Nidhi Chahal,
Tarun Singhal,
Ramanpreet Kaur,
Varsha Sood,
Tinu Anand,
- Assistant Professor, Department of Electronics and Communication Engineering Chandigarh Engineering College-CGC, Punjab, India
- Associate Professor, Department of Electronics and Communication Engineering Chandigarh Engineering College-CGC, Punjab, India
- Associate Professor, Department of Electronics and Communication Engineering Chandigarh Engineering College-CGC, Punjab, India
- Associate professor, Department of Electronics and Communication Engineering Chandigarh Engineering College-CGC, Punjab, India
- Student, Department of Electronics and Communication Engineering Chandigarh Engineering College-CGC, Punjab, India
Abstract
This paper is the second instalment of a two-part review on artificial intelligence (AI) for sixth-generation (6G) wireless networks. Where the companion paper traced the generational evolution of mobile networks and the Digital Twin architecture that underpins 6G, this paper narrows the focus to the specific AI techniques expected to drive 6G’s autonomous operation and to the air-interface problems those techniques are being asked to solve. We review machine learning, deep learning, reinforcement learning, and the emerging field of quantum reinforcement learning, examining how each contributes to resource allocation, network-traffic prediction, and control-policy learning under the extreme dimensionality of terahertz and massive-MIMO systems. We then turn to three concrete air-interface problems—Channel State Information (CSI) feedback compression, AI-based beam management, and AI-assisted wireless localization—describing how learning-based methods outperform classical statistical approaches in each case. A representative smart-city use case illustrates how multi-agent reinforcement learning coordinates large numbers of autonomous decision-makers in a shared environment. The paper closes with a structured set of research directions covering computational efficiency, big-data analytics, hardware development, energy management, and AI-enabled 6G IoT, supported by original comparative tables and illustrative figures summarizing reported performance trends.
Keywords: Artificial intelligence, machine learning, deep learning, reinforcement learning, quantum reinforcement learning, CSI feedback, beam management, wireless localization, 6G IoT
[This article belongs to Journal of Mobile Computing, Communications & Mobile Networks ]
References
- Saad W, Bennis M, Chen M. A vision of 6G wireless systems: applications, trends, technologies, and open research problems. IEEE Netw. 2020;34(3):134-42.
- Wen CK, Shih WT, Jin S. Deep learning for massive MIMO CSI feedback. IEEE Wirel Commun Lett. 2018;7(5):748-51.
- Lin YC, Lee TS, Ding Z. A scalable deep learning framework for dynamic CSI feedback with variable antenna port numbers. IEEE Trans Wirel Commun. 2024;23(4):3102-16.
- Yu X, Li X, Wu H, Bai Y. DS-NLCsiNet: exploiting non-local neural networks for massive MIMO CSI feedback. IEEE Commun Lett. 2020;24(12):2790-4.
- Alkhateeb A, Leus G, Heath RW. Limited feedback hybrid precoding for multi-user millimeter wave systems. IEEE Trans Wirel Commun. 2015;14(11):6481-94.
- Va V, Shimizu T, Bansal G, Heath RW. Beam design for beam switching based millimeter wave vehicle-to-infrastructure communications. In: 2016 IEEE International Conference on Communications (ICC); 2016 May 22. 2016. p. 1-6.
- Wang J, Lan Z, Pyo CW, Baykas T, Sum CS, Rahman MA, et al. Beam codebook based beamforming protocol for multi-Gbps millimeter-wave WPAN systems. IEEE J Sel Areas Commun. 2009;27(8):1390-9.
- Wymeersch H, Seco-Granados G, Destino G, Dardari D, Tufvesson F. 5G mmWave positioning for vehicular networks. IEEE Wirel Commun. 2017;24(6):80-6.
- Witrisal K, Meissner P, Leitinger E, Shen Y, Gustafson C, Tufvesson F, et al. High-accuracy localization for assisted living. IEEE Signal Process Mag. 2016;33(2):59-69.
- Breiman L. Random forests. Mach Learn. 2001;45(1):5-32.
- Huang H, Yang J, Huang H, Song Y, Gui G. Deep learning for super-resolution channel estimation and DOA estimation based massive MIMO system. IEEE Trans Veh Technol. 2018;67(9):8549-60.
- Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge (MA): MIT Press; 2016.
- Fayaz SA, Jahangeer Sidiq S, Zaman M, Butt MA. Machine learning: an introduction to reinforcement learning. In: Machine learning and data science: fundamentals and applications. 2022. p. 1-22.
- Yue L, Chen T. AI large model and 6G network. In: 2023 IEEE Globecom Workshops (GC Wkshps); 2023 Dec 4. 2023. p. 2049-54.
- Sofia RC, Shen H, Liu Y, Kacianka S, Pfeifer H. White paper: towards human-centric and sustainable 6G services—the fortiss research perspective [Preprint]. 2025. arXiv:2507.14209.
- Fang C, Hu Z, Meng X, Tu S, Wang Z, Zeng D, et al. DRL-driven joint task offloading and resource allocation for energy-efficient content delivery in cloud-edge cooperation networks. IEEE Trans Veh Technol. 2023;72(12):16195-207.
- Qiao L, Mashhadi MB, Gao Z, Foh CH, Xiao P, Bennis M. Latency-aware generative semantic communications with pre-trained diffusion models. IEEE Wirel Commun Lett. 2024;13(10):2652-6.
- Tong W, Li GY. Nine challenges in artificial intelligence and wireless communications for 6G. IEEE Wirel Commun. 2022;29(4):140-5.
- Kataria D, Walid A, Daneshmand M, Dutta A, Enright MA, Gu R, et al. INGR roadmap artificial intelligence and machine learning chapter. In: 2023 IEEE Future Networks World Forum (FNWF); 2023 Nov 13. 2023. p. 1-69.
- Chowdhury MZ, Shahjalal M, Ahmed S, Jang YM. 6G wireless communication systems: applications, requirements, technologies, challenges, and research directions. IEEE Open J Commun Soc. 2020;1:957-75.
| Volume | 13 | |
| Issue | 02 | |
| Received | 10/07/2026 | |
| Accepted | 09/09/2026 | |
| Published | 13/09/2026 | |
| Publication Time | 65 Days |