DASH of Water

Marie Skłodowska-Curie Fellowship - LEaDing Fellows PostDoc Programme¹

Across the globe, water utilities face exceptional challenges due to ageing water infrastructure, population growth, financial and regulatory pressures, and climate change while new resources are ill-equipped to meet rising water demands. Thus, water companies are forced to operate their systems in a more efficient way; e.g. through leakage reduction, energy use minimization, better asset lifecycle management, water quality improvements, etc.

A growing number of utilities use hydraulic models to improve the performance of their water distribution systems. However, flow and pressure sensors in these systems had only existed at larger distribution pipes and measurements are sparse even today —resulting in computer models that are not sufficiently good for optimizing operations.

A relevant recent development is ubiquitous customer side smart metering and associated big data analytics. An innovative new way of combining hydraulic models and data from smart meters—recently available devices measuring and transmitting water usage of households in real-time—can help to quantify and reduce model uncertainties and, hence, increase water system’s operational efficiency in a wide range of applications.

This project aims to develop beyond state-of-the-art methods to simulate water distribution systems in a more realistic and accurate way by utilising the potential of recently available smart meter technologies. First, data science algorithms will be developed and applied on real-world smart meter data to retrieve relevant information for hydraulic modelling and operational optimisation. By linking smart meter data, stochastic demand simulation software and hydraulic computer models—advanced DAta-driven Stochastic Hydraulic (DASH) models of drinking water systems will be developed. Finally, these novel models will be employed and tested on a wide range of real-world applications.

The research is based at the water management department of TU Delft and includes collaborations with Leiden University’s Institute of Advanced Computer Science (LIACS) on data science algorithms, KWR Water Cycle Research Institute on stochastic demand modelling, as well as a water utility (Oasen drinking water) for applying these novel DASH models on real-world water distribution systems.

1: “This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 707404. The opinions expressed in this document reflect only the author’s view. The European Commission is not responsible for any use that may be made of the information it contains.”