Over the last two decades, water smart metering programs have been launched in a number of medium to large cities worldwide to nearly continuously monitor water consumption at the single household level. The availability of data at such very high spatial and temporal resolution advanced the ability in characterizing, modeling, and, ultimately, designing user-oriented residential water demand management strategies (WDMS).

However, the effectiveness of these WDMS is often context-specific and strongly depends on our understanding of the drivers inducing people to consume or save water. Models that quantitatively describe how water demand is influenced and varies in relation to exogenous uncontrolled drivers (e.g., seasonality, climatic condi- tions) and demand management actions (e.g., water restrictions, pricing schemes, education campaigns) are essential to explore water users’ response to alternative WDMS, ultimately supporting strategic planning and policy design.

Traditionally, water demand models focus on different temporal and spatial scales. At the lowest resolution, studies have been carried out, mostly in the 1990s, to model water demand at the urban or block group scale, using low time resolution (i.e., above daily) consumption data retrieved through billing databases or experimental measurement campaigns on a quarterly or monthly basis. The main goal of these works is to inform regional water systems planning and management on the basis of estimated relationships between water consumption patterns and socio-economic or climatic drivers. The advent of smart meters in the late 1990s made available new water consumption data at very high spatial (household) and temporal (from several minutes up to few seconds) resolution, enabling the application of data analytics tools to develop accurate characterizations of end-use water consumption profiles. The use of smart meters provides essential information to construct models of the individual consumers behaviors, which can be employed for designing and evaluating consumer-tailored WDMS that can more effectively modify the users’ attitude favoring water saving behaviors. In particular, smart meters themselves constitute technologies that promote behavioral changes and water saving attitudes via tailored feedbacks.

A general procedure to study residential water demand management relying on the high-resolution data nowadays available can be structured in the following four phases: (i) data gathering, (ii) water end-uses characterization, (iii) user modeling, (iv) design and implementation of personalized WDMS. This work is part of the SmartH2O project, which aims at creating an ICT platform to raise customers’ awareness about their consumption and pursue water savings in the residential sector. Results will be deployed in three challenging use cases, in selected districts of London (UK), Valencia (S),  and Locarno (CH), potentially reaching millions of users.