Volume 17, Number 6

IOT-Based Smart Building Monitoring and Control Strategies with Intelligence Deep Neural Networks

  Authors

Tony Tsang and Yau Ka Hei, Hong Kong College of Technology, Hong Kong

  Abstract

This paper systematically discusses the application of Internet of Things (IoT) technology in intelligent building monitoring and control, focusing on its core role in energy management, environmental regulation, equipment maintenance and security monitoring. By integrating sensor networks, data communication layers, intelligent decision-making and execution layers, this study constructs an IoT-based intelligent building management framework, aiming to achieve real-time monitoring and dynamic optimization of the building environment. The literature review summarizes the current status of IoT technology applications in intelligent buildings, including innovative practices of algorithms such as support vector machines (SVM) and deep reinforcement learning in equipment control and energy scheduling, and points out the challenges such as sensor deployment, data integration and communication protocol optimization. Through case analysis and mathematical modelling (such as multi-objective optimization model and Q learning algorithm), the study verifies the significant advantages of deep neural networks (DNN)[1] in prediction accuracy and response with an accuracy of 85.2%, which is better than the traditional linear regression and SVM models. Preliminary data shows that the IoT system can dynamically adjust temperature, humidity and lighting intensity, reducing energy waste by more than 30%. Future research will focus on the integration of edge computing and distributed architecture to improve real-time and scalability of the system and to promote the evolution of smart buildings towards efficiency, greenness and adaptability.

  Keywords

Internet of Things (IoT), smart buildings, energy management, deep reinforcement learning, edge computing