Automated pipeline framework for processing of large-scale building energy time series data

Arash Khalilnejad; Ahmad M. Karimi; Shreyas Kamath; Rojiar Haddadian; Roger H. French; Alexis R. Abramson

doi:10.1371/journal.pone.0240461

Automated pipeline framework for processing of large-scale building energy time series data

Arash Khalilnejad, Ahmad M. Karimi, Shreyas Kamath, Rojiar Haddadian, Roger H. French, Alexis R. Abramson

Research output: Contribution to journal › Article › peer-review

15 Scopus citations

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.

Original language	English
Article number	e0240461
Journal	PLoS ONE
Volume	15
Issue number	12 December
DOIs	https://doi.org/10.1371/journal.pone.0240461
State	Published - Dec 2020
Externally published	Yes

Funding

This work was supported by the U.S. Department of Energy, Advanced Research Projects Agency-Energy (ARPA-E), under award DE-AR-0000668. All the authors were funded or partially funded by this award. The detailed information is given in: https://arpa-e.energy.gov/ technologies/projects/virtual-building-energy-audits. This research was performed in the SDLE Research Center, established with Ohio Third Frontier funding under award Tech 11-060, Tech 12-004, and the Great Lakes Energy Institute, both at Case Western Reserve University. This work made use of the Rider High Performance Computing Resource in the Core Facility for Advanced Research Computing at Case Western Reserve University. The authors acknowledge useful discussions with Tian Wang.

Funders	Funder number
Advanced Research Projects Agency-Energy	Tech 12-004, Tech 11-060, DE-AR-0000668
Great Lakes Energy Institute
U.S. Department of Energy
Case Western Reserve University

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1371/journal.pone.0240461

Cite this

@article{f22478ac398c4ed6ae94759006d2388c,

title = "Automated pipeline framework for processing of large-scale building energy time series data",

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{\textquoteright} 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{\textquoteright}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.",

author = "Arash Khalilnejad and Karimi, {Ahmad M.} and Shreyas Kamath and Rojiar Haddadian and French, {Roger H.} and Abramson, {Alexis R.}",

note = "Publisher Copyright: {\textcopyright} 2020 Khalilnejad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.",

year = "2020",

month = dec,

doi = "10.1371/journal.pone.0240461",

language = "English",

volume = "15",

journal = "PLoS ONE",

issn = "1932-6203",

publisher = "Public Library of Science",

number = "12 December",

}

TY - JOUR

T1 - Automated pipeline framework for processing of large-scale building energy time series data

AU - Khalilnejad, Arash

AU - Karimi, Ahmad M.

AU - Kamath, Shreyas

AU - Haddadian, Rojiar

AU - French, Roger H.

AU - Abramson, Alexis R.

N1 - Publisher Copyright: © 2020 Khalilnejad et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

PY - 2020/12

Y1 - 2020/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85097036639&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0240461

DO - 10.1371/journal.pone.0240461

M3 - Article

C2 - 33259504

AN - SCOPUS:85097036639

SN - 1932-6203

VL - 15

JO - PLoS ONE

JF - PLoS ONE

IS - 12 December

M1 - e0240461

ER -

Automated pipeline framework for processing of large-scale building energy time series data

Abstract

Funding

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this