Evaluating the Benefits of Smart Stormwater Systems

There is significant promise for the use of smart, distributed stormwater storage for addressing a range of challenges associated with integrated urban water management, including

  • Flood control via peak flow reductions and/or reduced infrastructure costs
  • Water for urban greening and cooling
  • Improving the quality of receiving waters.

This study assessed the benefits and costs of a range of stormwater storage options, including smart operation, for urban stormwater systems The benefits assessed include peak overland flow reduction, water re-use potential and water quality impacts. Results were compared with more traditionally used pipe upgrades. The case study catchment was located in the City of Unley, Adelaide, South Australia.

The key conclusions were:

  • Passive distributed storages optimised using machine learning achieves similar peak flow reduction as end-of-system storage with reduced storage size and cost and is easier to implement.
    Cost savings were 30%-44% compared to an equivalent pipe upgrade
  • Smart distributed storage with ‘before storm control’ achieves a similar peak flow reduction at similar cost as pipe upgrade with additional water reuse and water quality benefits
    Cost and peak flow reductions were similar to an equivalent pipe upgrade of approx. 550m to 700m length with the additional benefits of potential water reuse volume of 3.1 ML/year and water quality benefits with reduced total suspended solids (51%), phosphorus (27%) and nitrogen (9%).
  • Smart distributed storages with ‘during storm’ real-time control provide significant potential for additional peak flow reductions or cost savings through storage size reductions.
    Further development is required for this technology to be used in practice.
  • Machine learning / artificial intelligence optimisation methods played an essential role for identifying the optimal location, sizing and operating rules for the distributed storage options.
    Due to the high number of potential locations, sizes and operating rules a traditional trial and error design approach would be far slower and unlikely to achieve a similar outcome.