Yanine, Franco FernandoHidalgo, MauricioFrez, JonathanRao, Challa KrishnaSahoo, Sarat Kumar2026-08-262026-08-262026-08-26Sustainability, Vol. 18, N° 17 (2026), pp. 1-31https://hdl.handle.net/20.500.12254/7719The rapid integration of solar photovoltaic (PV) generation, distributed energy resources, and advanced communication infrastructures is transforming conventional power systems into highly interconnected cyber–physical smart grids. Although this transition improves sustainability and operational flexibility, it also increases grid-management complexity and introduces cyber–physical vulnerabilities, including false data injection attacks, communication failures, equipment degradation, and renewable-induced operational instabilities. This paper presents the Digital-Twin-Enabled Resilience Framework (DTERF), a conceptual reference architecture for anomaly detection in high-PV cyber–physical smart grids. DTERF integrates heterogeneous cyber–physical data acquisition, Digital Twin-based contextual representation, machine-learning analytics, explainable decision support, adaptive operational response, continuous learning, and self-healing capabilities within a unified resilience cycle. The framework is grounded in a structured review and comparative assessment ofcontemporary machine-learning approaches and recent integrated smart-grid research. Itsarchitecture is conceptually evaluated through requirements-to-architecture traceability, examining functional coverage and internal consistency across the complete operational cycle. The analysis shows that DTERF provides explicit architectural mechanisms addressing the principal requirements identified in the literature, including contextual anomaly analysis, interpretability, cybersecurity robustness, resilience support, and operational integration. Rather than proposing a new anomaly detection algorithm or claiming empirical performance superiority, DTERF provides a technology-agnostic architectural foundationfor coordinating complementary capabilities required for resilient anomaly management. Future work should empirically validate the framework using Digital Twin simulation environments, representative high-PV distribution systems, cyber–physical anomaly scenarios, and real or utility-derived operational data.enAtribución-NoComercial-CompartirIgual 3.0 Chile (CC BY-NC-SA 3.0 CL)machine learninganomaly detectionexplainable artificial intelligenceself-healing smart gridsgrid resiliencedigital twincyber–physical smart gridsArticlehttps://orcid.org/0000-0003-1086-0840https://doi.org/10.3390/su181787242071-1050