SmartB4P | Smart battery control for production

Energy flexibility in production using battery storage

Rising electricity prices in Germany are putting pressure on the international competitiveness of German industry. In addition to labor prices, the costs for peak loads are particularly high. At the same time, the construction of own generation facilities such as photovoltaic systems offers companies the opportunity to generate green electricity themselves with significant cost advantages, although the generation capacity is highly dependent on the weather. In this context, the use of battery storage systems can increase own consumption and avoid costly load peaks. In the production environment, these batteries must be controlled as optimally as possible depending on external conditions such as the weather and fluctuating energy requirements in order to achieve maximum benefit.

Smart battery control

The present research project is concerned with the investigation of a novel operating strategy of battery storage systems for use in manufacturing companies, which predictively controls charging and discharging depending on the situation and taking into account battery ageing and dynamically changing conditions such as weather or production capacity utilization. The system is designed to increase the electricity consumption at production sites with company-owned renewable electricity generation plants and to prevent costly load peaks, thus reducing electricity costs in the long term. In order to derive the best possible operating strategy in spite of the numerous stochastic influencing factors, methods of artificial intelligence and machine learning, in particular reinforcement learning, are used. In addition, production consumers that can be temporarily switched off are to be integrated into the operating strategy of the battery in order to operate an optimal load management.

SmartB4P

In the first step, a well-founded requirements analysis and conceptual design is carried out in cooperation with all partners involved, from storage technology and PV forecasting to the integration of production IT. Based on this, the information technology networking of all relevant components and systems can be carried out and a production and consumption forecast based on statistical models and machine learning can be developed. In order to be able to consider the cycle-dependent ageing of battery storage systems in the operating strategy, the energy storage system is modelled in detail. In order to increase the load shift potential, production-inherent storages are also identified and mapped. For the development of the actual operation strategy, methods of artificial intelligence, especially reinforcement learning, are used. In this way, adaptive and reactive control is to be achieved, which will finally be prototypically implemented and validated by a project partner.

Cooperation with Fraunhofer IGCV

Contact us for an individual solution that suits your business needs.

Industry solutions

The key sectors of Fraunhofer IGCV:

  • Mechanical and plant engineering
  • Aerospace
  • Automotive and commercial vehicles

Competences

We are shaping the way into the future of efficient engineering, networked production and intelligent multi-material solutions.