The rapid integration of renewable generation, distributed energy resources, and advanced monitoring infrastructures has increased the demand for data-driven methods in modern power systems. Artificial neural networks (ANNs) have become widely adopted for load forecasting, fault diagnosis, state estimation, stability assessment, and energy management. Despite substantial publication growth, large-scale operational deployment of ANN-based solutions remains limited. This study presents a bibliometric and engineering assessment of ANN applications in power systems between 2020 and 2024, based on 1511 SCI-Expanded journal articles retrieved from the Web of Science. Beyond conventional science mapping, the study integrates an engineering-oriented deployment-readiness evaluation that systematically links ANN architectures with core operational problem classes. The results reveal a significant imbalance between reported algorithmic performance and operational validation rigor. Forecasting and energy management applications demonstrate relatively higher readiness due to real-world dataset usage, whereas fault diagnosis and state estimation remain predominantly simulation-driven and lack explainability and robustness validation. A deployment-readiness matrix is applied to quantitatively evaluate dataset realism, interpretability integration, and reliability considerations across domains. The findings indicate that the primary barriers to ANN integration in power systems stem from insufficient validation protocols and resilience-oriented design rather than algorithmic limitations, highlighting key engineering priorities for reliable real-world implementation.
YELDA KARATEPE MUMCU (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: