Ongoing commissioning of water-cooled electric chillers using benchmarking models

This paper proposes two different types of benchmark models for the comparison of energy performance of water-cooled electric chillers: correlation-based models and Artificial Neural Network (ANN) models. Different techniques are proposed to establish the models and are evaluated with data collected from two chillers installed in an existing central cooling and heating plant. Both chillers have identical capacity and performance characteristics; however, they have quite different operating hours. The results show that models developed in this case study with 7 days of data monitored at the beginning of the summer season provide accurate results over the remaining of the summer and for the following summer. The proposed Multivariable Polynomial (MP) models for chillers provide the most accurate prediction with CV(RMSE) below 7% over the remaining of the summer season, and below 8% for the following summer season.