Decoding residential water use through high-resolution pressure sensing

Smart metering systems are one of the key components of  the digital transformation of the water sector and represent a significant advancement over traditional meters. However, it has been widely demonstrated that only data gathered at a sufficiently fine resolution (1 min or even better 1 sec) allows properly performing end-use disaggregation and classification while due to technical reasons, such as battery life, smart metered water consumption data are generally registered and collected by Water Utilities at daily or hourly time steps. As an alternative to approaches relying on data provided by smart meters, methods for end-use water consumption characterization based on pressure data have progressively gained attention, due to the technical and economic advantages associated with the installation of pressure sensors compared to flow meters.

This study presents an innovative method for estimating water consumption events based on pressure measurements at two distinct in-line sections of the domestic inlet pipe, from which the head-loss time series can be derived. As first phase, the method converts the head-loss time series into flowrate by exploiting the pressure-flowrate relationship, allowing the reconstruction of the water-consumption time series. As second phase, information about water consumption at the level of individual consumption events is obtained. The flowrate time series is firstly processed by an algorithm for signal stabilization and combined events segmentation. Consequently, all individual events are analysed based on their features (e.g. duration, volume, etc.) to provide further information on water uses.

To validate the methodology, a residential user consisting of a single-family house was considered and pressure monitoring at two sections of the inlet pipe was performed over a period of about one month and a half with 1-s resolution. In addition, daily volume supplied to the user over the same period was obtained through the mechanical flowmeter for method validation. The pressure signals were converted in head-loss time series by accounting for sensor-elevation difference estimated over a time window of nil flow in the inlet pipe. Head-loss time series was then converted in flowrate time series by exploiting the relation between head-loss and flowrate, for which the hydraulic resistance of the inlet-pipe segment was preliminarily assessed through field tests. The total water consumption estimated over the monitoring period deviated from the observed one (i.e. that obtained from water-meter readings) of about 2.3%, confirming the capability of the methodology of effectively providing flowrate time series starting from pressure data. Flowrate time series was then subject to filtering and segmentation, resulting in over 7,500 individual end-use events, 18% of which overlapped in time. The characteristics of the above events were then investigated in a duration-volume mesh. Overall, the methodology was proven to provide insights into end uses of water that can support water utilities in the characterization and modelling of residential water consumption by exclusively relying on pressure data.