A Pattern-Recognition-Based Ensemble Data Imputation Framework for Sensors from Building Energy Systems
Open Access
- 21 October 2020
- Vol. 20 (20), 5947
- https://doi.org/10.3390/s20205947
Abstract
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.Keywords
This publication has 11 references indexed in Scilit:
- A bi-directional missing data imputation scheme based on LSTM and transfer learning for building energy dataEnergy and Buildings, 2020
- A systematic feature selection procedure for short-term data-driven building energy forecasting model developmentEnergy and Buildings, 2018
- Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networksApplied Energy, 2018
- A case study to examine the imputation of missing data to improve clustering analysis of building electrical demandBuilding Services Engineering Research and Technology, 2015
- Data mining in building automation system for improving building operational performanceEnergy and Buildings, 2014
- Data association mining for identifying lighting energy waste patterns in educational institutesEnergy and Buildings, 2013
- Multiple imputation: review of theory, implementation and softwareStatistics in Medicine, 2007
- Missing-Data Methods for Generalized Linear ModelsJournal of the American Statistical Association, 2005
- A Review of Methods for Missing DataEducational Research and Evaluation, 2001
- Missing Data, Imputation, and the BootstrapJournal of the American Statistical Association, 1994