Artificial Intelligent Approaches for Modeling and Optimizing HVAC Systems

Abstract

Advanced energy management control systems (EMCS) offer an excellent means of reducing energy consumption in heating, ventilating, and air conditioning (HVAC) systems while maintaining and improving indoor environmental conditions. This can be achieved through the use of computational intelligence and optimization. This research will evaluate model-based optimization processes for HVAC systems utilizing MATLAB’s neural network Toolbox, which minimizes the error between measured and predicted performance data. The process can be integrated into the EMCS to perform several intelligent functions achieving optimal system performance. The development of a neuron model and optimizing the process will be tested using data collected from an existing HVAC system of a building on the campus of NC A&T State University.

This proposed research focuses on control strategies and Artificial Neural Networks (ANN) within a building automation system (BAS) controller. The controller will achieve the lowest energy consumption while maintaining occupant comfort by performing and prioritizing the appropriate actions. Recent technological advances in computing power, sensors, and databases will influence the cost savings and scalability of the system. Improved energy efficiencies of existing Variable Air Volume (VAV) HVAC systems can be achieved by optimizing the control sequence leading to advanced BAS programming. The program’s algorithms analyze multiple variables (humidity, pressure, temperature, CO₂, etc.) simultaneously at key locations throughout the HVAC system (pumps, cooling tower, chiller, fan, etc.) to reach the function’s objective, which is the lowest energy consumption while maintaining occupancy comfort.