Channel Modeling Aided Dataset Generation for AI-Enabled CSI Feedback: Advances, Challenges, and Solutions
Yupeng Li, Gang Li, Zirui Wen, Shuangfeng Han, Shijian Gao, Guangyi Liu, Jiangzhou Wang
TL;DR
The paper tackles the high data and deployment costs of AI-enabled CSI feedback in FDD MIMO by proposing CMDG, which uses limited field measurements to build a scene-specific SSCM that updates the standard TR 38.901 model. This SSCM enables large-scale data augmentation and a dataset-construction strategy tailored to sub-scenarios, reducing measurement and training delays while preserving generalization across environments. Simulation results show CMDG and the dataset-construction approach outperform benchmarks in SGCS and offer comparable performance with significantly reduced data requirements. The work also discusses standardization implications, highlighting the need to extend MDT to capture CSI statistics and support integrated AI lifecycle management for practical deployment.
Abstract
The AI-enabled autoencoder has demonstrated great potential in channel state information (CSI) feedback in frequency division duplex (FDD) multiple input multiple output (MIMO) systems. However, this method completely changes the existing feedback strategies, making it impractical to deploy in recent years. To address this issue, this paper proposes a channel modeling aided data augmentation method based on a limited number of field channel data. Specifically, the user equipment (UE) extracts the primary stochastic parameters of the field channel data and transmits them to the base station (BS). The BS then updates the typical TR 38.901 model parameters with the extracted parameters. In this way, the updated channel model is used to generate the dataset. This strategy comprehensively considers the dataset collection, model generalization, model monitoring, and so on. Simulations verify that our proposed strategy can significantly improve performance compared to the benchmarks.