In the wake of terrorist attacks in Europe, the European Union has increasingly prioritized collaborative efforts to bolster the protection, resilience, and cybersecurity of critical infrastructures and essential services. Nevertheless, a significant gap persists in accurately quantifying the resilience of these systems, particularly regarding the integration of Artificial Intelligence, which remains underdeveloped. This article endeavors to bridge this gap by developing a robust data-driven framework for Resilience Key Performance Indicators. This study focuses on identifying effective data-driven methodologies to assess the response of cyber-physical critical infrastructures to cyber attacks. A case study is also deployed to replicate cyber attack scenarios on cyber-physical assets and provide a meticulous evaluation of the resilience performance of an energy cyber-physical framework, comprising a Smart PV Station, Data Infrastructure, and Digital Twin for essential services. Notably, the anomaly detection algorithm successfully identifies anomalous behavior induced by simulated cyber attacks, thereby averting the system from reacting to falsely imposed conditions. Furthermore, the assessment inspects the functionality and features of the framework, thus enriching our comprehension and quantification of cyber-physical infrastructure resilience through Resilience Key Performance Indicators.