9NL, CTO, Victoria Island, Lagos, Nigeria.
Research Article
World Journal of Advanced Research and Reviews, 2021, 09(03), 409-428
Received on 19 January 2021; revised on 16 March 2021; accepted on 18 March 2021
The integration of cloud-native artificial intelligence (AI) technologies into predictive maintenance frameworks within the energy sector has emerged as a pivotal paradigm for enhancing operational reliability, optimizing asset performance, and minimizing unplanned downtime. This paper presents a comprehensive analysis of cloud-native AI solutions specifically tailored for predictive maintenance, emphasizing the inherent security implications associated with deploying such architectures in mission-critical energy infrastructures. Through an in-depth exploration of containerized microservices, edge-cloud orchestration, real-time data ingestion pipelines, and AI-driven anomaly detection algorithms, this study underscores the technical sophistication and adaptability of cloud-native approaches. Special attention is given to the security posture of these systems, including vulnerabilities arising from distributed computing, data privacy concerns, threat vectors in multi-tenant cloud environments, and secure model deployment practices. The paper further explores regulatory and compliance considerations in the context of cybersecurity standards for energy systems. The findings highlight the dual imperative of maintaining system integrity while leveraging scalable AI solutions for predictive insights.
Cloud-native; Artificial intelligence; Predictive maintenance; Energy sector; cybersecurity; Microservices; Edge computing; Data privacy; Anomaly detection; Regulatory compliance
Preview Article PDF
Akinniyi James Samuel. Cloud-Native AI solutions for predictive maintenance in the energy sector: A security perspective. World Journal of Advanced Research and Reviews, 2021, 9(3), 409-428. Article DOI: https://doi.org/10.30574/wjarr.2021.9.3.0052