Trust the Raw Data? The Importance of Applying Data Integrity Intelligence to Building Energy Management Systems

As the smart building solution providers industry continues to mature, the benefits of deploying Building Energy Management Systems (BEMS) to achieve and sustain energy efficiencies goals within the real estate portfolio, becomes ever clearer. However as with any high volume data acquisition environment, BEMS are susceptible to a myriad of ongoing data integrity operational issues that beyond the obvious data outage reporting difficulties, can ultimately lead to a mistrust in the underlying data sets, and therefore a degradation in the value of any applied analytics that relies on the provisioning of accurate sensor or meter data. For example how does the smart building practitioner maintain confidence in a BEMS system accuracy and effectiveness, when there are unknown and undetected data outages, intermittent sensor or meter raw data reporting, or abnormal or corrupted sensor data events? Or how does the user become aware of a problem of sensor drift that may impact the BEMS reporting accuracy, and given the growing complexity of the sensor and metering environments, how does the user quickly fault diagnose the problem once it has been identified? These questions are critical to the notion of ongoing effective use of BEMS in an organisation, and so this paper attempts to address these known industry concerns, by setting out the background of the most important of these practical data integrity issues, by defining a data integrity validation methodology, and finally through a series of use cases, demonstrate how such an approach could effectively be applied, to build trust levels, by introducing detection and timely fault diagnosis in underlying BEMS raw data sources.

By: Niall Brady, Raymond Lloyd

Published in: RC25537 in 2015


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to .