Paradigm Shift from Statistical Channel Modeling to Digital Twin Prediction: An Environment-Generalizable ChannelLM for 6G AI-enabled Air Interface

TL;DR

This paper introduces a novel digital twin channel prediction framework for 6G that leverages a large AI model, ChannelLM, to achieve environment-generalizable and real-time wireless channel predictions.

Contribution

It proposes a ChannelLM-driven digital twin architecture with modules for environment reconstruction, feature extraction, and a large AI model for generalized channel prediction, improving accuracy and latency.

Findings

ChannelLM reduces prediction errors by 4.23 dB in unseen environments.

Achieves 70 ms end-to-end inference latency in real-world scenarios.

Outperforms small-scale AI models in environment generalization.

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 multimodal alignment of image and point cloud data, physically interpretable environment feature extraction, and a ChannelLM core to mapping these features into generalized environment representations for multi-task channel prediction. Simulation results demonstrate that, in unseen test environments, compared with small-scale AI models, ChannelLM reduces prediction errors by 4.23 dB in channel state information prediction while achieving an end-to-end inference latency of 70 milliseconds in the real world.