AI4Grids

  • Konstanz, Germany
  • September 2020
  • HTWG-Konstanz
The aim of the project is to efficiently integrate the generators and consumers required for the energy transition into the medium- and low-voltage grid by means of intelligent grid management. In this way, a better synchronization of energy quantities and grid capacities is to be achieved. To achieve this, algorithms based on artificial intelligence (AI) are being developed to support the planning and operational management of power grids at the distribution grid level and of microgrids ("island grids"). As an example, in the event of a fault, an algorithm recommends a course of action to the control room in order to quickly rectify the problem.
  • Open source
  • 18/82/- (% m/f/d)
  • Public

Project stage (in ):

Beta/Testing

Implemented by:

Inhouse

Industrial Sectors:

Electricity, gas, steam and air conditioning supply, Information and communication

Usage of AI:

Data Management and Analysis, Information Retrieval, Generative Models, Probabilistic Forecasting, Anomaly Detection

Generation of AI:

Traditional Machine Learning (Linear Regression, CART, SVM, etc.), Deep Learning (CNN, Transformers, etc.)

Model training:

Supervised Learning

Contact

Responsible Person

Prof. Dr. Gunnar Schubert

Motivation and values

What in your view defines the public interest and how does your project meet this purpose?

To slow climate change, we need a shift away from fossil energy sources. However, the necessary expansion of renewable energies and the switch to electric cars pose challenges for the power grid: Solar and wind energy feed in power very irregularly, while energy demand is rising, especially in cities. Nevertheless, new flexible consumers, such as electric charging stations and heat pumps, can become the solution for the energy transition in interaction with the fluctuating renewable generators – through intelligent grid control.

How did the idea of your project come about?

Internal in our organization

What is the goal of your project in relation to the public interest?

Development of AI-based algorithms to accelerate the planing and enable intelligent control of energy-grids with high penetration of renewable energies, electric mobility and heat pumps, to complete the energy transition on the path toward a climate neutral society.

Design & Safeguards

Which stakeholders were involved in the process of development and implementation of the project?

Developer, External domain expert, Academic researcher, Industry partners

How did you engage relevant stakeholders?

Oversight board

Have the project results been validated by third parties?

No

Have the design and the results of the project been made transparent to the public?

Yes

In what way have the design and the results of the project been made transparent to the public?

By academic researchers, By the open-source community

Involving the people who will be affected by the project is a necessary part of the project design

3

How did you verify the accuracy and robustness of your system?

- real-time power HIL tests - test and demonstration in real environment

What technical and organizational safeguards have you implemented to protect personal data and mitigate possible harms? Choose all that apply

Data minimization (incl. not gathering personal data), Authentication and access management, User control (consent, update, retract), Maintaining an up to date privacy policy

Do you take measures in regards to ecological sustainability of your project? Please elaborate.

Evaluation of energy efficiencies of developed algorithms

Is your project directly or indirectly contributing to solutions for the climate crisis or other UN sustainability goals?

Directly

Does your project rely partly or fully on the use of open data and/or publish results in an open data set? Please elaborate.

yes