Enablers of IoT ‐Driven Intelligent Buildings: Internet Technologies, AI ‐Based Energy Prediction, and Assessment Frameworks

With the rapid development of Internet technologies, intelligent buildings have become an important application scenario for the Internet of Things (IoT), artificial intelligence (AI), and data‐driven energy management. Balancing building energy consumption reduction with indoor comfort and living quality remains a critical challenge. This paper reviews and systematically analyzes representative studies related to IoT‐enabled intelligent building energy management. An integrated analytical framework is proposed to summarize energy consumption prediction and control strategies from four interconnected perspectives: (i) Internet‐based sensing and communication architectures, (ii) AI and machine learning algorithms for energy prediction, (iii) energy consumption assessment and evaluation methods, and (iv) the role of energy‐efficient building materials within IoT‐driven systems. The review reveals that most existing studies focus on isolated components, such as prediction models or sensing devices, while comprehensive system‐level analyses that integrate data acquisition, prediction, control, and feedback mechanisms remain limited. In particular, the interaction between energy prediction results, real‐time control strategies, and energy‐saving implementation is insufficiently explored. Furthermore, this study discusses how modern Internet technologies, including IoT platforms, big data analytics, and machine learning, enable the extraction of actionable insights from large‐scale data streams generated by intelligent buildings and smart cities. Finally, key research gaps, future development trends, and technical challenges for IoT‐based intelligent building energy prediction systems are identified, providing guidance for future Internet‐oriented energy management research.