Modeling and Optimizing a Chiller System Using a Machine Learning Algorithm

This study was conducted to develop an energy consumption model of a chiller in a heating, ventilation, and air conditioning system using a machine learning algorithm based on artificial neural networks. The proposed chiller energy consumption model was evaluated for accuracy in terms of input layers that include the number of input variables, amount (proportion) of training data, and number of neurons. A standardized reference building was also modeled to generate operational data for the chiller system during extended cooling periods (warm weather months). The prediction accuracy of the chiller’s energy consumption was improved by increasing the number of input variables and adjusting the proportion of training data. By contrast, the effect of the number of neurons on the prediction accuracy was insignificant. The developed chiller model was able to predict energy consumption with 99.07% accuracy based on eight input variables, 60% training data, and 12 neurons.

[1]  Maria del Carmen Pegalajar Jiménez,et al.  An Application of Non-Linear Autoregressive Neural Networks to Predict Energy Consumption in Public Buildings , 2016 .

[2]  Jin Woo Moon,et al.  Performance tests on the ANN model prediction accuracy for cooling load of buildings during the setback period , 2017 .

[3]  Nabil Nassif,et al.  Modeling and optimization of HVAC systems using artificial neural network and genetic algorithm , 2013, Building Simulation.

[4]  Ji-Hoon Jang,et al.  Prediction of optimum heating timing based on artificial neural network by utilizing BEMS data , 2019, Journal of Building Engineering.

[5]  Ashwin M. Khambadkone,et al.  Energy optimization methodology of multi-chiller plant in commercial buildings , 2017 .

[6]  M. Cannistraro,et al.  Testing a dual-source heat pump , 2018, Mathematical Modelling of Engineering Problems.

[7]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[8]  M. Cannistraro,et al.  Preliminary evaluation of the energy-saving behavior of a novel household refrigerator , 2019, Journal of Renewable and Sustainable Energy.

[9]  Haritza Camblong,et al.  A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation , 2018 .

[10]  Wonchang Choi,et al.  Development of Optimization Algorithms for Building Energy Model Using Artificial Neural Networks , 2017 .

[11]  Kyoung Sook Kim.  Study on the Edit form and the Discourse of the 『Sasanggye』in the 1950s - Focusing on 『Sasang』~ 『Sasanggye』 Published in 1959 , 2018 .

[12]  Chirag Deb,et al.  Forecasting diurnal cooling energy load for institutional buildings using Artificial Neural Networks , 2016 .

[13]  F. W. Yu,et al.  Improved energy management of chiller systems by multivariate and data envelopment analyses , 2012 .

[14]  Jui-Sheng Chou,et al.  Modeling heating and cooling loads by artificial intelligence for energy-efficient building design , 2014 .

[15]  Antonio Morán,et al.  A Data-Driven Approach for Enhancing the Efficiency in Chiller Plants: A Hospital Case Study , 2019 .

[16]  M. Cannistraro,et al.  Numerical analysis of a novel household refrigerator with controllable loop thermosyphons , 2019, International journal of refrigeration.