Rising electricity costs and inefficient energy usage pose challenges for homeowners, particularly those with solar panels who struggle to maximize self-consumption. Homes excessively rely on the power grid due to limited visibility into their energy consumption patterns and insufficient control over their solar power utilization.
This project aims to develop a Smart Household Energy Management System that monitors energy usage, integrates solar power, and optimizes electricity consumption. By leveraging machine learning foreceasting and linear programming, the system will predict load demand and solar panel power output, schedule appliance usage, and minimize grid dependence.
The scope of our project includes designing an IoT-based energy monitoring system, developing an optimization algorithm for scheduling power consumption of deferrable/controllable loads, integrating real-time weather and pricing data, and implementing a dashboard for visualization and control. The system will provide automated energy management, enabling homeowners to reduce costs by at least 20% while maximizing solar self-consumption above 75%.
