Predicting Human Activity and Energy Management in smart Home through Artificial Intelligence: A Review

Abstract

Human activity prediction plays a crucial role in energy management within smart homes. By understanding and anticipating residents’ daily behaviors, energy management systems can optimize resource usage by adjusting lighting, heating, or appliance consumption based on actual needs. This approach helps reduce energy consumption, minimize costs, and maximize energy efficiency. In this paper we provide a comprehensive review of human activity recognition and prediction methods, focusing on machine learning techniques. It also explores associated energy management methods, highlighting how these techniques, when combined with activity predictions, enable smarter and more autonomous energy management systems in connected homes.