Title: Projecting household-scale utility usage: a case study using a long-term dataset

Authors: Jongjun Park; Hyunhak Kim; Taewook Heo; Seung-Mok Yoo; JeongGil Ko

Addresses: IoT Convergence Research Department, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, Korea ' IoT Convergence Research Department, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, Korea ' IoT Convergence Research Department, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, Korea ' IoT Convergence Research Department, Electronics and Telecommunications Research Institute, 218 Gajeong-ro, Yuseong-gu, Daejeon, Korea ' Department of Software Convergence Technology, Ajou University, 206 Worldcup-Ro, Yeongtong-Gu, Suwon, Gyeonggi-Do 16499, South Korea

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.

Keywords: household utility management; adaptive utility usage prediction; case study; advanced metering; artificial neural networks; ANNs; normalised LMS; NLMS; least mean squares; Kalman filter; smart grid; sensor networks; electricity consumption; water consumption; gas consumption.

DOI: 10.1504/IJSNET.2016.076703

International Journal of Sensor Networks, 2016 Vol.20 No.4, pp.264 - 277

Received: 14 Jul 2013
Accepted: 01 Feb 2014

Published online: 23 May 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article