Imputation of missing values in residential building monitored data: Energy consumption, behavior, and environment information

This study compares missing value handling algorithms based on the type of missing value occurrence for building monitored data. The study data comprised energy consumption and occupancy data for residential buildings and indoor and outdoor environmental information. The missing mechanism was assumed to be missing completely at random (MCAR), with random missing data generated by assuming missing rates of 10-50 % to simulate various missing scenarios. The missing value handling algorithms applied statistical imputation methods and data-driven approaches. The normalized root mean squared error was calculated to verify the imputation and measurement error. The results showed that the appropriate missing value handling algorithm depends on the building energy monitoring data items and type of missingness. For both temporal resolutions, the results show that the data-driven model performs well in estimating missing values for energy consumption data by use, while the linear interpolation imputation method performs well for environmental and occupancy information. These results demonstrate the effectiveness of considering the characteristics of data items and the type of missing values when dealing with missing values and implys that previously underutilized data-driven models could be valuable imputation algorithms.