Eliminating faults in the electricity grid long before they can occur: this is made possible by the use of artificial intelligence based on a technology developed in its present form by E.ON. It is now being used by Schleswig-Holstein Netz AG, a German grid operator belonging to the E.ON group. Combining comprehensive data analysis with a self-learning algorithm now makes it possible to predict faults and failures in the electricity grid much more reliably than before, and to take appropriate action much earlier.
E.ON has been using this method in Schleswig-Holstein Netz AG's medium-voltage grids for around nine months. And the results are astonishing: "The probability that we can predict a defect in the power grid has increased by a factor of two to three," explains Thomas König, responsible for E.ON’s German grid business. "And our customers benefit as well because possible sources of error that we identify in advance reduce the number of faults and make our grid more stable."
The new forecasting approach, also known as predictive maintenance, uses a variety of internal and external data such as the age and type of the power lines, maintenance and weather data as well as real-time information such as the current load behavior. The resulting forecasts open up completely new possibilities for the maintenance of the network infrastructure.
By identifying potential sources of failure, the number of faults and failures can be reduced because the sources of a defect can be eliminated before the predicted failure occurs. For this reason, around a dozen maintenance projects in Schleswig-Holstein Netz AG's grids were brought forward in recent months.
The new technology also improves planning for grid construction projects, which benefits municipalities in particular. For citizens and communities, improved maintenance means a reduction in construction activities and earthworks for repair purposes. For the company itself, it offers the prospect of allocating budgets and planning investments much better in advance.
In recent years, E.ON has continuously improved the security of supply in its networks. At Schleswig-Holstein Netz AG, for example, the average downtime in 2016 was just 8.85 minutes, around a third lower than the nation-wide average of 12.8 minutes.