From Data to Behavior: Artificial Intelligence-driven Insights for Sustainable Energy Management

Abstract

The Internet of Behavior (IoB) is an emerging research domain that uses behavioral insights from the Internet of Things (IoT)- generated data to analyze and influence human actions. In the context of growing energy demand and the need for sustainable resource management, IoB systems offer a promising approach to optimizing energy consumption, enabling personalized demand-response mechanisms, and developing adaptive energy efficiency strategies considering user preferences and environmental conditions. While several surveys have explored IoB applications in various domains, no comprehensive review has specifically focused on its role in the energy sector. This paper addresses this gap by providing the first systematic review of IoB applications for energy consumption through a structured taxonomy that categorizes and analyzes existing research based on five key dimensions: application scope, Machine Learning (ML) techniques, optimization strategies, behavioral influence types, and explainability approaches. Additionally, a comparative analysis of state-of-the-art methodologies is presented, highlighting key trends in Artificial Intelligence (AI)-driven IoB architectures and their respective strengths and challenges. Furthermore, this study synthesizes current advancements and identifies critical issues related to IoB in the energy sector, such as ethical concerns, data privacy, and scalability. By laying the groundwork for future research, this review establishes a foundation for developing robust and human-centric AI-powered IoB systems, paving the way for transformative solutions in sustainable energy management.