Channel charting (CC) applies dimensionality reduction to channel state information (CSI) data at the infrastructure basestation side with the goal of extracting pseudo-position information for each user. The self-supervised nature of CC enables predictive tasks that depend on user position without requiring any ground-truth position information. In this work, we focus on the practically relevant streaming CSI data scenario, in which CSI is constantly estimated. To deal with storage limitations, we develop a novel streaming CC architecture that maintains a small core CSI dataset from which the channel charts are learned. Curation of the core CSI dataset is achieved using a min-max-similarity criterion. Numerical validation with measured CSI data demonstrates that our method approaches the accuracy obtained from the complete CSI dataset while using only a fraction of CSI storage and avoiding catastrophic forgetting of old CSI data.
Self-Supervised Pretraining for Transmission-Relevant MIMO CSI Representation
Pohang University of Science and Technology(浦项科技大学);Institute of New Media and Communications, Seoul National University(首尔大学新媒体与通信研究所);Department of Electrical and Computer Engineering, Seoul National University(首尔大学电气与计算机工程系);Department of Electrical Engineering, Stanford University(斯坦福大学电气工程系)