Residential Energy Management System using Machine Learning Algorithms

Residential Energy Management Systems (REMS) are emerging as a key solution to address energy efficiency and sustainability challenges in residential settings. Homeowners gain awareness of their energy consumption patterns, enabling them to make informed decisions and adopt energy-saving behaviors. REMS facilitate real-time feedback, helping individuals understand the impact of their actions on energy usage and promoting sustainable habits. Through intelligent control and coordination, homeowners can maximize the utilization of on-site solar panels or battery storage systems, reducing reliance on the grid and promoting clean energy generation. Based on the charging and discharging cycles, the REMS ensures the switching of loads to the storage systems energized by REGs, effectively. This paper uses Support Vector Machines (SVMs), and Machine Learning Algorithms (MLAs) to perform switching automation. This ensures a significant reduction in the grid-supplied power.