J B, et al. Unsupervised learning-based joint active and passive beamforming design for reconfigurable intelligent surfaces aided wireless networks. IEEE Communications Letters, 2021, 25(3): 892-896.

[15] POTU V D, SUNKU V S, MOUNIKA M, et al. A deep learning scheme for integrated active and passive beamforming in reconfigurable intelligent surface aided wireless MISO networks. Proceedings of the 2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET'22), 2022, Mar 24 - 26, Chennai, India. Piscataway, NJ, USA: IEEE, 2022: 226-230.

[16] GAO A, SUN X S, XU Y S, et al. Heterogeneous multi-agent reinforcement learning for joint active and passive beamforming in IRS assisted communications. Proceedings of the 32nd Wireless and Optical Communications Conference (WOCC'23), 2023, May 5 - 6, Newark, NJ, USA. Piscataway, NJ, USA: IEEE, 2023: 5p.

[17] XU X, LU Y, FU Q M. Applying graph neural network in deep reinforcement learning to optimize wireless network routing. Proceedings of the 9th International Conference on Advanced Cloud and Big Data (CBD'22), 2022, Mar 26 - 27, Xi'an, China. Piscataway, NJ, USA: IEEE, 2022: 218-223.

[18] RAHMAN M M, RAHMAN M S . Performance analysis of classical and graph neural network-based power allocation schemes for single-hop Ad hoc wireless networks. Proceedings of the 12th International Conference on Electrical and Computer Engineering (ICECE'22), 2022, Dec 21 - 23, Dhaka, Bangladesh. Piscataway, NJ, USA: IEEE, 2022: 449-452.

[19] EISEN M, RIBEIRO A . Optimal wireless resource allocation with random edge graph neural networks. IEEE Transactions on Signal Processing, 2020, 68: 2977-2991.

[20] CHEN J, LIANG Y C, CHENG H V, et al. Channel estimation for reconfigurable intelligent surface aided multi-user mmWave MIMO systems. IEEE Transactions on Wireless Communications, 2023, 22(10): 6853-6869.

[21] VELIKOVI P, CUCURULL G, CASANOVA A, et al. Graph attention networks. Proceedings of the 6th International Conference on Learning Representations (ICLR'18), 2018, Apr 30 - May 3, Vancouver, Canada. 2018: 12p.

[22] ZHU J Y, HUANG Y M, WANG J H, et al. Power efficient IRS-assisted NOMA. IEEE Transactions on Communications, 2021, 69(2): 900-913.

[23] LIU C, LIU X M, WEI Z Q, et al. Deep learning-empowered predictive beamforming for IRS-assisted multi-user communications. Proceedings of the 2021 IEEE Global Communications Conference (GLOBECOM'21), 2021, Dec 7 - 11, Madrid, Spain. Piscataway, NJ, USA: IEEE, 2023: 7p.

[24] PEKKA K, JUHA M, LASSI H, et al. WINNER II channel models. IST-4-027756 WINNER II D1.1.2 V1.2, 2008.

[25] GUO H Y, LIANG Y C, CHEN J, et al. Weighted sum-rate maximization for reconfigurable intelligent surface aided wireless networks. IEEE Transactions on Wireless Communications, 2020, 19(5): 3064-3076.

[26] KYAW K T, SANTIPACH W, MAMAT K, et al. Optimization of transmit beamforming using channel covariances for MISO downlink assisted by reconfigurable intelligent surfaces. Proceedings of the 21st International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON'24), 2024, May 27 - 30, Khon Kaen, Thailand. Piscataway, NJ, USA: IEEE, 2024: 6p.

[27] NADEEM Q U A, ALWAZANI H, KAMMOUN A, et al. Intelligent reflecting surface-assisted multi-user MISO communication: channel estimation and beamforming design. IEEE Open Journal of the Communications Society, 2020, 1: 661-680.