Data-Driven Baseline Estimation of Residential Buildings for Demand Response
The advent of advanced metering infrastructure (AMI) generates a large volume of data related with energy service. This paper exploits data mining approach for customer baseline load (CBL) estimation in demand response (DR) management. CBL plays a significant role in measurement and verification pro...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2015-09-01
|
Series: | Energies |
Subjects: | |
Online Access: | http://www.mdpi.com/1996-1073/8/9/10239 |
_version_ | 1811186096128655360 |
---|---|
author | Saehong Park Seunghyoung Ryu Yohwan Choi Jihyo Kim Hongseok Kim |
author_facet | Saehong Park Seunghyoung Ryu Yohwan Choi Jihyo Kim Hongseok Kim |
author_sort | Saehong Park |
collection | DOAJ |
description | The advent of advanced metering infrastructure (AMI) generates a large volume of data related with energy service. This paper exploits data mining approach for customer baseline load (CBL) estimation in demand response (DR) management. CBL plays a significant role in measurement and verification process, which quantifies the amount of demand reduction and authenticates the performance. The proposed data-driven baseline modeling is based on the unsupervised learning technique. Specifically we leverage both the self organizing map (SOM) and K-means clustering for accurate estimation. This two-level approach efficiently reduces the large data set into representative weight vectors in SOM, and then these weight vectors are clustered by K-means clustering to find the load pattern that would be similar to the potential load pattern of the DR event day. To verify the proposed method, we conduct nationwide scale experiments where three major cities’ residential consumption is monitored by smart meters. Our evaluation compares the proposed solution with the various types of day matching techniques, showing that our approach outperforms the existing methods by up to a 68.5% lower error rate. |
first_indexed | 2024-04-11T13:39:55Z |
format | Article |
id | doaj.art-839da1dd8b564d459d900623456af816 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-04-11T13:39:55Z |
publishDate | 2015-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-839da1dd8b564d459d900623456af8162022-12-22T04:21:18ZengMDPI AGEnergies1996-10732015-09-0189102391025910.3390/en80910239en80910239Data-Driven Baseline Estimation of Residential Buildings for Demand ResponseSaehong Park0Seunghyoung Ryu1Yohwan Choi2Jihyo Kim3Hongseok Kim4Department of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, KoreaDepartment of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, KoreaDepartment of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, KoreaOmni System Co., Ltd., 172, Gwangnaru-ro, Seongdong-gu, Seoul 133-822, KoreaDepartment of Electronic Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 121-742, KoreaThe advent of advanced metering infrastructure (AMI) generates a large volume of data related with energy service. This paper exploits data mining approach for customer baseline load (CBL) estimation in demand response (DR) management. CBL plays a significant role in measurement and verification process, which quantifies the amount of demand reduction and authenticates the performance. The proposed data-driven baseline modeling is based on the unsupervised learning technique. Specifically we leverage both the self organizing map (SOM) and K-means clustering for accurate estimation. This two-level approach efficiently reduces the large data set into representative weight vectors in SOM, and then these weight vectors are clustered by K-means clustering to find the load pattern that would be similar to the potential load pattern of the DR event day. To verify the proposed method, we conduct nationwide scale experiments where three major cities’ residential consumption is monitored by smart meters. Our evaluation compares the proposed solution with the various types of day matching techniques, showing that our approach outperforms the existing methods by up to a 68.5% lower error rate.http://www.mdpi.com/1996-1073/8/9/10239demand response (DR) managementanalytics for energy datadata miningresidential buildingssmart meterscustomer baseline load |
spellingShingle | Saehong Park Seunghyoung Ryu Yohwan Choi Jihyo Kim Hongseok Kim Data-Driven Baseline Estimation of Residential Buildings for Demand Response Energies demand response (DR) management analytics for energy data data mining residential buildings smart meters customer baseline load |
title | Data-Driven Baseline Estimation of Residential Buildings for Demand Response |
title_full | Data-Driven Baseline Estimation of Residential Buildings for Demand Response |
title_fullStr | Data-Driven Baseline Estimation of Residential Buildings for Demand Response |
title_full_unstemmed | Data-Driven Baseline Estimation of Residential Buildings for Demand Response |
title_short | Data-Driven Baseline Estimation of Residential Buildings for Demand Response |
title_sort | data driven baseline estimation of residential buildings for demand response |
topic | demand response (DR) management analytics for energy data data mining residential buildings smart meters customer baseline load |
url | http://www.mdpi.com/1996-1073/8/9/10239 |
work_keys_str_mv | AT saehongpark datadrivenbaselineestimationofresidentialbuildingsfordemandresponse AT seunghyoungryu datadrivenbaselineestimationofresidentialbuildingsfordemandresponse AT yohwanchoi datadrivenbaselineestimationofresidentialbuildingsfordemandresponse AT jihyokim datadrivenbaselineestimationofresidentialbuildingsfordemandresponse AT hongseokkim datadrivenbaselineestimationofresidentialbuildingsfordemandresponse |