فهرست نشریات علمی دسترسی آزاد ایران

The increasing energy consumption in smart buildings has created numerous challenges regarding environmental sustainability, operational costs, and energy efficiency. The Internet of Things, as an emerging technology, enables precise monitoring and control of energy consumption. However, a fundamental challenge in this domain is developing an optimization model that not only reduces energy consumption but also maintains user comfort levels. Previous studies have proposed various methods for managing energy consumption in smart buildings, including rule-based control, machine learning algorithms, and multi-objective models for simultaneously optimizing energy use and user comfort. Although these approaches have achieved improvements in energy efficiency, there remains a need for a more effective model that establishes a better balance between energy savings and user experience. In this paper, an energy consumption optimization model based on IoT and Multi-Objective Particle Swarm Optimization (MOPSO) is proposed, integrating data analysis from smart sensors, information processing through data mining techniques, and the Kalman filter for predicting subsequent time intervals of energy consumption. The proposed model not only aims to reduce energy consumption but also incorporates user comfort and satisfaction into the decision-making process. The MOPSO algorithm finds optimal solutions for multiple objectives simultaneously by updating particle positions in the search space. Simulation results demonstrate that the proposed model provides more effective optimization of energy consumption in smart buildings compared to previous models while simultaneously increasing user satisfaction. This model can serve as a practical solution for optimizing energy consumption in future smart infrastructure.