Exploiting Age of Information in Network Digital Twins for AI-driven Real-Time Link Blockage Detection

TL;DR

This paper introduces a novel approach that incorporates Age of Information into Network Digital Twins to enable real-time, AI-driven detection of line-of-sight blockages in high-frequency wireless links, improving responsiveness and efficiency.

Contribution

It proposes integrating AoI metrics with deep learning models and raytracing data collection to enhance real-time blockage detection and mitigate model drift efficiently.

Findings

Achieved 32x computational speedup with 4x8 resolution reduction.

Successfully mitigated model performance degradation with only 1% of data.

Demonstrated effectiveness in realistic urban simulation environments.

Abstract

The Line-of-Sight (LoS) identification is crucial to ensure reliable high-frequency communication links, especially those vulnerable to blockages. Network Digital Twins and Artificial Intelligence are key technologies enabling blockage detection (LoS identification) for high-frequency wireless systems, e.g., 6>GHz. In this work, we enhance Network Digital Twins by incorporating Age of Information (AoI) metrics, a quantification of status update freshness, enabling reliable real-time blockage detection (LoS identification) in dynamic wireless environments. By integrating raytracing techniques, we automate large-scale collection and labeling of channel data, specifically tailored to the evolving conditions of the environment. The introduced AoI is integrated with the loss function to prioritize more recent information to fine-tune deep learning models in case of performance degradation (model drift). The effectiveness of the proposed solution is demonstrated in realistic urban simulations, highlighting the trade-off between input resolution, computational cost, and model performance. A resolution reduction of 4x8 from an original channel sample size of (32, 1024) along the angle and subcarrier dimension results in a computational speedup of 32 times. The proposed fine-tuning successfully mitigates performance degradation while requiring only 1% of the available data samples, enabling automated and fast mitigation of model drifts.