Professor Alan Smeaton of DCU standing against a wall with framed photos and diplomas

Switching energy provider? Prof Alan Smeaton has a tool for you

Submitted on Friday, 02/02/2024

Looking to switch energy provider? Prof Alan Smeaton of Insight at DCU has the tool for you. He writes:

If you are like me, then you may spend (or waste?) time creating a spreadsheet when it comes to renewing your energy provider. You might spend hours entering estimates of your usage data and checking what this would cost with all the energy suppliers in order to get the cheapest rate for the next year. Or maybe you use one of the traditional comparison platforms such as or or even the CER. The problem with those platforms is they use standard consumption models based on the ‘average consumer,’ which don’t capture the diverse energy profiles of individual households.

Who is that ‘average consumer’ anyway? It is not you or me because we are all different. Data based on averages will not give a satisfactory answer for either of us.

This has been a problem, until now. Now you can really optimise your domestic electricity costs with our electricity tariff analysis tool.

Our methodology uses data from your smart meter if you have one, which records your electricity usage in 30-minute intervals. Your usage data is available to you to download via ESB Networks. Our algorithm which is part of a research project at the Insight SFI Research Centre for Data Analytics at Dublin City University, processes your high-resolution consumption data, alongside variables related to your dwelling (e.g., type and size of home, heating systems, number of occupants) and lifestyle patterns (e.g., cooking, heating preferences). This gives a personalised data-driven analysis allowing a more accurate comparison of current energy tariffs and a bespoke recommendation of which tariff, tailored to your unique energy profile, is cheapest for you, right now.

The forthcoming Version 2 of our tool enhances this model by incorporating comparative usage patterns from households similar to yours, similar number of occupants, similar size, type of home, etc. This feature allows us to adjust our predictive model to account for unusual consumption scenarios, like reduced usage while you were traveling or on vacation, or increased usage during colder periods or you are at home due to illness when you had the heating on or if you had guests staying with you. These refinements in our predictive analytics promise even more precise tariff recommendations.

For detailed information and to access our service, visit

Thank you for considering our data-driven approach and helping you to select the best electricity tariff for you.