Paradigm shift from statistical channel modeling to digital twin prediction: an environment-generalizable ChannelLM for 6G AI-enabled air interface

Abstract

Abstract As 6G advances, ubiquitous connectivity and higher capacity requirements of the air interface pose substantial challenges for accurate and real-time wireless channel acquisition in diverse environments. Conventional statistical channel modeling relies on offline measurement data from limited environments, struggling to support online applications facing diverse environments. To this end, the digital twin channel (DTC) has emerged as a novel paradigm that constructs a digital replica of the physical environment through high-fidelity sensing and predicts corresponding channel in real time utilizing artificial intelligence (AI) models. As the engine of DTC, existing AI models struggle to simultaneously achieve strong environmental generalization in real-world and end-to-end channel prediction for real-time tasks. Therefore, this paper proposes a channel large model (ChannelLM)-driven DTC architecture comprising three modules: low-complexity and high-accuracy environment reconstruction based on dynamic object detection and multi-modal alignment of image and point cloud data, physically interpretable environment feature extraction, and a ChannelLM core to map these features into generalized environment representations for multi-task channel prediction. Simulation results under the considered simulated outdoor environments demonstrate that ChannelLM reduces the channel state information prediction error by 4.22 dB compared with small-scale AI models, while the complete DTC pipeline, including sensing, feature extraction, and channel prediction, achieves an end-to-end latency of approximately 75 milliseconds in the system-level evaluation.