Abstract

New wireless networks use millimeter-wave large MIMO-OFDM systems, however beam squint effects, pilot overhead, and low power and spectrum allocation under dynamic channel conditions limit their effectiveness. These challenges are addressed by an integrated deep learning-driven system that improves hybrid beamforming, adaptive channel prediction, and dynamic resource allocation in wideband mmWave contexts Framework includes multi-scale graph attention-based hybrid beamforming, transformer-based adaptive channel estimation with frequency-aware memory, meta-learning-enhanced deep reinforcement learning for resource allocation, sparse coding-based beamforming enhancement, and multi-agent reinforcement learning for coordinated beam alignment and powers. Real-world urban mmWave studies indicate considerable improvements in all performance metrics. The framework boosts spectral efficiency by 30-40% across antenna and user configurations, peaking at 28.5 bits/s/Hz in large-scale MIMO. Improved channel estimate accuracy by 35%, lowering normalized mean square error to -22.1 dB and pilot overhead by 35%. Wideband beam misalignment is considerably minimized by 96.5% beamforming accuracy. Dynamic resource allocation efficiency surpasses 97%, saving 25-35% power without compromising throughput.  The framework is appropriate for 5G and 6G ultra-reliable and high-capacity wireless networks because closely integrated deep learning architectures can enable scalable, low-latency, and energy-efficient mmWave MIMO-OFDM communication sets. 

Keywords

Hybrid Beamforming, Channel Estimation, Resource Allocation, Deep Learning, mmWave, MIMO-OFDM,

Downloads

Download data is not yet available.

