Spotlights illuminate paths towards intelligent energy systems


Probabilistic grid condition forecasting: Simplified decision-making

Is there any capacity left? This question frequently arises in the power grid when more solar and wind power plants want to feed energy into the grid in good weather conditions. Grid operators need reliable forecasts to be able to correctly assess the situation in the grid. The assumptions regarding grid utilization have so [...]


Intelligent partial discharge evaluation of generator insulators using machine learning methods (SmartPD)

Recognizing partial discharge patterns in electrical machines: The service life of electrical machines substantially depends on the condition of the insulation. This insulation is assessed manually based on partial discharge measurements. These measurements show the current PD behavior. The trained eye can recognize PD patterns and infer the causes of PD. Statements on the [...]


Temporal Fusion Transformers – Improved wind power forecasting

The wind blows where it pleases. This is also experienced by wind farm operators. To accurately estimate the generation capacity of the plants, relying on local power measurement values and parameters from weather models is not sufficient. AI could improve these predictions, providing accurate forecasts for the next eight hours. The aim of the [...]


Alsland – Detecting microgrids using artificial intelligence

Microgrids in the interconnected grid represent a real challenge, because the entire interconnected grid works as a single unit. However, grid faults can cause individual sections to be cut off. If there is additionally a local power balance, unintentional microgrids can develop. To prevent personal injury and plant damage, unintentional microgrids need to be [...]


CTRL – Development chain for intelligent plant control

Can reinforcement learning revolutionize control technology? The Cognitive Train/Test System for Reinforcement Learning using Labs (CTRL) project sets up an infrastructure for independent control in the distribution grid. The project offers an infrastructure for training control concepts for distributed plants. Agents are prepared for their areas of application from simulated pretraining and realistic hardware-in-the-loop [...]


KESL2RPN – Power grid manages challenges independently

Self-driving vacuum cleaners no longer surprise anyone. However, an autonomous power grid is not yet a given. Automated operation was simulated as part of the international competition “L2RPN Challenge” (“Learn to Run a Power Network”). On the initiative of French transmission grid operator RTE, a self-learning agent took over the operation of a nationwide [...]


InvEx – Expert tool for developing converters

Converters are becoming more and more important in energy supply. In terms of profitability and eco-friendliness, increasing the efficiency and service life of these systems while reducing the investment costs is the top priority. The development of new converters for various applications takes 1-3 years on average and requires many years of experience and [...]


AI OPF – The grid as a complex arithmetical problem

From the stakeholder to the system: Grid operators need complex calculation models to accommodate a great number of power producers and flexible consumers. Current mathematical models for grid optimization, which ensure a stable and cost-efficient power grid, are increasingly reaching their limits. The AI OPF project investigates whether the AI-based method of deep reinforcement [...]


Cognition2H2Force – Efficient hydrogen production

Hydrogen is a highly versatile element and is considered to be the missing link in the energy transition. However, its production requires large amounts of energy. For this reason, excess power from solar and wind power plants is intended to be used predominantly for electrolysis. To this end, power-to-gas plants for producing hydrogen are [...]


HeatCast – Reducing CO2 emissions through efficient forecasts

The German industry has to reduce its CO2 emissions – a fact virtually everyone agrees on. But how? The factories of Bosch are also facing this question. They have already reduced their CO2 emissions, but want to reduce them even more. A key element in reducing CO2 emissions is the optimized use of power, [...]


GRAF-CoWi – Combination of wind power forecasts

One of the major challenges in forecasting the power generated by almost fully weather-dependent renewable energy sources such as wind and PV is the inaccuracy of the employed weather forecasts (numerical weather predictions – NWPs). These forecasts – especially the forecast horizon of 0-4 h – are essential for the energy market. Uncertainties and [...]



The TLP4Heat project is aimed at developing a digitization workflow that allows for utilizing maintenance information in district heating systems to develop optimal maintenance strategies. To ensure efficient operation of the district heating network, the maintenance activities at the district heating transfer stations can be optimized by using predictive maintenance strategies. A necessary prerequisite [...]


PDET – Incorporating the results of automated energy trading into science

Energy trading on the continuous intraday electricity market is a highly complex process that differs significantly from other markets due to the transience and volatility of the traded products. As part of the PDET project, a first trading agent was developed on the basis of deep reinforcement learning that operates on the energy market [...]


AAE – Adversarial attacks in the energy sector

The project involved investigating the robustness of an AI-based wind power forecasting model against intentional but imperceptible changes in input data aimed at falsifying the output data. The use of AI-based methods in critical infrastructures such as the energy sector can lead to potential security issues. For instance, adversarial attacks are a major threat. [...]


GRADS – Generating artificial district heating supply systems

Due to the limited number of district heating supply systems in Germany and their individuality, their data are difficult to use for research purposes and unpublishable. The sensitive data reveals the affiliation to specific providers, posing a risk of abuse. Artificial intelligence, specifically deep reinforcement learning (DRL), is used for research purposes to create [...]



Testing machine learning algorithms for intelligent distributed charging management at company locations. What is the problem? Avoiding load peaks to reduce load peaks and power price costs and meeting the requirements of the grid operator. Current technologies are limited in particular in terms of costs, flexibility, and complexity management. What problems emerge? Simultaneous charging [...]



Forecasting power flows in the electrical grid using graph neural networks: Forecasting of power flows in the electrical grid enables grid operators to make advance grid calculations to recognize bottlenecks in good time and take countermeasures. Machine learning approaches using local forecasting models are not capable of considering dependencies between individual system components (such [...]


Vertical load forecasting: Going with the flow

The bottom line must be zero – this applies to power input and consumption at all times. To establish this equilibrium, power grid operators calculate load flows in advance for the next few hours. In this process, the load at the transition points between different electrical grids represents a particular challenge. An innovative approach [...]


ARCANA – Wind turbines monitor themselves

Errors can happen – but it is important to recognize them. This also applies to the operation of wind power plants. Major damage and failures can be disastrous for the operators of such plants. The anomalies detected by monitoring systems often only indicate that a potential error is present or may occur. In the [...]


Deep Energy Trade – Automated electricity trading for all

Trading in energy has so far been a domain for pros. This could change with the help of machines. Other stakeholders might then also become more interested in the electricity exchange. In the Deep Energy Trade project, a demonstrator shows how intelligent automated electricity trading can work. The self-learning agent is capable of developing [...]

“Artificial intelligence is a key technology for the ongoing development of the energy turnaround.”

Angela Dorn, Hessian Minster of Higher Education, Research and the Arts

“Artificial intelligence is a central element of tomorrow’s economy – and an important element for the sustainable transformation of our energy system.”

Kerstin Andreae, Managing Director of the German Association of Energy and Water Industries (BDEW)