A emissions-tracking tool, developed in Britain, is using machine learning to work out if the next 96 hours of electricity has been sustainably produced - offering a big boost to both energy-consumer transparency and the transition to renewables.
In the summer of 2019, Great Britain became the first G7 country to set itself the goal of reducing net greenhouse gas emissions to zero by 2050. That would effectively make the country completely climate neutral. An ambitious, but by no means utopian plan. In what was once the former homeland of coal power, renewables are now the largest source of electricity in the country. Coal currently makes up only around two percent of Britain's electricity mix.
But Britain is still a long way from enjoying 100% green electricity. And the share of renewable energies within their total electricity generation is prone to massive fluctuation. Even the most conscious consumer can't tell whether it's electricity from renewable sources or from fossil fuels that is currently coming out of the socket.
Energy forecasts for improved transparency
But now there's an app that can tell you exactly that. Together with Oxford University, the Environmental Defense Fund Europe and the WWF, the electricity transmission network National Grid has developed an app called the "Carbon Intensity Forecast", a sort of "weather report" for clean electricity.
The "carbon intensity" of electricity is a measurement of how many CO2 emissions are produced per kilowatt hour of energy. The more electricity produced by renewable energies such as solar or wind power, the lower the emissions are. National Grid assessments are calculated using information from all kinds of different power plants, meaning that their software can work out how much of Britain's electricty is made up of renewable and non-renewable energy sources. This then results in a prediction of the CO2 emissions.
The carbon intensity of the electricity we use is changing by tiny amounts all the time, depending on the type of electricity being generated and the demand for power. Based on data from these changes, this programme provides a prediction of the CO2 intensity for the next 96 hours, which is updated every 30 minutes. The software works with regression models based on machine learning. This allows consumers to see when the electricity is going to be produced most sustainably, and adjust their energy consumption accordingly. "The forecast was developed to both raise awareness and enable consumers to postpone using energy use for periods low carbon intensity - thus reducing carbon emissions," Dr. Alasdair Bruce, lead scientist behind the project, told RESET.
Freely available and with huge potential
The underlying software system is also made available to other developers as a so-called “Open API”. "There are now many companies that use the Carbon Intensity API," reports Bruce. "Some car manufacturers plan to embed the forecast in electric vehicles so that owners can charge their cars during the 'greenest' periods."
Other apps could also be developed on this same basis. It would also make sense to integrate it into existing smart home systems, ones designed to charge electrical devices at times when there is a high proportion of green electricity in the mix. Developers could potentially use it in countless different applications to enable consumers and/or smart devices to optimise their energy consumption behaviour to reduce carbon emissions. Automatically applying information about electricity's carbon-intensity in this way could play a key role in driving forward the energy transition in the future.
And the carbon intensity forecast won't only be limited to Great Britain in the future. Alasdair Bruce assured RESET that the impact of the app was set to spread and grow: “We have a lot of plans. Working together with European partners, in the future the whole of Europe will be covered by a carbon intensity forecast.”This is a translation of an original article that first appeared on RESET's German-language site.
The RESET Special Feature on AI is part of a project funded by the Deutschen Bundesstiftung Umwelt (German Federal Environmental Foundation DBU). As part of this project, over a period of two years we will be developing four RESET Special Features on the topic of "Opportunities and Potentials of Digitalisation for Sustainable Development".
Find more information here.