International Journal of Science, Engineering and TechnologyAuthors: Ajay Damor, Dr Nidhi Tiwari, Professor Madhavi S Bhanwar
Abstract: The emergence of sixth-generation (6G) wireless networks demands highly efficient spectrum utilization and robust communication strategies to support ultra-reliable, low-latency, and high-capacity services. One of the critical challenges in 6G is accurate channel estimation, especially in dense user environments where spectrum resources are limited. This paper proposes a novel hybrid approach for channel estimation that integrates Non-Orthogonal Multiple Access (NOMA) with Artificial Intelligence (AI)-driven algorithms. The NOMA framework enables simultaneous multi-user transmission within the same spectrum band, thereby enhancing spectral efficiency, while the AI-based module leverages deep learning and reinforcement learning models to perform adaptive and dynamic channel estimation under varying propagation conditions. The proposed methodology not only minimizes estimation errors but also reduces computational complexity compared to conventional estimation methods. Simulation results demonstrate significant improvements in spectral efficiency, bit error rate, and overall system throughput, validating the potential of the AI–NOMA hybrid approach for next-generation wireless networks. This work highlights the importance of intelligent channel estimation techniques in realizing the performance requirements of 6G communication systems.
