Chiller Optimization Using Data Mining Based on Prediction Model, Clustering and Association Rule Mining

Elsa Chaerun Nisa, Yean- Der Kuan and Chin-Chang Lai
Additional contact information
Elsa Chaerun Nisa: Graduate Institute of Precision Manufacturing, National Chin-Yi University of Technology, Taichung 41170, Taiwan
Yean- Der Kuan: Refrigeration, Air Conditioning and Energy Engineering Department, National Chin-Yi University of Technology, Taichung 41170, Taiwan
Chin-Chang Lai: Refrigeration, Air Conditioning and Energy Engineering Department, National Chin-Yi University of Technology, Taichung 41170, Taiwan

Energies, 2021, vol. 14, issue 20, 1-14

Abstract: The chiller is the major energy consuming HVAC component in a building. Currently, huge chiller data is easy to obtain due to Internet of Things (IoT) technology development. In order to optimize the chiller system, this study presents a data mining technique that utilizes the available chiller data. The data mining techniques used are prediction model, clustering analysis, and association rules mining (ARM) analysis. The dataset was collected every minute for a year from a water-cooled chiller at an institutional building in Taiwan and from meteorological data. The power consumption prediction model was built using deep neural networks with 0.955 of R 2 , 4.470 of MAE, and 6.716 of RMSE. Clustering analysis was performed using the k-means algorithm and ARM analysis was performed using Apriori algorithm. Each cluster identifies those operational parameters that have strong association rules with high performance. The operational parameters from ARM were simulated using the prediction model. The simulation result shows that the ARM operational parameters can successfully save the energy consumption by 22.36 MWh or 18.17% in a year.

Keywords: chiller system; operational parameter optimization; data mining; prediction model; neural network; clustering analysis; ARM analysis; energy-saving (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.mdpi.com/1996-1073/14/20/6494/pdf (application/pdf)
https://www.mdpi.com/1996-1073/14/20/6494/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:14:y:2021:i:20:p:6494-:d:653247

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().