Minimizing energy consumption of an air handling unit with a computational intelligence approach

A data-mining approach is applied to optimize the energy consumption of an air handling unit. A multi-perceptron ensemble algorithm is used to model a chiller, a pump, and the supply and return fans. A non-linear model is developed to minimize the total energy consumption of the air-handling unit while maintaining the temperature of the supply air and the static pressure in a predetermined range. A dynamic, penalty-based, electromagnetism-like algorithm is designed to solve the proposed model. In all, 200 test data points are used to validate the proposed algorithm. The computational results show that the energy consumed by the air-handling unit is reduced by almost 23%.