19.07.2024
A project led by the Fraunhofer IEE has developed a protection system against cyberattacks for virtual power plants using machine learning.
The protection system is "innovative", according to a press release from the Fraunhofer Institute for Energy Economics and Energy System Technology (IEE). It is designed to protect virtual power plants with decentralized energy systems from outages in an "automated" manner. The project, which has received 2.7 million euros in funding from the Federal Ministry for Economic Affairs and Energy, is called "SecDER". The consortium partners have titled the research proposal "AI-based detection and resilient prevention of cyber attacks and technical faults in virtual power plants and decentralized energy systems".
Fraunhofer IEE and its partners have developed a system that only uses general data and communication channels that each plant shares with its virtual power plant instead of using data from a specific network and systems of a specific plant. Such an approach is not yet to be found in standard market systems. It is therefore not necessary to know the energy systems and their measured variables in detail. The solution is therefore independent of proprietary plant technology and therefore manufacturer-independent, it continues.
Virtual power plants in particular, with their sometimes extensive and networked pool of plants, offer a large target for cyber attacks. "Cyberattacks on energy systems cannot be completely avoided," says Tobias Schellien. It must be assumed that attacks in this area will continue to increase in the future. "That's why we have taught the systems in the Secder project to react to cyber attacks and disruptions in such a way that total failures are avoided," says the project manager from Fraunhofer IEE.
Protection system to be further developed with the energy industry
As a first step, the researchers investigated the security of virtual power plants and simulated cyber attacks in the model. They discovered that even successful attacks on individual plants are not always noticed by the operators, as conventional monitoring systems do not necessarily react to individual failures. The intrusion detection system was developed against this background. It automatically detects cyberattacks and any technical faults immediately and with the help of AI, and fends them off. The entire system is put into a "suitable cybersafe position", the researchers write. Insecure control measures are no longer possible in this state. The system reacts to various dangerous situations, such as physical attacks or DoS attacks. The acronym stands for Denial of Service and refers to attacks that aim to bombard servers with requests so that they collapse. Accordingly, there is not just one single cybersafe position, but many. The system's response is "dynamic and precise", so that virtual power plants can continue to generate energy despite ongoing attacks and disruptions.
The Secder project started in April 2021 and has now been completed. At the moment, the protection system is still a prototype. However, the researchers want to develop it further with the energy industry. "Given the complex and advanced threats affecting the energy sector and virtual power plants, advanced solutions are needed. The solutions created in the Secder project have been developed precisely for these challenges and ensure that the systems remain functional even during an attack," says George Gkoktsis, scientist at the Fraunhofer Institute for Secure Information Technologies (SIT).
In addition to the two Fraunhofer Institutes IEE and SIT, Hanover University of Applied Sciences and Arts, Decoit GmbH, Enertrag AG and ANE GmbH & Co KG were also involved in the project.
Author: Fritz Wilhelm
Source: Energy & Management Powernews