Cognitive Digital Twins for Self-Aware Channel Estimation

Abstract

Artificial intelligence (AI) and machine learning (ML)-based channel estimators silently degrade when propagation conditions drift from their training distributions. This letter proposes a model-agnostic cognitive digital twin (CDT) framework that combines a variational autoencoder (VAE) with latent activation monitoring to detect distribution drift and autonomously execute \textsc{continue}, \textsc{update}, or \textsc{retire} lifecycle actions without requiring ground-truth channel knowledge. The proposed framework is fully compatible with the AI-native lifecycle management envisioned in 3rd Generation Partnership Project (3GPP). Simulations over various channels demonstrate accurate drift detection and robust channel estimation, consistently outperforming conventional offline-trained deep learning estimators under moderate and severe channel drift.