Abstract
Commercial buildings account for one third of the total electricity consumption in the United States and a significant amount of this energy is wasted. Therefore, there is a need for "virtual" energy audits, to identify energy inefficiencies and their associated savings opportunities using methods that can be non-intrusive and automated for application to large populations of buildings. Here we demonstrate virtual energy audits applied to large populations of buildings' time-series smart-meter data using a systematic approach and a fully automated Building Energy Analytics (BEA) Pipeline that unifies, cleans, stores and analyzes building energy datasets in a non-relational data warehouse for efficient insights and results. This BEA pipeline is based on a custom compute job scheduler for a high performance computing cluster to enable parallel processing of Slurm jobs. Within the analytics pipeline, we introduced a data qualification tool that enhances data quality by fixing common errors, while also detecting abnormalities in a building's daily operation using hierarchical clustering. We analyze the HVAC scheduling of a population of 816 buildings, using this analytics pipeline, as part of a cross-sectional study. With our approach, this sample of 816 buildings is improved in data quality and is efficiently analyzed in 34 minutes, which is 85 times faster than the time taken by a sequential processing. The analytical results for the HVAC operational hours of these buildings show that among 10 building use types, food sales buildings with 17.75 hours of daily HVAC cooling operation are decent targets for HVAC savings. Overall, this analytics pipeline enables the identification of statistically significant results from population based studies of large numbers of building energy time-series datasets with robust results. These types of BEA studies can explore numerous factors impacting building energy efficiency and virtual building energy audits. This approach enables a new generation of data-driven buildings energy analysis at scale.
Highlights
Buildings account for approximately one-third of the world’s total electricity consumption [1]
We have developed a virtual energy audits tool, EDIFES (Energy Diagnostics Investigator for Efficiency Savings) using a data-driven analytical approach based on smart-meter data provided by electrical utility companies or building owners [4,5,6,7,8]
Studies show that the HBase model, an open-source, non-relational data warehouse that runs on top of Hadoop Distributed File System (HDFS), if implemented properly, could be very efficient for machine learning applications in large-scale energy time series datasets [18]
Summary
Buildings account for approximately one-third of the world’s total electricity consumption [1]. We have developed a virtual energy audits tool, EDIFES (Energy Diagnostics Investigator for Efficiency Savings) using a data-driven analytical approach based on smart-meter data provided by electrical utility companies or building owners [4,5,6,7,8] Another important challenge for the large scale application of virtual energy audits is the ability to analyze large numbers of buildings and volumes of building time-series data so that energy savings across distinct building populations can be prioritized and buildings can be compared and ranked [9, 10]. Is an advanced high performance computing cluster essential, but a robust job scheduling pipeline that can automatically ingest, process and analyze the datasets and rank-order and compare the results is required For this purpose, NoSQL databases address the dataset scalability issues of peta-byte scale analyses and have seen increasing use in energy research [14]. Studies show that the HBase model, an open-source, non-relational data warehouse that runs on top of HDFS, if implemented properly, could be very efficient for machine learning applications in large-scale energy time series datasets [18]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
