Independent Researcher, USA.
Research Article
World Journal of Advanced Research and Reviews, 2022, 15(03), 631-639
Article DOI: 10.30574/wjarr.2022.15.3.0954
Received on 16 August 2022; revised on 24 September 2022; accepted on 28 September 2022
This paper introduces PredictNet, a novel AI-enabled predictive maintenance system designed specifically for telecommunications infrastructure. The research addresses the critical challenge of maintaining reliability in increasingly complex telecom networks while reducing operational costs. Using machine learning algorithms and real-time sensor data, PredictNet demonstrates superior performance in predicting equipment failures before they occur. The system was implemented and tested on a mid-sized telecommunications network over a 12-month period, achieving 92.7% prediction accuracy with a mean time-to-failure prediction of 18.3 days. Results show a 43% reduction in network downtime and 37% decrease in maintenance costs compared to traditional scheduled maintenance approaches. The study validates PredictNet's effectiveness and provides a framework for implementing AI-driven predictive maintenance in telecommunications infrastructure.
Predictive Maintenance; Artificial Intelligence; Machine Learning; Telecommunications Infrastructure; Network Reliability
Preview Article PDF
Mohamed Abdul Kadar Mohamed Jabarullah. PredictNet: AI-enabled predictive maintenance system for telecommunications infrastructure reliability. World Journal of Advanced Research and Reviews, 2022, 15(3), 631-639. Article DOI: https://doi.org/10.30574/wjarr.2022.15.3.0954