The trend of using larger scale antenna arrays will continue toward 6G systems, where the number of antennas will be further scaled up to improve spectral efficiency. However, the increase in the number of antennas will bring new challenges to the physical layer, such as frequent feedback in high-speed mobile communications, multiband coexistence overhead from sub-6 (gigahertz) GHz to terahertz (THz), and energy consumption due to increased antenna components and circuits. In this article, we introduce artificial intelligence (AI)-based channel extrapolation to address these problems. Specifically, we divide the channel extrapolation into time, frequency, and space domains according to different application scenarios. The channel propagation characteristics that affect the extrapolation of each domain, such as the spatial consistency property (SCP), partial reciprocity, and spatial nonstationarity, are analyzed. The motivations for selecting various AI models in each domain are explained, and the performance of AI models is compared. Furthermore, we find the gain of cross-domain channel extrapolation based on transfer learning (TL). The simulation results show that the experience of the AI model cross different domains can be mutually reinforcing. Finally, we introduce several challenges for AI-based channel extrapolation, which can be regarded as potential research directions for realizing future AI-powered 6G systems.

Conventionally statistical path loss models are high-dimensional data-based without utilizing specific environment features. In this letter, a novel environment features-based model (EFBM) for path loss prediction is presented. We connect the propagation environment and channel by representing the environment with low-dimensional features: distance, deviation, volume, and blockage. The features are propagation-related, which can predict path loss directly by utilizing the Random Forest (RF) method. Compared with the data-based method, the proposed method can reduce the Root Mean Squared Error (RMSE) by 0.33 and 0.89 dB at 6 and 28 GHz and provide closer results to the Ray-Tracing (RT)-based ground-truth values.

To reduce the downlink beam sweep overhead of mmWave systems, we propose a deep reinforcement learning based dynamic beam selection (DRL-DBS) method. A new learning motivation is presented by analyzing the dynamic change laws of high- and low-frequency channels in the spatial domain: to learn the index offset between the optimal beam of mmWave and sub-6 GHz spatial spectrum. In the DRL-DBS method, we propose a novel action space where actions can dynamically adjust the size of the beam sweep subset according to the high-and low-frequency channel propagation laws. Hence, the DRL-DBS method can predict a mmWave downlink beam sweep subset with dynamic size, and the optimal beamforming index is from beam sweep results on the subset. A dual-input dueling Q-network with noisy networks and prioritized experience replay is designed to select the optimal action. The DRL-DBS method can achieve a dynamic trade-off between mmWave beam selection quality and beam sweep overhead based on the reward function. Simulation results demonstrate the superior performance of the DRL-DBS method compared with the existing strategies. Especially, the DRL-DBS method outperforms the exhaustive search algorithm in achievable rate because the overhead of mmWave beam sweep is considered.

In view of the propagation environment directly determining the channel properties, the applications can also be solved with the aid of environmental information. Inspired by task-oriented semantic communication and machine learning (ML) powered environment-channel mapping methods, we aim to provide a new view of the environment from the semantic level. This letter defines propagation environment semantics (PES) as a limited set of propagation environment semantic symbols (PESS). The PESS is extracted, which is oriented to the application tasks with concerned channel properties as a foundation. For method validation, the PES-aided beam prediction (PESaBP) is investigated and implemented for non-line-of-sight (NLOS) scenarios. Environment features and graph representations are constructed for actions of channel quality evaluation and target scatterer detection with maximum power. It can obtain 0.92 and 0.9 precision, respectively, and save over 87% of the time cost.

Channel state information (CSI) is crucial for massive multi-input multi-output (MIMO) system. As the antenna scale increases, acquiring CSI results in significantly higher system overhead. In this letter, we propose a novel channel prediction method which utilizes wireless environment information with pilot pattern optimization for channel prediction (WEI-CP). Specifically, the distribution of scatterers around the mobile station (MS) significantly affecting the CSI, which represents the wireless environment information, is acquired using multi-view images. Then, to dig out the mapping relationship between wireless environment information (WEI) and CSI, the image feature extraction module extracts environment feature map from multi-view images. Additionally, the pilot pattern optimization module acquires an optimal fixed pilot pattern to select partial CSI. Finally, using the environment feature map and partial CSI, the channel prediction module predicts the complete CSI. Simulation results show that the WEI-CP can reduce pilot overhead from 1/5 to 1/8 and improve prediction accuracy, with the normalized mean squared error reduced to 0.0113, an 83.2% improvement over channel prediction method without WEI.