Smart Energy Utilization for Home Appliances Using Blockchain and Digital Twin Framework

Energy consumption has increased due to the growing usage of electrical appliances in contemporary homes, making predictive maintenance and effective monitoring techniques necessary. In order to improve energy efficiency and appliance management, this study suggests an Internet of Things (IoT)-based power consumption monitoring system that incorporates machine learning(ML) approaches. Predicting power consumption, detecting anomalies to predict failures, estimating appliance longevity, and scheduling maintenance with energy optimization are the four main goals of the system. It combines cloud-based storage, real-time data collecting via hardware implementation, and data-driven analytics that models appliance behaviour using synthetic datasets. The predictive modelling strategy makes use of survival analysis tools, such as Kaplan-Meier and Weibull distribution, for lifespan prediction, Isolation Forests for anomaly identification, and XGBoost for energy forecasting. In order to create an intelligent maintenance scheduling system that guarantees proactive service and optimizes energy use, power consumption trends are also examined. The system's ability to precisely predict energy usage, identify malfunctions, and enhance maintenance plans is demonstrated by experimental findings. Through the use of IoT and ML, this research advances the creation of intelligent energy management systems that improve sustainability, efficiency, and failure prediction in both residential and commercial settings.