Project SHANGO

The aim of the SHANGO project is to help find solutions to reduce the energy consumption of heat generators in the private sector sustainably and in the long term. As part of this work, Fraunhofer IIS/EAS is responsible for the focal area of data science.

There is a decisive link between our society’s energy consumption and the high level of CO2 emissions that are driving climate change. Heating systems are particularly energy-intensive consumers – and incorrect operation, installation errors, and undiscovered wear lead to inefficient operation and therefore wasted energy, especially in the case of heat pumps. Although today’s systems already incorporate sensor technology and communication interfaces, these are only queried sporadically. Moreover, it is still very cost- and labor-intensive to carry out problem detection and diagnosis by acquiring operating data.

Project aim

Together with other project partners, Fraunhofer IIS/EAS has joined the Smart Heating System Optimization (SHANGO) project, which aims to help find solutions to reduce the energy consumption of heat generators in the private sector sustainably and in the long term. As part of this work, Fraunhofer IIS/EAS is responsible for the focal area of data science, while other project partners contribute expertise in relation to heating technology and energy management software.

The goal is to activate low-threshold efficiency potentials and improve the assessment of economic factors when it comes to the replacement and modification of systems.

In the future, the aim is for existing systems – with their existing sensor technology and control and communication hardware – to be monitored and optimized during operation with minimal installation and operating effort. Using artificial intelligence (AI) and machine learning, missing information will be added and datasets then generated that also incorporate additional data such as weather, building data, and the observed operating patterns. The project also includes the compilation of an error database that reproduces, generates, and analyzes typical operating patterns and is subsequently used to train an AI-based algorithm that provides the basis for operation in the field.

Specifically, the SHANGO project includes the following steps:

  • Compilation of an overview of the most relevant ineffiencies and operating errors by energy system
  • Creation of an error pattern library
  • Development of an expanded minimally invasive measurement concept in order to obtain a better data basis
  • Planning and setup of an IT platform as a training, development, and validation environment for the AI system
  • Development of algorithms for the detection of errors and efficiency potentials
  • Elaboration of a user concept, including recommendations for action

During the project, a laboratory measurement stand was set up at Fraunhofer IIS/EAS in order to carry out hardware-in-the-loop (HiL) simulations of heat generator operation within a virtual building environment. This environment is used to simulate specific system configurations, use and error cases, and precise framework conditions such as weather and usage data. The laboratory measurements provide a set of operating data that are suitable for training AI processes in order to detect problematic operating states.

Similarly, the load-shifting potential of heat pumps is to be investigated using a simulation-based evaluation. This is intended to clarify how successfully and in what circumstances existing small heat generators can be put to sensible use in the power grid within the framework of dynamic load management.

Our expertise for your project

You would like to become our project partner? Fraunhofer IIS/EAS has decades of experience in contract research for industrial companies. Submit your request and we will contact you to discuss the possibilities of a collaboration.

BMWK: Support + Bundestag
BMWK: Support + Bundestag

SHANGO is funded by the German Federal Ministry of Economic Affairs and Climate Action on the basis of a decision by the German Bundestag.