Artificial Intelligence for the Efficient Control of Solar Heating Systems
Abstract
Artificial Neural Networks (ANN) are the basis of a new intelligent control concept for residential heating systems developed at Fraunhofer ISE. This artificial intelligence based concept is able to predict thermal behavior of a building and load level of a thermal storage based on measured data without using any physical model based simulation tool. This allows to improve energy efficiency and simplicity of control devices at the same time. The focus of the concept is simplicity of application, thus enabling low cost model predictive control. Up to 12% gain of energy efficiency was calculated for a current 1950’s building in Southern Germany. This gain is reached without any interaction of installer or user. The ANN control approach proved to work in a real building, too.