Collaborative data analytics for smart buildings: opportunities and models

Sanja Lazarova-Molnar*, Nader Mohamed

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Smart buildings equipped with state-of-the-art sensors and meters are becoming more common. Large quantities of data are being collected by these devices. For a single building to benefit from its own collected data, it will need to wait for a long time to collect sufficient data to build accurate models to help improve the smart buildings systems. Therefore, multiple buildings need to cooperate to amplify the benefits from the collected data and speed up the model building processes. Apparently, this is not so trivial and there are associated challenges. In this paper, we study the importance of collaborative data analytics for smart buildings, its benefits, as well as presently possible models of carrying it out. Furthermore, we present a framework for collaborative fault detection and diagnosis as a case of collaborative data analytics for smart buildings. We also provide a preliminary analysis of the energy efficiency benefit of such collaborative framework for smart buildings. The result shows that significant energy savings can be achieved for smart buildings using collaborative data analytics.
Original languageEnglish
JournalCluster Computing: The Journal of Networks, Software Tools and Applications
Volume22
Issue numberSupplement. 1
Pages (from-to)1065-1077
ISSN1386-7857
DOIs
Publication statusPublished - 16. Jan 2019

Fingerprint

Intelligent buildings
Fault detection
Failure analysis
Energy efficiency
Energy conservation
Sensors

Keywords

  • Collaborative data analytics
  • Energy efficiency
  • Fault detection and diagnosis
  • Models
  • Smart buildings

Cite this

@article{b4dcfebab9f44887adefccf2149ad22f,
title = "Collaborative data analytics for smart buildings: opportunities and models",
abstract = "Smart buildings equipped with state-of-the-art sensors and meters are becoming more common. Large quantities of data are being collected by these devices. For a single building to benefit from its own collected data, it will need to wait for a long time to collect sufficient data to build accurate models to help improve the smart buildings systems. Therefore, multiple buildings need to cooperate to amplify the benefits from the collected data and speed up the model building processes. Apparently, this is not so trivial and there are associated challenges. In this paper, we study the importance of collaborative data analytics for smart buildings, its benefits, as well as presently possible models of carrying it out. Furthermore, we present a framework for collaborative fault detection and diagnosis as a case of collaborative data analytics for smart buildings. We also provide a preliminary analysis of the energy efficiency benefit of such collaborative framework for smart buildings. The result shows that significant energy savings can be achieved for smart buildings using collaborative data analytics.",
keywords = "Collaborative data analytics, Energy efficiency, Fault detection and diagnosis, Models, Smart buildings",
author = "Sanja Lazarova-Molnar and Nader Mohamed",
year = "2019",
month = "1",
day = "16",
doi = "10.1007/s10586-017-1362-x",
language = "English",
volume = "22",
pages = "1065--1077",
journal = "Cluster Computing: The Journal of Networks, Software Tools and Applications",
issn = "1386-7857",
publisher = "Springer",
number = "Supplement. 1",

}

Collaborative data analytics for smart buildings: opportunities and models. / Lazarova-Molnar, Sanja; Mohamed, Nader.

In: Cluster Computing: The Journal of Networks, Software Tools and Applications, Vol. 22, No. Supplement. 1, 16.01.2019, p. 1065-1077.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Collaborative data analytics for smart buildings: opportunities and models

AU - Lazarova-Molnar, Sanja

AU - Mohamed, Nader

PY - 2019/1/16

Y1 - 2019/1/16

N2 - Smart buildings equipped with state-of-the-art sensors and meters are becoming more common. Large quantities of data are being collected by these devices. For a single building to benefit from its own collected data, it will need to wait for a long time to collect sufficient data to build accurate models to help improve the smart buildings systems. Therefore, multiple buildings need to cooperate to amplify the benefits from the collected data and speed up the model building processes. Apparently, this is not so trivial and there are associated challenges. In this paper, we study the importance of collaborative data analytics for smart buildings, its benefits, as well as presently possible models of carrying it out. Furthermore, we present a framework for collaborative fault detection and diagnosis as a case of collaborative data analytics for smart buildings. We also provide a preliminary analysis of the energy efficiency benefit of such collaborative framework for smart buildings. The result shows that significant energy savings can be achieved for smart buildings using collaborative data analytics.

AB - Smart buildings equipped with state-of-the-art sensors and meters are becoming more common. Large quantities of data are being collected by these devices. For a single building to benefit from its own collected data, it will need to wait for a long time to collect sufficient data to build accurate models to help improve the smart buildings systems. Therefore, multiple buildings need to cooperate to amplify the benefits from the collected data and speed up the model building processes. Apparently, this is not so trivial and there are associated challenges. In this paper, we study the importance of collaborative data analytics for smart buildings, its benefits, as well as presently possible models of carrying it out. Furthermore, we present a framework for collaborative fault detection and diagnosis as a case of collaborative data analytics for smart buildings. We also provide a preliminary analysis of the energy efficiency benefit of such collaborative framework for smart buildings. The result shows that significant energy savings can be achieved for smart buildings using collaborative data analytics.

KW - Collaborative data analytics

KW - Energy efficiency

KW - Fault detection and diagnosis

KW - Models

KW - Smart buildings

U2 - 10.1007/s10586-017-1362-x

DO - 10.1007/s10586-017-1362-x

M3 - Journal article

VL - 22

SP - 1065

EP - 1077

JO - Cluster Computing: The Journal of Networks, Software Tools and Applications

JF - Cluster Computing: The Journal of Networks, Software Tools and Applications

SN - 1386-7857

IS - Supplement. 1

ER -