Increasing control and efficiency in regional energy systems using quantum sensors and machine learning

A major challenge connected to the integration of renewable energy sources into power grids is to control the energy distribution on a local system level taking into consideration individual power sources. The identification of anomalies and the implementation of countermeasures to increase control and flexibility in power systems requires a precise current measurement within the connected devices and the local power system.
Novel quantum sensors based on NV-centers in diamond can be used to measure magnetic fields, currents and temperature effectively. These sensors work in harsh environments and are most suitable to be used in medium-voltage applications (up to 30 kV). This will provide vital information about the performance of a medium voltage transmission line unavailable so far by conventional current sensing schemes.  
At the same time it would be possible to use the sensors on a microscopic scale to measure current within power semiconductors in power converters for grid connected batteries, PV and wind power plants. The sensor nodes in PV systems will be complemented by weather sensors.
The data obtained by this novel de-centralized sensors will be analysed by machine learning techniques. The machine-learning based identification of patterns in power grids and weather conditions increases the flexibility of the power system by an improved prediction of energy demand and production as well as storage capacity at the city district level.