Automated daily pattern filtering of measured building performance data


The amount of sensor data generated by modern building systems is growing rapidly. Automatically discovering the structure of diurnal patterns in this data supports implementation of building commissioning, fault detection and retrofit analysis techniques. Additionally, these data are crucial to informing design professionals about the efficacy of their assumptions and strategies used in performance prediction simulation models. In this paper, we introduce DayFilter, an day-typing process that uses symbolic aggregate approximation (SAX), motif and discord extraction and clustering to detect the underlying structure of building performance data. Discords, or infrequent daily patterns, are filtered and tagged for deeper, detailed analysis of potential energy savings opportunities. Motifs, or the most frequent patterns, are detected and further aggregated using k-means clustering. This procedure is designed for application on whole building and sub-system metrics from hierarchical building and energy management systems (BMS/EMS). The process transforms quantitative raw data into qualitative subgroups based on daily performance similarity and visualizes them using expressive techniques. We apply DayFilter on 474 days of example data from an international school campus in a tropical climate and 407 days of data from an office building from a temperate European climate. Discords were filtered resulting in 17 and 22 patterns were found. Selected discords were investigated and many correlated with specific failures and energy savings detected by the on-site operations staff. Six and ten motif candidates were detected in the two case studies. These motifs were then further aggregated to five and six performance clusters that reflect the typical operational behavior of those projects. Finally, we discuss the influence of the parameter choices and provide initial parameter settings for the DayFilter process.



Performance and energy data generation in the built environment is rapidly growing (Khan 2011). Modern building controls and management systems are improving in their ability to acquire and store measured data as costs of these features are reduced. This phenomenon results in vast portfolios of collected data from heterogeneous buildings. Figure \ref{fig:hierarchy} illustrates a general example of various types of measured data from a conventional commercial building. Whole building performance is influenced by layers of complex measurement systems. Aggregated performance metrics or sensors are often measured or calculated at each level of this hierarchy in order to condense the exponential detailed sensor data downstream.

\label{fig:hierarchy} Example of levels of building performance data complexity