Published Paper Details:

The energy consumed by heating, ventilating, and air conditioning (HVAC) systems has been Increasing over the last decades. Thus, improving efficiency of HVAC systems has gained attention of industry and academia. This concern has posed challenges for modeling and optimizing HVAC systems. The traditional methods, such as analytical and statistical approaches, usually involve assumptions that may not hold in practice since HVAC systems are complex, nonlinear, and dynamic. Data-mining is a novel science aiming at extracting system characteristics, identifying models and recognizing patterns from large-size data sets. It has proved its power in modeling complex and nonlinear systems through various effective and successful applications in industrial, business, and medical areas. Applications of classical data-mining approaches, such as neural networks and boosting tree have been reported in the HVAC literature. Evolutionary computation, including swarm intelligence, have rapidly developed in the past decades and then applied to improving the performance of HVAC systems. This analysis focuses on modeling, optimizing, and controlling HVAC systems. Data-mining algorithms are utilized to extract predictive models from experimental data sets provided by the Energy Resource Station located in Ankeny,. In the optimization process, two set points of the HVAC system, supply air duct static pressure set point and supply air temperature set point, are controlled aiming at improving energy efficiency and maintaining thermal comfort. However, for some special projects, due to the specific design and control of the HVAC system, conventional settings may not be necessarily energy-efficient in daily operation. The HVAC system design and equipment selection for a commercial building (376 TR) is included as a case study in this paper. The outcomes of this paper are efficient design of HVAC system with minimum energy consumption and equipment selection based on operating