Machine Learning Based Residential Energy Management System

Self-Discipline in performing energy management at a domestic level is expected as an inherent nature of every individual that cumulatively solves the problems of global energy crisis and climate change. Adhering to the fact that “Energy Management should start from Home”, Residential Energy Management System (REMS) is proposed in this paper that effectively switches possible loads to renewably energized local energy storage based on its charge-discharge transactions and grid availability thereby reducing the power consumption from the grid. Automation of switchover is performed using Artificial Neural Networks (ANN) and Support Vector Machine (SVM), machine learning algorithms for suggesting optimized humanlike decisions. The results prove that SVM is superior to ANN in terms of classification accuracy.