In the early evening hours, many electrical appliances are switched on at the same time, for example when showering, cooking or washing. This simultaneous activation of many electrical appliances creates enormous network loads. It is important to avoid these or at least to smooth them out.
Intelligent control of power consumption
In order to reach this, knowledge is needed over it, when current hungry devices, as for example heat pumps, must be supplied compellingly river and when this is not absolutely necessary.
With Nilm4Balance this can be found out, and beyond that where surplus energy can be stored locally by using already installed consumers (boilers, heat pumps, electric mobile, etc.) as short-term inexpensive storage tanks.
In order to smooth and reduce peak loads in this way, it is first necessary to determine where heat pumps are installed and where photovoltaics are generated - information that is only partially known to the electricity companies. The more difficult question, however, was: How much time is there to reduce and smooth the load peaks without the users feeling a loss of comfort?
To this end, the researchers are taking advantage of the increasing digitalization of power distribution networks with smart meters. Artificial intelligence comes into play to calculate a thermal model of the buildings under investigation from this data. The algorithms analyze smart meter data and identify individual power-consuming devices such as heat pumps, boilers or electric vehicles and power-producing devices such as photovoltaic systems from the total power consumption.
Added value without sacrificing comfort
The project results open up new possibilities for the project partners ASGAL Informatik GmbH and Semax AG: Thanks to the automatic identification of electricity consumers and the calculation of their so-called load shifting potential, they can offer electricity supply companies a service that helps them to save fees without having to make additional investments in their distribution networks.
