Please use this identifier to cite or link to this item: https://doi.org/10.1016/j.enbuild.2022.112096
Title: ALDI plus plus : Automatic and parameter-less discord and outlier detection for building energy load profiles
Authors: Quintana, Matias
Stoeckmann, Till
Park, June Young
Turowski, Marian
Hagenmeyer, Veit
Miller, Clayton 
Keywords: Science & Technology
Technology
Construction & Building Technology
Energy & Fuels
Engineering, Civil
Engineering
Smart meter
Load profile
Matrix profile
Discord detection
Portfolio analysis
ANOMALY DETECTION
RANDOM FOREST
CONSUMPTION
VERIFICATION
PREDICTION
FRAMEWORK
MACHINE
Issue Date: 15-Jun-2022
Publisher: ELSEVIER SCIENCE SA
Citation: Quintana, Matias, Stoeckmann, Till, Park, June Young, Turowski, Marian, Hagenmeyer, Veit, Miller, Clayton (2022-06-15). ALDI plus plus : Automatic and parameter-less discord and outlier detection for building energy load profiles. ENERGY AND BUILDINGS 265 : 10.1016/j.enbuild.2022.112096. ScholarBank@NUS Repository. https://doi.org/10.1016/j.enbuild.2022.112096
Abstract: Data-driven building energy prediction is an integral part of the process for measurement and verification, building benchmarking, and building-to-grid interaction. The ASHRAE Great Energy Predictor III (GEPIII) machine learning competition used an extensive meter data set to crowdsource the most accurate machine learning workflow for whole building energy prediction. A significant component of the winning solutions was the pre-processing phase to remove anomalous training data. Contemporary pre-processing methods focus on filtering statistical threshold values or deep learning methods requiring training data and multiple hyper-parameters. A recent method named ALDI (Automated Load profile Discord Identification) managed to identify these discords using matrix profile, but the technique still requires user-defined parameters. We develop ALDI++, a method based on the previous work that bypasses user-defined parameters and takes advantage of discord similarity. We evaluate ALDI++ against a statistical threshold, variational auto-encoder, and the original ALDI as baselines in classifying discords and energy forecasting scenarios. Our results demonstrate that while the classification performance improvement over the original method is marginal, ALDI++ helps achieve the best forecasting error improving 6% over the winning's team approach with six times less computation time.
Source Title: ENERGY AND BUILDINGS
URI: https://scholarbank.nus.edu.sg/handle/10635/229403
ISSN: 03787788
18726178
DOI: 10.1016/j.enbuild.2022.112096
Appears in Collections:Staff Publications
Elements

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
1-s2.0-S0378778822002675-main.pdfPublished version1.17 MBAdobe PDF

CLOSED

None

Page view(s)

29
checked on Oct 6, 2022

Download(s)

3
checked on Oct 6, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.