Quantifying stagnation time through non-intrusive residential end-use disaggregation

Water quality in residential buildings can potentially deteriorate after water enters building premise plumbing, potentially introducing public health concerns. Stagnation time, among other considerations, is an important factor in determining water quality in premise plumbing. Residential premise plumbing often contains several dead-end pipes leading to different fixtures and appliances, often composed of different materials that affect water quality. Household water consumption habits, including conservation and efficiency, also affect stagnation time within water systems. However, water flow is usually only monitored at the main inlet and little is known about how stagnation time varies among different end-uses since monitoring every water fixture can be both costly and intrusive. Smart water metering systems can provide fine temporal resolution whole-home data that can be used to identify specific residential water end uses via disaggregation and non-intrusive machine learning techniques. This whole-home smart water metering approach can classify distinct end uses within a category (e.g., distinguishing showers in different locations) and evaluate the duration between two consumption events from a distinct end-use and thus, enable quantification of stagnation time for different classified water end uses across residential housing configurations. We develop a method to link fine-resolution smart water metering system data to stagnation time based on demonstration in a monitored study home. Our study advances current water stagnation time monitoring that often neglects the temporal stagnation variations among different household end-uses in premise plumbing, revealing areas of future work to integrate water quantity and water quality.