Smart-Meter Enabled Estimation and Prediction of Outdoor
Residential Water Consumption.
MMath thesis, University of Waterloo, School of Computer Science, 2018.
Smart meter technology allows frequent measurements of water consumption at a household level. This greater availability of data allows improved analysis of patterns of residential water consumption, which is important for demand management and targeting conservation efforts. The dataset in this thesis includes 8,000 single family residences in Abbotsford, British Columbia from 2012--2013, and contains hourly measurements of water consumption recorded by smart meters installed in 2010. This work focuses on identifying outdoor consumption due to its contribution to peak demand during the summer, which is important because of concerns about strain on infrastructure in Abbotsford. This research shows that outdoor water consumption can be robustly identified from hourly measurement of total water consumption by determining an upper threshold on plausible indoor usage, and that this estimated outdoor water consumption is consistent with seasonal patterns of water consumption identified in previous work, with the timing of restrictions on outdoor watering, and with household size. The research also includes regression tree-based models for predicting next-hour water consumption, however the predictability of this consumption is limited. In contrast to previous work, there is little correlation between outdoor consumption and demographic factors such as income. Outdoor consumption shows a large amount of individual variability, with 8.6% of households accounting for 50% of the total outdoor usage. This limits the predictability of outdoor consumption, but also highlights the importance of identifying this consumption for each household to allow for targeted conservation efforts.