FAME4ME

Foresight and AI-based, user-centred management of energy services

Challenge and innovation

The FAME4ME research project is responding to the challenge posed by the changing use of energy applications (e.g. controlling heat pumps, charging electric cars) and the variable availability of energy sources (e.g. wind, solar) in the building sector. Intelligent energy management in residential and building environments can help to increase the use of renewable energies through controlled energy consumption while also providing flexibility potential for the system.

Therefore, FAME4ME aims to use artificial intelligence to test and improve energy services for private users. It combines smart meters, energy management and time-variable electricity tariffs. As part of the project, user behaviour is investigated in relation to flexible electricity consumption and the adaptation of time-variable electricity tariffs. This way the benefits and the effectiveness of the respective tariffs from the user's perspective are to be improved. In addition, a user-friendly app is being developed: It is supposed to provide a visualisation of generation and consumption forecasts as well as price signals for electricity use and individualised recommendations for action. The aim is to increase energy efficiency and develop a sustainable energy supply.

The connection of the platform to the SmartLivingNEXT ecosystem, especially to the Dataspace, allows access to relevant contextual data such as incentive signals or market information. Combining data from different data sources is an important innovation compared to previous solutions. Data on supply and demand of electricity can be used to develop customised energy services using AI processing.

Application and benefits

Real applications (use cases) are analysed by different user groups in workshops with pilot customers, pilot studies, and through other specific examinations of the project. Surveys and analyses of user behaviour with certain tariffs are intended to enable conclusions to be drawn on how to improve customer benefits. At the same time, interoperability with the various platforms is to be tested and expanded through the complete technical implementation by the users. The continuously generated data will also contribute to the further development of the AI methods used.

Project partners

Universität Würzburg, EnBW Energie Baden-Württemberg AG (Countrol GmbH i.G im Unterauftrag)

Consortium leader

Fraunhofer-Gesellschaft – Institut für Solare Energiesysteme ISE