mmWave Signal
Millimeter-wave (mmWave) signals, crucial for high-bandwidth 5G and 6G communication, face challenges from high path loss and susceptibility to blockage. Current research focuses on mitigating these issues through machine learning techniques, employing models like convolutional neural networks, recurrent neural networks (including LSTMs and GRUs), vision transformers, and reinforcement learning algorithms to improve beamforming, blockage prediction, and resource allocation. These advancements are significant for enhancing the reliability and efficiency of mmWave networks, impacting areas such as vehicular communication, healthcare monitoring, and fixed wireless access.
Papers
Using Deep Reinforcement Learning for mmWave Real-Time Scheduling
Barak Gahtan, Reuven Cohen, Alex M. Bronstein, Gil Kedar
Beam Management in Ultra-dense mmWave Network via Federated Reinforcement Learning: An Intelligent and Secure Approach
Qing Xue, Yi-Jing Liu, Yao Sun, Jian Wang, Li Yan, Gang Feng, Shaodan Ma
Position Aided Beam Prediction in the Real World: How Useful GPS Locations Actually Are?
João Morais, Arash Behboodi, Hamed Pezeshki, Ahmed Alkhateeb
Deep Reinforcement Learning Based on Location-Aware Imitation Environment for RIS-Aided mmWave MIMO Systems
Wangyang Xu, Jiancheng An, Chongwen Huang, Lu Gan, Chau Yuen