The paper presents the design and implementation of an AI-enabled smart timer-based power control and energy monitoring solution for household appliances. The proposed system integrates real-time sensing of electrical device parameters with cloud artificial intelligence for predictive analytics and automatic control. Continuous measurement of voltage, current and power consumption of the connected appliances are performed for analysis of the usage patterns. The appliance operation is completely automated by choosing between the best option which is the user-defined schedule or the load shifted schedule recommended by AI. The AI recommendation depends on peak demand of the day and the current load requirement thereby aiding approximate smoothening of daily load curve and improving load factor. The data collected is transmitted to the cloud for real-time and historical data collection, for prediction of consumption patterns, anomaly detection, and clustering appliances according to their operational behavior. A machine learning model trained on an energy dataset enhances decision-making by predicting overload conditions and distributing the load throughout the day. A mobile interface provides live monitoring, cost estimation, scheduling, and control. The modular design allows the proposed solution to be scalable by adding an additional appliance.
The experimental evaluation provided evidence of the system’s ability to predict an overload condition, and its capacity to shift loads to off-peak hours thereby providing energy savings of 20-30%, based on usage patterns. By integrating IoT monitoring, cloud analytics, and AI-enabled automation the proposed system overcomes the limitations of standard metering, and high-cost proprietary solutions. Overall, it offers a scalable, cost-effective, and intelligent approach to appliance-level energy management, fostering sustainable energy practices and reducing operating costs.