)
Fortum is a Nordic energy company operating in areas where district heating is in high demand during the cold winters. Fortum worked with Vaisala Xweather to implement hyperlocal forecasting for its district heating network in Helsinki and its surrounding cities.
Challenge
There are significant variations in local weather conditions across Fortum’s large district heating network. Large differences in topography, vegetation, and the built environment, make accurate forecasting challenging.
Solution
Vaisala Xweather delivered a hyperlocal forecasting solution using a machine-learning model trained on real-time observations from a managed network of 26 weather sensors installed at key locations across Fortum’s network.
Results
Xweather Optimize improved the accuracy of Fortum's 6-hour forecast by up to 36% and reduced the number of errors greater than 2.5 °C in the 24-hour forecast by 59%.
"Our observation network of Vaisala weather stations provides us with accurate local data of critical weather parameters, enabling us to optimize heating supply temperature more precisely than before."