Standard content for Members only

To continue reading this article, please login to your Utility Week account, Start 14 day trial or Become a member.

If your organisation already has a corporate membership and you haven’t activated it simply follow the register link below. Check here.

Become a member

Start 14 day trial

Login Register

WPD to track low-carbon technologies using AI

Western Power Distribution (WPD) is to use artificial intelligence and machine learning to virtually monitor electric vehicles and other low-carbon technologies on its low-voltage network as part of a new trial.

The Virtual Monitoring Data project will allow the company to locate and track emerging hot spots on its network, helping it to avoid or defer costly and disruptive reinforcements.

Information from Electralink’s Energy Market Data Hub will be analysed to create half-hourly load profiles for customers that will then be fed into a virtual monitoring tool developed through IBM’s artificial intelligence platform Watson Studio.

The scheme will build upon the work undertaken as part of WPD’s Low Carbon Technologies Detection project, which was completed earlier this year and used similar techniques to identify 15,000 previously unknown electric vehicles and solar panels connected to its network.

WPD innovation team manager Jonathan Berry, said, “The Low Carbon Technologies Detection project really showed us what can be done to gain a widescale view of exactly what is happening on our network.

“The Virtual Monitoring Data project takes this a step further – we will create robust and validated models which we can use to plan, forecast and reduce costs. This project will set the precedent for using data and machine learning to proactively improve, manage and operate electricity networks.”

Electralink chief executive Stuart Lacey said: “We are excited to be extending our partnership with WPD and IBM to work on this ground-breaking project.

“The Virtual Monitoring Data project is another example of how data is revolutionising the traditional distribution network model, in this case through linking digitised energy assets with customer level retail market data.”

The trial will be supported by funding from the Network Innovation Allowance.