| Download | - View accepted manuscript: Energy performance based anomaly detection in non-residential buildings using symbolic aggregate approximation (PDF, 604 KiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1109/COASE.2018.8560433 |
|---|
| Author | Search for: Ashouri, Araz1; Search for: Hu, Yitian1; Search for: Newsham, Guy R.1; Search for: Shen, Weiming1 |
|---|
| Affiliation | - National Research Council of Canada. Construction
|
|---|
| Format | Text, Article |
|---|
| Conference | 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE), 20-24 August 2018, Munich, Germany |
|---|
| Subject | fault detection and diagnosis; building energy management; energy auditing; data analysis; electricity demand |
|---|
| Abstract | Building system faults in commercial and office buildings can result in a reduced occupant comfort and increased utility bills. Energy performance-based anomaly detection helps operators efficiently identify faults. In this work, a data-driven method for anomaly detection is presented. Using a symbolic aggregate method, the weekly energy demand profiles are statistically quantised and labeled to determine normal and abnormal building behaviours. A case study with three federal office buildings has been conducted to demonstrate the proposed method. The resulting technology provides building operators with easily-interpreted and actionable information for optimised building performance. |
|---|
| Publication date | 2018-12-06 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| NRC number | NRCC-CONST-56261E |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 4a2c0581-f009-4692-a91c-c6c91a1f71d9 |
|---|
| Record created | 2019-04-11 |
|---|
| Record modified | 2020-06-03 |
|---|
