A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems
Building operation data are important for monitoring, analysis, modeling, and control of building energy systems. However, missing data is one of the major data quality issues, making data imputation techniques become increasingly important. There are two key research gaps for missing sensor data im...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/20/5947 |
| _version_ | 1797550351008661504 |
|---|---|
| author | Liang Zhang |
| author_facet | Liang Zhang |
| author_sort | Liang Zhang |
| collection | DOAJ |
| description | Building operation data are important for monitoring, analysis, modeling, and control of building energy systems. However, missing data is one of the major data quality issues, making data imputation techniques become increasingly important. There are two key research gaps for missing sensor data imputation in buildings: the lack of customized and automated imputation methodology, and the difficulty of the validation of data imputation methods. In this paper, a framework is developed to address these two gaps. First, a validation data generation module is developed based on pattern recognition to create a validation dataset to quantify the performance of data imputation methods. Second, a pool of data imputation methods is tested under the validation dataset to find an optimal single imputation method for each sensor, which is termed as an ensemble method. The method can reflect the specific mechanism and randomness of missing data from each sensor. The effectiveness of the framework is demonstrated by 18 sensors from a real campus building. The overall accuracy of data imputation for those sensors improves by 18.2% on average compared with the best single data imputation method. |
| first_indexed | 2024-03-10T15:27:58Z |
| format | Article |
| id | doaj.art-daaaa259e6b544b3b18dcefcce533e93 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:27:58Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-daaaa259e6b544b3b18dcefcce533e932023-11-20T17:56:46ZengMDPI AGSensors1424-82202020-10-012020594710.3390/s20205947A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy SystemsLiang Zhang0National Renewable Energy Laboratory, Buildings and Thermal Sciences Center, Golden, CO 80401, USABuilding operation data are important for monitoring, analysis, modeling, and control of building energy systems. However, missing data is one of the major data quality issues, making data imputation techniques become increasingly important. There are two key research gaps for missing sensor data imputation in buildings: the lack of customized and automated imputation methodology, and the difficulty of the validation of data imputation methods. In this paper, a framework is developed to address these two gaps. First, a validation data generation module is developed based on pattern recognition to create a validation dataset to quantify the performance of data imputation methods. Second, a pool of data imputation methods is tested under the validation dataset to find an optimal single imputation method for each sensor, which is termed as an ensemble method. The method can reflect the specific mechanism and randomness of missing data from each sensor. The effectiveness of the framework is demonstrated by 18 sensors from a real campus building. The overall accuracy of data imputation for those sensors improves by 18.2% on average compared with the best single data imputation method.https://www.mdpi.com/1424-8220/20/20/5947missing datadata imputationensemble methodpattern recognitionmachine learningbuilding sensors |
| spellingShingle | Liang Zhang A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems Sensors missing data data imputation ensemble method pattern recognition machine learning building sensors |
| title | A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems |
| title_full | A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems |
| title_fullStr | A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems |
| title_full_unstemmed | A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems |
| title_short | A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems |
| title_sort | pattern recognition based ensemble data imputation framework for sensors from building energy systems |
| topic | missing data data imputation ensemble method pattern recognition machine learning building sensors |
| url | https://www.mdpi.com/1424-8220/20/20/5947 |
| work_keys_str_mv | AT liangzhang apatternrecognitionbasedensembledataimputationframeworkforsensorsfrombuildingenergysystems AT liangzhang patternrecognitionbasedensembledataimputationframeworkforsensorsfrombuildingenergysystems |