Model predictive control of HVAC chilled water system based on load forecasting

The Heating, Ventilation, and Air Conditioning (HVAC) system is a critical component of building energy consumption, accounting for a significant portion of total energy usage. Given the inherent nonlinearity, susceptibility to environmental variations, and stringent energy efficiency requirements of HVAC systems, traditional control strategies, often based on fixed rules or empirical knowledge, frequently fall short in their ability to dynamically adjust control parameters and achieve substantial energy savings. This paper introduces a novel Model Predictive Control (MPC) approach for chilled water systems, leveraging genetic algorithms to optimize control strategies. The proposed methodology is designed to enhance energy efficiency by implementing an energy-saving optimal control scheme, complemented by the formulation of rational objective functions and constraint conditions. Experimental validation conducted on a simulation platform demonstrates that the proposed control strategy not only significantly improves system energy efficiency but also exhibits robust performance and reliability under various operational conditions. The results show that the optimized MPC strategy achieves a 10%−15% reduction in total energy consumption, providing a valuable reference for building energy efficiency management.