Logistic regression-based optimal control for air-cooled chiller

Predictive chiller operation: A data-driven loading and scheduling approach

“…Mainly two types of methodologies can be found on the literature, i) generic global optimization tools and ii) specific heuristics-based controller implementations. Generic global optimization tools are common in chiller control applications, a study of air-cooled chillers optimal control used random forests to implement an empirical model of the chillers and then applied generic algorithms to carry out the estimation of the optimal values of the control parameters [19].…”

Model-Based Condenser Fan Speed Optimization of Vapor Compression Systems

“…In this context, Scarpa et al [13] have stated that the most accurate models lead to a COP estimation error of ±5%, and ±10% can be considered as a high level of accuracy. In fact, the most models for set-point optimization perform a COP estimation accuracy of about ±10% [14][15][16][17][18][19][20]. The ideal condenser fan speed exhibits a strong dependence on the ambient temperature and the refrigeration capacity [7,8].…”

“…Using different modeling approaches, various optimizing system controls of varying complexity are proposed in the literature [21,22]. As a simple solution, the ideal condenser fan speed can be determined in advance to derive a linear function [7,8] or a regression [19,23] for control. In 2004, Chan and Yu [8] published a control of the condensing temperature as a linear function of the ambient temperature.…”

“…In 2004, Chan and Yu [8] published a control of the condensing temperature as a linear function of the ambient temperature. In a further publication, Yu and Chang [19] suggested a load-based speed control for a small ambient temperature range. These solutions can provide a significant improvement compared to the traditional constant condensing pressure control, but only achieve suboptimal results for different operating conditions of ambient temperature and cooling load [7,8].…”

“…Model predictions and test data of the refrigerant mass flow rate are provided in Figure 10. With respect to Equation (19), the mass flow rate calculation includes the errors due to the component modeling of the evaporator, compressor, and condenser. However, for varying input parameters, the coefficient of determination is 99.67%, and for constant inputs is 99.27%.…”