Case study

Using data from electricity meters to predict energy consumption

Learn how a research institution used clustering to optimise heating and energy consumption.

This guidance is part of a wider collection about using artificial intelligence (AI) in the public sector.

AI technique used

  • clustering

Objective

A research institution needed to understand which electric appliances were being used in a house at a certain time to optimise heating and energy consumption.

Situation

The research institution did not know when particular electric appliances were being used. This meant they were unable to optimise heating and energy consumption resulting in higher prices and energy waste.

Action

The research institution used non-intrusive load monitoring to gather unlabelled data from electricity meters to see which appliances were being used and when.

They used unsupervised machine learning techniques to convert the unlabelled data into patterns. From this, the research institution could cluster the different types of appliances based on their power consumption patterns.

Impact

The model:

  • was able to predict future energy needs of a property
  • could help plan when households might use appliances
  • enabled smart use of heating - for example turning off heating while the occupier is out and turned on when they are coming home

Updates to this page

Published 10 June 2019