Adaptive multi-task ensemble framework for smart home automation

Abstract

Smart home technology has evolved rapidly with an emphasis on indoor environmental control. It aims to automate the control of the indoor environment through sensors, regulators, and other technologies in order to improve comfort, energy saving, emission reduction, safety, and intelligence. However, there is still a research gap between existing research and real-world applications. Most studies focus on modeling individual regulators, neglecting the cooperation between elements that influence the experience of the occupants. This leads to several cooperation issues like inconsistent and overlapping control. In addition, few studies have focused on the performance degradation of the entire system over the life cycle. To bridge the above missing gap, this paper proposes an adaptive multi-task framework that combines graph neural networks, multi-task learning, and incremental learning to achieve better cooperation and synergy among multiple regulators. The framework has been successfully tested on a wide range of smart home automation systems, achieving a 5–15 % improvement in performance for each individual regulator. Meanwhile, the proposed framework also demonstrates significant advantages against performance degradation over the life cycle. It provides a feasible, user-friendly, consumer-oriented framework for indoor environment automation that assists the entire system to improve the user experience.