Balancing thermal comfort and energy conservation– A multi-objective optimization model for controlling air-condition and mechanical ventilation systems

Abstract

Building air condition and mechanical ventilation (ACMV) systems which provide cooling operations suffers from the balance between thermal comfort (TC) and energy consumption (EC). This study presents a multi-objective optimization model that resolves the trade-off between TC and EC. Four operating variables are selected as decision variables because they significantly affect TC and EC. Firstly, the component power consumption pattern of the ACMV system (that is, fan, pump, and compressor) is built by a semi-empirical model. Then EC is modeled as a function of the component power consumption pattern and air temperature. Secondly, TC is modeled as a function of environmental, personal, and human-robot collaboration variables. Thirdly, an artificial neural network (ANN) was constructed as a prediction model of TC and EC. Then, ANN is coupled with multi-objective whale optimization algorithm for optimization of decision variables. Sensitivity analysis was carried out to examine the variation of decision variables. Experiment result shows that (1) the proposed ANN for TC and EC exhibits high performance with a goodness-of-fit of 98.83% and 98.25% respectively. (2) The optimization model reduces a 16.51% of EC and improves TC by 49.06% as compared to the reference operation. This study successfully builds a multi-objective optimization model of an ACMV system for TC and EC.