Projecting household-scale utility usage: a case study using a long-term dataset Online publication date: Mon, 23-May-2016
by Jongjun Park; Hyunhak Kim; Taewook Heo; Seung-Mok Yoo; JeongGil Ko
International Journal of Sensor Networks (IJSNET), Vol. 20, No. 4, 2016
Abstract: The deployment of advanced metering 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 show that per-household utility usage data introduces high variances and low correlations 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.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Sensor Networks (IJSNET):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com