A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers

In the process of collecting operational data for the performance analysis of water-cooled centrifugal chillers, missing values are inevitable due to various factors such as sensor errors, data transmission failures, and failure of the measurement system. When a substantial amount of missing data is...

Full description

Saved in:
Bibliographic Details
Main Authors: Sung Won Kim, Young Il Kim
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Energies
Subjects:
Online Access:https://www.mdpi.com/1996-1073/18/11/2779
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330904150835200
author Sung Won Kim
Young Il Kim
author_facet Sung Won Kim
Young Il Kim
author_sort Sung Won Kim
collection DOAJ
description In the process of collecting operational data for the performance analysis of water-cooled centrifugal chillers, missing values are inevitable due to various factors such as sensor errors, data transmission failures, and failure of the measurement system. When a substantial amount of missing data is present, the reliability of data analysis decreases, leading to potential distortions in the results. To address this issue, it is necessary to either minimize missing occurrences by utilizing high-precision measurement equipment or apply reliable imputation techniques to compensate for missing values. This study focuses on two water-cooled turbo chillers installed in Tower A, Seoul, collecting a total of 118,464 data points over 3 years and 4 months. The dataset includes chilled water inlet and outlet temperatures (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>2</mn></mrow></msub></mrow></semantics></math></inline-formula>) and flow rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>V</mi></mrow><mo>˙</mo></mover></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula>) and cooling water inlet and outlet temperatures (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>4</mn></mrow></msub></mrow></semantics></math></inline-formula>) and flow rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>V</mi></mrow><mo>˙</mo></mover></mrow><mrow><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula>), as well as chiller power consumption (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>W</mi></mrow><mo>˙</mo></mover></mrow><mrow><mi>c</mi></mrow></msub></mrow></semantics></math></inline-formula>). To evaluate the performance of various imputation techniques, we introduced missing values at a rate of 10–30% under the assumption of a missing-at-random (MAR) mechanism. Seven different imputation methods—mean, median, linear interpolation, multiple imputation, simple random imputation, k-nearest neighbors (KNN), and the dynamically clustered KNN (DC-KNN)—were applied, and their imputation performance was validated using MAPE and CVRMSE metrics. The DC-KNN method, developed in this study, improves upon conventional KNN imputation by integrating clustering and dynamic weighting mechanisms. The results indicate that DC-KNN achieved the highest predictive performance, with MAPE ranging from 9.74% to 10.30% and CVRMSE ranging from 12.19% to 13.43%. Finally, for the missing data recorded in July 2023, we applied the most effective DC-KNN method to generate imputed values that reflect the characteristics of the studied site, which employs an ice thermal energy storage system.
format Article
id doaj-art-d4fd077c4ba042f4aec2a0aeb1f0fd46
institution Kabale University
issn 1996-1073
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Energies
spelling doaj-art-d4fd077c4ba042f4aec2a0aeb1f0fd462025-08-20T03:46:46ZengMDPI AGEnergies1996-10732025-05-011811277910.3390/en18112779A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal ChillersSung Won Kim0Young Il Kim1Department of Architectural Engineering, Graduate School, Seoul National University of Science & Technology, Seoul 01811, Republic of KoreaSchool of Architectural, Seoul National University of Science & Technology, Seoul 01811, Republic of KoreaIn the process of collecting operational data for the performance analysis of water-cooled centrifugal chillers, missing values are inevitable due to various factors such as sensor errors, data transmission failures, and failure of the measurement system. When a substantial amount of missing data is present, the reliability of data analysis decreases, leading to potential distortions in the results. To address this issue, it is necessary to either minimize missing occurrences by utilizing high-precision measurement equipment or apply reliable imputation techniques to compensate for missing values. This study focuses on two water-cooled turbo chillers installed in Tower A, Seoul, collecting a total of 118,464 data points over 3 years and 4 months. The dataset includes chilled water inlet and outlet temperatures (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>2</mn></mrow></msub></mrow></semantics></math></inline-formula>) and flow rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>V</mi></mrow><mo>˙</mo></mover></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula>) and cooling water inlet and outlet temperatures (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>T</mi></mrow><mrow><mn>4</mn></mrow></msub></mrow></semantics></math></inline-formula>) and flow rate (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>V</mi></mrow><mo>˙</mo></mover></mrow><mrow><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula>), as well as chiller power consumption (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mover accent="true"><mrow><mi>W</mi></mrow><mo>˙</mo></mover></mrow><mrow><mi>c</mi></mrow></msub></mrow></semantics></math></inline-formula>). To evaluate the performance of various imputation techniques, we introduced missing values at a rate of 10–30% under the assumption of a missing-at-random (MAR) mechanism. Seven different imputation methods—mean, median, linear interpolation, multiple imputation, simple random imputation, k-nearest neighbors (KNN), and the dynamically clustered KNN (DC-KNN)—were applied, and their imputation performance was validated using MAPE and CVRMSE metrics. The DC-KNN method, developed in this study, improves upon conventional KNN imputation by integrating clustering and dynamic weighting mechanisms. The results indicate that DC-KNN achieved the highest predictive performance, with MAPE ranging from 9.74% to 10.30% and CVRMSE ranging from 12.19% to 13.43%. Finally, for the missing data recorded in July 2023, we applied the most effective DC-KNN method to generate imputed values that reflect the characteristics of the studied site, which employs an ice thermal energy storage system.https://www.mdpi.com/1996-1073/18/11/2779centrifugal chillerCVRSMEdata imputationDC-KNNMAPEperformance analysis
spellingShingle Sung Won Kim
Young Il Kim
A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
Energies
centrifugal chiller
CVRSME
data imputation
DC-KNN
MAPE
performance analysis
title A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
title_full A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
title_fullStr A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
title_full_unstemmed A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
title_short A Data Imputation Approach for Missing Power Consumption Measurements in Water-Cooled Centrifugal Chillers
title_sort data imputation approach for missing power consumption measurements in water cooled centrifugal chillers
topic centrifugal chiller
CVRSME
data imputation
DC-KNN
MAPE
performance analysis
url https://www.mdpi.com/1996-1073/18/11/2779
work_keys_str_mv AT sungwonkim adataimputationapproachformissingpowerconsumptionmeasurementsinwatercooledcentrifugalchillers
AT youngilkim adataimputationapproachformissingpowerconsumptionmeasurementsinwatercooledcentrifugalchillers
AT sungwonkim dataimputationapproachformissingpowerconsumptionmeasurementsinwatercooledcentrifugalchillers
AT youngilkim dataimputationapproachformissingpowerconsumptionmeasurementsinwatercooledcentrifugalchillers