idw – Informationsdienst Wissenschaft
Nachrichten, Termine, Experten
Nachrichten, Termine, Experten
idw - Informationsdienst
Wissenschaft
Professorship of Artificial Intelligence at the Chemnitz University of Technology is a project partner in BMBF-funded joint project for greater digital security in smart grids - contribution to greater social acceptance of AI solutions
The energy transition requires not only renewable energies on a grand scale but also intelligent power grids. The so-called "smart grids" ensure that energy is distributed according to demand and thus efficiently - for example, when numerous electric cars need electricity to charge overnight in one fell swoop. Digital technology plays an essential role in this. For this to function and be protected against attacks and disruptions, for example by hacking, malware, and viruses, sophisticated mechanisms are needed that can intervene immediately on an autonomous basis using artificial intelligence. This is precisely the goal of the joint project entitled “Knowledge-based anomaly detection using artificial intelligence in critical infrastructures” (German).
Brandenburg University of Technology Cottbus-Senftenberg (Prof. Dr. Andriy Panchenko) is in charge. The project partner is the Professorship of Artificial Intelligence (Prof. Dr. Fred Hamker) at the Chemnitz University of Technology, which is responsible for research and development in the field of recurrent neural networks.
The project is funded with 2.72 million euros by the German Federal Ministry of Education and Research (BMBF) over a period of three years. The project will run until August 2023.
Contributing to the social acceptance of AI solutions
"Smart grids" are intelligent power grids with which - to put it simply - power generation, consumption, and storage can be dynamically controlled. With this strong application reference to the safety of smart grids using AI, the project makes a valuable contribution to the social acceptance of AI solutions. Automatic detection of anomalies - more effective grid operation attacks generate deviations from the normal technical state of digital systems, which are often difficult to detect using standard IT security procedures today. Using a new AI-based method, these anomalies are to be detected automatically in the future. For this purpose, an analysis procedure is being developed in which several machine learning methods are combined in a novel way in order to exploit the respective advantages of the approaches.
In doing so, Prof. Hamker and Dr. Vitay are pursuing current approaches with recurrent neural networks to enable increased automation. In addition, the researchers are comparing these approaches with the classical ones used at the Brandenburg University of Technology Cottbus-Senftenberg in order to combine them, if necessary. In particular, the goal is to achieve effective machine learning based on less or incomplete training data.
Using neural networks, the innovative security solution developed in the project will be quickly applicable in other environments beyond the considered use case. One use case is networks of the so-called critical infrastructures (KRITIS sectors) such as power or water networks. Such use is already planned in the project.
Prof. Dr. Fred Hamker, Chair of the Professorship of Artificial Intelligence at the Chemnitz University of Technology, phone +49 (0)371 531-37875, e-mail fred.hamker@informatik.tu-chemnitz.de.
Die TU Chemnitz beteiligt sich an einem Forschungsprojekt zur Entwicklung einer KI für effektivere S ...
Pixabay/Pexels / Jacob Müller
TU Chemnitz
Criteria of this press release:
Journalists, Scientists and scholars
Information technology
transregional, national
Cooperation agreements, Research projects
English
You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).
