Zentur.io creates AI-based schedules for producers in local & district heating networks. This will allow more renewable energy sources to be integrated and fossil fuels to be used more efficiently. This saves CO2, costs and increases the share of renewable energy in the heat supply. Through our Cloud SaaS solution, you can easily obtain our service in your own dashboard or optionally link it to your existing IT systems via API.
In which sector do you think we Germans consume the most energy? Is it electricity, transport or heat? In fact, we consume over 52% of energy in the heating sector. At the same time, only 14% is generated from renewable energy sources. In order to successfully implement the energy transition, the heat supply in particular must therefore become much greener!
This is what is expected from local, district heating and neighborhood solutions, which will cover almost 40% of the heat supply by 2050. The biggest challenge here is the smart integration of generally weather-dependent renewable energy sources while simultaneously optimizing fossil generation plants. That’s why we founded Zentur.io.
We make heating networks smart with our AI solution. We process data from generators, consumers, and weather forecasts in machine learning models to optimize the schedules of fossil generation plants in particular, and to better schedule weather-dependent renewables. This allows us to achieve a lower return temperature, which means that heat from renewable sources, e.g. solar thermal, can be fed in at a lower heat output even when the sun is shaded. The predicted amount of heat from renewables is then used as the basis for creating schedules for fossil fuel heat generators (oil, gas, etc.) that need to burn less fuel or avoid unnecessary burning through our schedules. This saves fuel, costs and CO2 emissions.
An initial estimate from a pilot customer puts the savings at 10-15%. The inclusion of consumer profiles (households & industry) rounds off the concept. This allows us to validate and simulate network planning to provide important results, for example, for the expansion or new planning of heating networks. We make these results available via a SaaS model. Our Machine Learning Pipeline is built in the AWS Cloud and ready to go as an MVP.
As a result of the law on the digitization of the energy transition, utilities must not only digitize heating networks with smart meters. Also, the FFVAV regulation that was just recently published (October 2021) forces heating utilities to read meters remotely. This is expected to lead to a better understanding of the customer (consumer) side in particular. According to customer interviews, there is still a blind spot in the management of heating networks 4.0.