Researchers protect solar technologies from cyberattacks
Newswise – New research from the University of Georgia suggests a new approach to protecting a possible target from a cyberattack – the nation’s solar farms. In a study published in IEEE Transactions on the Smart Grida team from UGA’s College of Engineering has demonstrated a sensor system that monitors a key electrical component in solar farms to detect signs of cyber intrusion in real time.
“A growing concern is that hackers could exploit the converters that connect solar farms to the power grid,” said WenZhan Song, Georgia Power Mickey A. Brown professor of engineering and lead researcher of the study. “In modern grid-connected solar farms, power electronics converters can be controlled remotely, but this Internet connection also increases the potential for cyberattacks.”
In general, power electronics uses semiconductor switching devices to control and convert the flow of electrical energy from one form to another. This technology has revolutionized modern life by streamlining manufacturing processes, increasing product efficiency and improving the delivery of reliable power by utilities.
In a solar farm, power electronic devices convert direct current (DC) electricity generated by photovoltaic solar panels into alternating current (AC) electricity for use on the power grid. The US Department of Energy estimates that up to 80% of electricity could flow through power electronics by 2030.
To protect against cyber threats, UGA researchers have developed a system capable of detecting anomalies in the operation of an electronic power converter in real time using a single voltage sensor and a single current sensor. Coupled with deep learning methods, the system can distinguish between normal conditions, open circuit faults, short circuit faults and cyberattacks.
“To our knowledge, this has never been attempted before,” Song said.
A small passive sensor connected to the power converter collects data on electrical waveforms and transmits the information to a computer screen. Even if an attack eludes the firewall or security software, the sensors will detect unusual activity in the electrical current of the power electronics device. The system may also run diagnostic tests to determine the type of problem that has occurred.
“At your house, the power meter usually takes a reading every 15 minutes,” Song said. “Our system takes 10,000 samples per second. »
Compared to existing detection methods that only detect abnormal waveforms, the UGA researchers say their system was found to be better at identifying cyberattacks in tests using a solar farm model. The researchers also claim that their system can identify new types of cyberattacks that have not been programmed into deep learning algorithms.
The researchers have filed a US patent application for their approach, noting that the sensor system could provide protection against cyberattacks for manufacturing systems, office buildings and even smart homes.
In addition to Song, the research team includes Jin Ye, assistant professor, Jinan Zhang and Stephen James Cosatt, both of whom hold Ph.D. students and Lulu Guo, a research professor at Tongji University in China, who served as a postdoctoral research associate at UGA.
The study is part of a larger project sponsored by the US Department of Energy that involves several universities and several national laboratories. The University of Arkansas is the lead academic institution in efforts to advance technologies that protect the solar array from cyberattacks. Ye is the principal investigator of the UGA part of the project.
Note to Editors: The following photos are available online
Cutting line: Wenzhan Song stands in front of a large solar panel. (Photo by Dorothy Kozlowski/UGA)
This press release is available online at