eVader: UK Case study - Yorkshire Water

Yorkshire Water has been using the eVader algorithm to help reduce leakage and supply interruptions across their network, in response to their ambitious AMP7 regulatory targets, and as part of their IEN project. Since January 2021, eVader raised alarms for 93 supply interruption events, with a potential to save 84.6 seconds from customer minutes lost. This corresponds to a potential ODI penalty reduction of between £209,000 and £2.09M. 300 l/s of leakage was saved across a 12-week period, with bursts ranging from 5 l/s to 27 l/s. The result is a valuable and useful tool for the control room, automatically sending alerts, without inundating the team with notifications.

Background:

Yorkshire Water provides water and waste-water services to more than five million customers in the North of England. They produce over 1 billion litres of high-quality drinking water every day and deliver this through over 30,000 km of distribution network.

Challenges:

Continuously providing this service with minimal interruption is a challenge that Yorkshire has historically performed well in. However, they recognised that in order to continue to meet challenging targets over the next 5 years more needed to be done.

Until recently, confirmation of bursts sometimes only occurred after customers notified Yorkshire about them. It was understood that there were also bursts that could go unnoticed for quite some time. Yorkshire Water wanted a solution that would help to identify visible and invisible bursts earlier so that they could resolve them more quickly – minimising water lost from the network and the effect on customers.

Project overview:

Yorkshire Water have embarked on a large-scale “intervention enabled networks” (IEN) project, and as part of this project, event detection algorithms were evaluated. eVader has been part of this project since 2018, and in 2021, was extended to operate on the whole network. Currently, data is ingested from more than 3,000 loggers every 5 minutes and prepared for analysis.

As new data is received, the eVader algorithm runs and checks if it is normal or not, and categories any abnormalities that are identified. It also updates its model of what ‘normal’ is. Between the hours of 10pm and 6am, the time period selected by Yorkshire Water, they receive emails of Events Detected from the iNet system as soon as they are identified. The email includes information about the location of the issue as well as the size of the anomaly, the percentage change from normal, and the categorisation.

This data is used by the control room, the leakage team and by analysts to enable quick operational decisions to be made before customers make contact.

Outcomes:

Since January 2021, eVader raised alarms for 93 supply interruption events, with a potential to save 84.6 seconds from customer minutes lost (CML). In 2021/22, 65.16 seconds could be linked to alarms.

The potential CML savings corresponds to a potential reduction in ODI penalty of between £209,000 and £2.09M, depending on the speed of eVader’s response.

Yorkshire Water saved more than 300 l/s of leakage over a single 12-week period with Event Detection, with bursts ranging from 5 l/s to 27 l/s.

We send an average of 6.5 notifications per night to Yorkshire Water. This is an average of 2,373 per year, across 2,628 DMAs. This is less than one notification per DMA per year.

Feedback:

"A large proportion of leaks are now identified by Event Detection; currently, a number of different systems are used but eVader gives the potential to reduce duplication."

“It is a valuable and useful tool for the control room.”

“eVader is a useful tool which is smart, gives more information and automatically updates. All of the other engineers would agree.”

“From a leakage perspective, it’s great. We usually have at least one a night that we will deal with. It works.”

Click here to see our infographic!

Yorkshire Water – Implementing real-time network event detection to detect potential supply interruptions

A successful real-world trial of our groundbreaking eVader software

Ofwat – Developing scenarios for long-term reductions in household water use

Demonstrating that 50 litres per head per day is a feasible goal in the long-term

eVader: UK Case study - Yorkshire Water

Outcomes and benefits of using our event detection algorithm in Yorkshire Water