Abstract
The deployment of advanced metring infrastructures allows suppliers and consumers to better understand the utility supply and usage chain. Data from these systems are typically used to analyse utility usage in a large scale, but when observed at smaller scales, we can enable a number of interesting new application. In this work we use utility usage data collected from 300 households over three years and perform detailed analysis to understand per-household utility usage patterns.We showthat per-household utility usage data introduces high variances and lowcorrelations among different households even if they are co-located in similar geographical regions. Using our findings, we introduce AUUP, an adaptive utility usage prediction scheme that combines the output from different (existing) forecasting schemes to adaptively make smart small-scale utility usage predictions. Our evaluations show that AUUP effectively reduces the prediction errors of artificial neural networks, LMS and Kalman filter-based AR model prediction schemes.
| Original language | English |
|---|---|
| Pages (from-to) | 264-277 |
| Number of pages | 14 |
| Journal | International Journal of Sensor Networks |
| Volume | 20 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 2016 Jan 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Computer Science Applications
- Computer Networks and Communications
- Electrical and Electronic Engineering
Cite this
}
Projecting household-scale utility usage : A case study using a long-term dataset. / Park, Jongjun; Kim, Hyunhak; Heo, Taewook; Yoo, Seung Mok; Ko, Jeong Gil.
In: International Journal of Sensor Networks, Vol. 20, No. 4, 01.01.2016, p. 264-277.Research output: Contribution to journal › Article
TY - JOUR
T1 - Projecting household-scale utility usage
T2 - A case study using a long-term dataset
AU - Park, Jongjun
AU - Kim, Hyunhak
AU - Heo, Taewook
AU - Yoo, Seung Mok
AU - Ko, Jeong Gil
PY - 2016/1/1
Y1 - 2016/1/1
N2 - The deployment of advanced metring infrastructures allows suppliers and consumers to better understand the utility supply and usage chain. Data from these systems are typically used to analyse utility usage in a large scale, but when observed at smaller scales, we can enable a number of interesting new application. In this work we use utility usage data collected from 300 households over three years and perform detailed analysis to understand per-household utility usage patterns.We showthat per-household utility usage data introduces high variances and lowcorrelations among different households even if they are co-located in similar geographical regions. Using our findings, we introduce AUUP, an adaptive utility usage prediction scheme that combines the output from different (existing) forecasting schemes to adaptively make smart small-scale utility usage predictions. Our evaluations show that AUUP effectively reduces the prediction errors of artificial neural networks, LMS and Kalman filter-based AR model prediction schemes.
AB - The deployment of advanced metring infrastructures allows suppliers and consumers to better understand the utility supply and usage chain. Data from these systems are typically used to analyse utility usage in a large scale, but when observed at smaller scales, we can enable a number of interesting new application. In this work we use utility usage data collected from 300 households over three years and perform detailed analysis to understand per-household utility usage patterns.We showthat per-household utility usage data introduces high variances and lowcorrelations among different households even if they are co-located in similar geographical regions. Using our findings, we introduce AUUP, an adaptive utility usage prediction scheme that combines the output from different (existing) forecasting schemes to adaptively make smart small-scale utility usage predictions. Our evaluations show that AUUP effectively reduces the prediction errors of artificial neural networks, LMS and Kalman filter-based AR model prediction schemes.
UR - http://www.scopus.com/inward/record.url?scp=84971420457&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84971420457&partnerID=8YFLogxK
U2 - 10.1504/IJSNET.2016.076703
DO - 10.1504/IJSNET.2016.076703
M3 - Article
AN - SCOPUS:84971420457
VL - 20
SP - 264
EP - 277
JO - International Journal of Sensor Networks
JF - International Journal of Sensor Networks
SN - 1748-1279
IS - 4
ER -