References

  1. Y. Huang, Z. Zhang, J. Che, J., Z. Yang, Q. Yang, K.K. Wong, Self-attention reinforcement learning for multi-beam combining in mmWave 3D-MIMO systems. Science China Information Sciences, 66(6), (2023) 162304. https://doi.org/10.1007/s11432-022-3542-6
  2. V. Kikan, A. Kumar, A detailed review of 5G MIMO and array antenna design evolution with performance enhancement for mmWave applications. Wireless Networks, 31(3), (2025) 2039-2090. https://doi.org/10.1007/s11276-024-03862-7
  3. M. Banar, A. Mohammadi, M. Kazemi, (Outage Probability of X-Duplex AF Relay-Aided mmWave MIMO Systems with Relay Selection in B5G and 6G. Wireless Personal Communications, 138(3), 2024) 1919-1936. https://doi.org/10.1007/s11277-024-11585-3
  4. Y. Zhang, J. Sun, G. Gui, Y. Lin, H. Gacanin, H. Sari, F. Adachi, Attention mechanism based intelligent channel feedback for mmWave massive MIMO systems. Peer-to-Peer Networking and Applications, 17(1), (2024) 261-283. https://doi.org/10.1007/s12083-023-01594-7
  5. X. Zhou, X. Chen, L. Tong, Y. Wang, Attention-deep reinforcement learning jointly beamforming based on tensor decomposition for RIS-assisted V2X mmWave massive MIMO system. Complex & Intelligent Systems, 10(1), (2024) 145-160. https://doi.org/10.1007/s40747-023-01148-7
  6. M.A. Haque, J.H. Nirob, K.H. Nahin, N.M. Jizat, M.A. Zakariya, R.A. Ananta, M. Wazie Abdulkawi, K. Aljaloud, S.S. Al-Bawri, Machine learning-based technique for gain prediction of mm-wave miniaturized 5G MIMO slotted antenna array with high isolation characteristics. scientific reports, 15(1), (2025) 276. https://doi.org/10.1038/s41598-024-84182-w
  7. J. Meng, Z. Wei, Y. Zhang, B. Li, C. Zhao, Machine learning based low-complexity channel state information estimation. EURASIP Journal on Advances in Signal Processing, 2023(1), (2023) 98. https://doi.org/10.1186/s13634-023-00994-4
  8. Y. Zhao, X. Liu, H. Liu, X. Wang, L. Huang, RIS-Aided MmWave hybrid relay network based on multi-agent deep reinforcement learning. Mobile Networks and Applications, 29(3), (2024) 825-840. https://doi.org/10.1007/s11036-024-02323-x
  9. S.U. Hassan, Z. Ye, T. Mir, U. Mir, Machine learning-inspired hybrid precoding with low-resolution phase shifters for intelligent reflecting surface (IRS) massive MIMO systems with limited RF chains. Wireless Networks, 31(1), (2025) 235-245. https://doi.org/10.1007/s11276-024-03748-8
  10. S. Sahoo, H.K. Sahoo, S. Nanda, S. Samal, Extreme learning machine and correntropy criterion-based hybrid precoder for 5G wireless communication systems. Signal, Image and Video Processing, 18(Suppl 1), (2024) 935-944. https://doi.org/10.1007/s11760-024-03205-1
  11. K.C. Mamillapally, R.K. Dasari, Deep learning-based channel estimation and beamforming architecture for massive MIMO systems. Journal of the Institution of Engineers (India): Series B, 106(4), (2025) 1117-1128. https://doi.org/10.1007/s40031-024-01131-x
  12. A. Swain, S.M. Hiremath, S.K. Patra, Variational AutoEncoder Based CSI Feedback for Massive MIMO Systems: A. Swain et al. Wireless Personal Communications, 145(3), (2025) 385-402. https://doi.org/10.1007/s11277-023-10762-0
  13. T. Van Le, N. C. Luong, K. Lee, Adaptive Perturbation-Based Opportunistic Beamforming Design in Limited Feedback IRS-Assisted mmWave Systems. Wireless Personal Communications, 139(1), (2024) 573-593. https://doi.org/10.1007/s11277-024-11638-7
  14. M. Malekzadeh, Performance prediction and enhancement of 5G networks based on linear regression machine learning. EURASIP Journal on Wireless Communications and Networking, 2023(1), (2023) 74. https://doi.org/10.1186/s13638-023-02282-z
  15. M.D. Woldesenbet, S. Mishra, M. Siddique, Least mean squares based Kalman hybrid precoding for multi-user millimeter wave massive MIMO systems. Wireless Personal Communications, 135, (2024) 563–592. https://doi.org/10.1007/s11277-024-11086-3
  16. R.D. Kadiyala, A. Lokam, C. Bhar, A joint self-information and Markovian model-driven deep channel estimation and feedback model for millimeter-wave massive MIMO systems. Wireless Networks, 31, (2025) 1683–1703. https://doi.org/10.1007/s11276-024-03845-8
  17. S. Gaikwad, P. Malathi, Performance enhancement of massive MIMO using optimal antenna selection technique towards antenna sub array. Wireless Personal Communications, 132(2), (2023) 1273-1291. https://doi.org/10.1007/s11277-023-10660-5
  18. A.B. Farakte, K.P. Sridhar, M.B. Rasale, An energy-aware traffic offloading approach based on deep learning and optimization in massive MIMO. Telecommunication Systems, 87(2), (2024) 301-328. https://doi.org/10.1007/s11235-024-01177-8
  19. C. Sudhamani, M. Roslee, L.L. Chuan, A. Waseem, A.F. Osman, M.H. Jusoh, Enhanced Indoor Path Loss and RSRP of 5G mmWave Communication System with Multi-objective Genetic Algorithm. Wireless Personal Communications, 138(1), (2024) 603. https://doi.org/10.1007/s11277-024-11524-2
  20. C. He, X. Wang, J. Jiao, Y. Huang, C. Han, Y. Zhang, J. Zhu, A rapid fingerprint positioning method based on deep convolutional neural network for MIMO-OFDM systems. Urban Lifeline, 2(1), (2024) 12. https://doi.org/10.1007/s44285-024-00021-4
  21. U. Altun, E. Basar, Machine learning-based PHY-authentication without prior attacker information for wireless multiple access channels. Wireless Personal Communications, 135, (2024) 1383–1396. https://doi.org/10.1007/s11277-024-11087-2
  22. S. Ramanathan, M.A. Bennet, Optimized precoding for massive MU-MIMO systems with KLDA dimension reduction and RNN-crossover GBO algorithm. Telecommunication Systems, 86, (2024) 363–381. https://doi.org/10.1007/s11235-024-01135-4
  23. R.S.A. Anooz, J. Pourrostam, M. Al-Ibadi, Performance evaluation of 2D and 3D beam and channel tracking using adaptive filtering techniques. Iranian Journal of Science and Technology, Transactions of Electrical Engineering, 48, (2024) 1361–1372. https://doi.org/10.1007/s40998-024-00723-z
  24. K. Xu, X. Xia, C. Li, W. Xie, J. Liu, R. Zhu, H. He, Robust DOA estimation and tracking for integrated sensing and communication massive MIMO OFDM systems. Science China Information Sciences, 66(10), (2023) 202302. https://doi.org/10.1007/s11432-022-3661-0
  25. Y. Luo, G. Fu, UAV based device-to-device communication for 5G/6G networks using optimized deep learning models. Wireless Networks, 30(8), (2024) 7137-7151. https://doi.org/10.1007/s11276-023-03578-0