Heat demand forecast

Energy supply networks are subject to strong fluctuations on the consumer side (for various reasons). In district heating networks, these are mainly caused by weather influences such as wind, sun and temperature, but also by social influences. These include, for example, different behavior on different days of the week or changing capacity utilization in tourism businesses.

In order to ensure the stable supply of such grids, it is crucial to react correctly to load fluctuations and to decouple the energy producers from them in the best possible way.

A virtual look into the future is very helpful and effective here.

It is precisely for this look into the future, namely for our heat demand forecast, that we use AI-based technologies that expand and enrich the state of the art in the field of higher-level control technology.

Using machine and deep learning methods, we create data-driven models from the operating data of your system. The models are fed with live data from the system and the model results are fed back to the higher-level control system.

In order to maintain the balance between performance and robustness in the age of AI   , a classic control concept is active in parallel to the AI model, which always retains control over the system status and only uses model results for system control in a clearly defined operating range.

The heat demand forecast thus enables a forward-looking operation of the generation system in the truest sense of the word, while at the same time ensuring a reliable supply to the consumers in the heating network.