The increasing deployment of renewable energy infrastructure such as solar photovoltaic systems, wind turbines, and smart grid components has created the need for advanced asset monitoring and lifecycle management strategies. Traditional maintenance approaches are often reactive, inefficient, and costly, leading to reduced system reliability and increased operational downtime. This study proposes a Digital Asset Management Framework that integrates Internet of Things (IoT)–based monitoring, Asset Health Index (AHI) modelling, machine learning–based predictive maintenance, and lifecycle optimization algorithms for sustainable energy infrastructure. The framework enables real-time acquisition of operational parameters including temperature, vibration, voltage, and power output from energy assets. These data are processed to compute asset health conditions and predict potential failures using machine learning models such as Random Forest, Artificial Neural Networks, and Support Vector Machines. Furthermore, optimization techniques including Genetic Algorithms and Particle Swarm Optimization are employed to determine optimal maintenance schedules and improve lifecycle performance. Simulation results demonstrate improvements in asset reliability, prediction accuracy, maintenance cost reduction, and system downtime minimization. The proposed framework provides an intelligent and scalable approach for enhancing operational efficiency and supporting sustainable energy infrastructure management.
Kukuchuku et al. (Sat,) studied this question.