Approaches based on LAMDA control applied to regulate HVAC systems for buildings

Abstract

The control of HVAC (Heating Ventilation and Air Conditioning) systems is usually complex because its modeling in certain cases is difficult, since these systems have a large number of components. Heat exchangers, chillers, valves, sensors, and actuators, increase the non-linear characteristics of the complete model, so it is necessary to propose new control strategies that can handle the uncertainty generated by all these elements working together. On the other hand, artificial intelligence is a powerful tool that allows improving the performance of control systems with inexact models and uncertainties. This paper presents new control alternatives for HVAC systems based on LAMDA (Learning Algorithm for Multivariable Data Analysis). This algorithm has been used in the field of machine learning, however, we have taken advantage of its learning characteristics to propose different types of intelligent controllers to improve the performance of the overall control system in tasks of regulation and reference change. In order to perform a comparative analysis in the context of HVAC systems, conventional methods such as PID and Fuzzy-PID are compared with LAMDA-PID, LAMDA-Sliding Mode Control based on Z-numbers (ZLSMC), and Adaptive LAMDA. Specifically, two HVAC systems are implemented by simulations to evaluate the proposals: an MIMO (Multiple-input Multiple-output) HVAC system and an HVAC system with dead time, which are used to compare the results qualitatively and quantitatively. The results show that ZLSMC is the most robust controller, which efficiently controls HVAC systems in cases of reference changes and the presence of disturbances.