Paper Title: TwinLink6G: An Explainable Autoencoder Framework for Digital Twins in 6G O-RAN
Conference Name: Korean Institute of Communications and Information Sciences (KICS Winter 2025) Conference
Abstract: TwinLink6G is a novel explainable autoencoder-based communication framework tailored for transmitting high-dimensional battery digital twin data over 6G Open Radio Access Networks (O-RAN). The framework integrates Explainable Artificial Intelligence (XAI) techniques, specifically Local Interpretable Model-agnostic Explanations (LIME), to ensure both robustness and interpretability. By employing phase shift keying (PSK) modulation schemes such as BPSK, QPSK, and 16-PSK, TwinLink6G achieves high reconstruction accuracy and reduced block error rates (BLER). Experimental results demonstrate up to 98% reconstruction accuracy, with LIME offering critical insights into feature importance, such as state of charge (SoC) and temperature, enhancing system transparency and aligning with O-RAN goals of reliability and efficiency.