A Conceptual Model Development for Evaluating AI-Driven Predictive Maintenance in SCADA-Integrated Smart Grid Systems

This study develops a conceptual model for evaluating AI-driven predictive maintenance (PdM) in SCADA-integrated smart grid systems through a systematic review and meta-analysis conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines. A structured search across six major databases, IEEE Xplore, Scopus, Web of Science, ScienceDirect, ACM Digital Library, and Google Scholar, covering the period from January 2013 to December 2024 yielded 4,847 initial records, of which 63 studies met the full inclusion criteria following rigorous dual-reviewer screening, quality appraisal using the Newcastle-Ottawa Scale, and risk-of-bias assessment; pooled effect sizes were subsequently computed using a random-effects model (DerSimonian-Laird estimator) to account for inter-study heterogeneity (I² = 78.4%), with subgroup analyses stratified by AI algorithm type, grid segment, and SCADA integration depth. Meta-analytic findings revealed a weighted mean fault detection accuracy of 94.3% (95% CI: 92.1%–96.5%), with deep learning architectures — particularly LSTM and hybrid CNN-LSTM models — significantly outperforming traditional machine learning approaches (SMD = 0.67; 95% CI: 0.48–0.86, p < 0.001), and real-time SCADA-integrated configurations demonstrating markedly greater reductions in unplanned outage rates (SMD = 0.81; 95% CI: 0.59–1.03) relative to offline processing alternatives, with no significant publication bias detected via Egger's test (p = 0.16). Grounded in this synthesized evidence, the study proposes the SCADA-AI Predictive Maintenance Evaluation Framework (SAPMEF), a five-dimensional conceptual model encompassing data acquisition and sensor integration, AI model architecture selection, real-time SCADA communication fidelity, maintenance decision optimization, and grid resilience metrics, offering researchers, grid operators, and policymakers a structured, evidence-based instrument for benchmarking and deploying intelligent PdM solutions, while identifying cybersecurity resilience, model interpretability, and cross-grid transferability as critical priorities for future research.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.