The role of artificial intelligence (AI) is becoming increasingly important in following through with the energy transition and establishing an efficient and climate-neutral energy supply. The energy systems will become even more diverse in the future therefore we will need more intelligent control systems. They will be required to network the various renewable sources of power like wind energy, photovoltaics, hydropower or combined heat and power fuel cells with the various energy consumption sectors, such as electricity, building heat, process heat and electromobility. This will also include the generation of green hydrogen through electrolysis.
With the production of energy fluctuating in a supply system based on renewable sources, precise predictions of electricity generation and electricity consumption are increasingly important when it comes to keeping the energy system in balance. This is the background context in which the ZSW has been developing innovative processes and methods in AI and machine learning (ML) for many years. They are used in collaboration with industrial partners or are offered as services in support of the energy transition.
Artificial intelligence is also important in the energy-efficient and resource-efficient organisation of industrial manufacturing processes. The use of AI can be of assistance, not only in modelling and optimising processes but also in facilitating quality control and minimising wastage in production processes.
Artificial intelligence (AI) is being used more and more frequently in the energy turnaround sector. Self-learning methods help to better predict wind and solar power feed-in or to optimize production processes for photovoltaic modules, batteries and fuel cells. However, small and medium-sized enterprises in particular still use AI technologies too rarely. For many years, the ZSW has been developing innovative processes and methods of AI or machine learning (ML) within the scope of research and development projects in the field of renewable energies.
In April 2020, the ZSW launched the "Regional AI Lab for Renewable Energies" project, which is funded by the state of Baden-Württemberg. The aim of the AI Lab is primarily to support small and medium-sized companies in BW in order to offer new products and services using artificial intelligence and thus gain a competitive advantage. If you are interested in consulting on how you can make more out of your data with machine learning, please contact us. The consulting and first application of machine learning methods with your data are free of charge within the AI Lab. We are looking forward to your questions and your contact.
The percentage of fluctuating energy sources in our power supply is growing at a steady pace. Precise chronological forecasts of power feed-in are thus playing an increasingly important role. Wind, photovoltaics and hydroelectric power feed-in forecasts are already essential parameters in the management of transfer and distribution grids.
ZSW researches application-oriented technologies that raise the accuracy of forecasts of the complex interaction between weather model forecasts, satellite data and meteorological measurements and the historic and future wind, solar and hydroelectric power yields of a specific site or region.
The latest algorithms for machine learning methods play an important role in this context. They are capable of significantly improving physically calculated wind, solar irradiation and output forecasts by employing long-term measurement series that help them learn the interaction patterns between the numerous parameters that cannot be covered by physical models and apply the results to the respective current weather situation. Systematic deviations that generally occur in physical models are automatically corrected.
The Simulation & Optimisation (SimOpt) working group at ZSW has many years of experience in meteorology, processing of satellite data and wind power forecasting. The working group has successfully coordinated and implemented numerous international and national projects in recent years.
As a result of the WinReNN project subsidised by the German Federal Ministry for the Environment (BMUB), ZSW has been running an operational wind power forecasting system in conjunction with the EWC company in Karlsruhe for over three years. ZSW has also developed a PV performance prognosis system that is currently being prepared in conjunction with EWC for operational use. A great deal of the wind and PV generation forecasting work performed by the SimOpt group has benefited from the group’s substantial experience with machine learning methodology and the efficient use of extremely high-performance processor architectures based on parallel connected graphic processors.
The PV yield calculations for known or predictively calculated irradiation levels benefit from many years of yield measurements carried out on various PV module technologies at the ZSW solar testing grounds in Widderstall. This includes evaluations of direct and diffuse irradiation and spectral analyses over a period of many years, which allow yield calculations to be performed for various PV generator orientations.
