Cranfield University research using data from smart meters has found that household water consumption changed significantly after the start of the COVID-19 lockdown, shifting from predominantly higher usage early in the morning to multiple peaks and continued demand throughout the day.
The study used machine learning algorithms to analyse and identify patterns in hourly water consumption data from 11,528 households in the East of England from January to May 2020.
The research is the first of its kind in the UK to quantify network consumption and segment households into different behavioural clusters according to significant differences in usage patterns.
Key findings were that:
Halidu Abu-Bakar, PhD researcher in the Cranfield Centre for Competitive Creative Design, Cranfield University, said: "The COVID-19 lockdown has instigated significant changes in household behaviour across a variety of categories including water consumption, which in the south and east regions of England is at an all-time high. The impact of the extended time people stayed at home under the lockdown and the ensuing changes in behaviour arising from this led to an increase in household water demand, exacerbating existing pressure on network water supply.
"Having knowledge of these patterns provides a solid framework for peak demand management and can help utility companies to forecast consumption, especially at unusual times such as pandemics, droughts and when there are seasonal variations."
Professor Leon Williams, Head of the Cranfield Centre for Competitive Creative Design, said: "Quality data driven research will provide the intelligence needed for water utilities to make strategic decisions."
Professor Stephen Hallett, Centre for Environmental and Agricultural Informatics, Cranfield University, said: "Water utility companies are increasingly searching for ways to understand the full nature of household water use, how to improve network demand forecasting and achieve effective water efficiency interventions. This data-driven characterisation of household clusters and understanding the impact of these unique patterns of behaviour on network demand can help in the design of demand forecasting and intervention that targets households on the basis of their shared cluster characteristics."
###
The research used anonymised smart meter data and was supported by the UK Engineering and Physical Sciences Research Council (EPSRC).
npj Clean Water