VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!
 

Reinforcement Learning for the Cybersecurity of Grid-Forming and Grid-Following Inverters

dc.contributor.authorKwiatkowski, Brian Michaelen
dc.contributor.committeechairMehrizi-Sani, Alien
dc.contributor.committeememberCenteno, Virgilio A.en
dc.contributor.committeememberLiu, Chen-Chingen
dc.contributor.departmentElectrical Engineeringen
dc.date.accessioned2024-12-07T09:00:29Zen
dc.date.available2024-12-07T09:00:29Zen
dc.date.issued2024-12-06en
dc.description.abstractThe U.S. movement toward clean energy generation has increased the number of installed inverter-based resources (IBR) in the grid, introducing new challenges in IBR control and cybersecurity. IBRs receive their set point through the communication link, which may expose them to cyber threats. Previous work has developed various techniques to detect and mitigate cyberattacks on IBRs, developing schemes for new inverters being installed in the grid. This work focuses on developing model-free control techniques for already installed IBR in the grid without the need to access IBR internal control parameters. The proposed method is tested for both the grid-forming and grid-following inverter control. Separate detection and mitigation algorithms are used to enhance the accuracy of the proposed method. The proposed method is tested using the modified CIGRE 14-bus North American grid with 7 IBRs in PSCAD/EMTDC. Finally, the performance of the detection algorithm is tested under grid normal transients, such as set point change, load change, and short-circuit fault, to make sure the proposed detection method does not provide false positives.en
dc.description.abstractgeneralDue to the increasing presence of renewable energy resources such as photovoltaic and solar has introduced new challenges to the grid as the United States shifts towards clean energy. Those resources rely on devices called inverters to transform the energy to match the conditions of the grid. Inverters receive instructions to change their values before making the connection, making them potentially vulnerable to cyberattacks. While there has been progress in developing protection methods for inverters, existing inverters require additional protection to ensure their safe and reliable function. This work proposes a way to improve the reliability of existing inverters without changing the values of their internal settings. The method, tested under several conditions, successfully detects and counters potential cyberattacks without mistaking normal grid operations such as adjustments in demand and short circuit events.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:42081en
dc.identifier.urihttps://hdl.handle.net/10919/123754en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectCyberattacken
dc.subjectinverter-based resources (IBR)en
dc.subjectpower system controlen
dc.subjectreinforcement learning (RL)en
dc.subjectrenewable energy sourcesen
dc.titleReinforcement Learning for the Cybersecurity of Grid-Forming and Grid-Following Invertersen
dc.typeThesisen
thesis.degree.disciplineElectrical Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 2 of 2
Name:
Kwiatkowski_BM_T_2024.pdf
Size:
3.77 MB
Format:
Adobe Portable Document Format
Name:
Kwiatkowski_BM_T_2024_support_1.pdf
Size:
88.28 KB
Format:
Adobe Portable Document Format
Description:
Supporting documents

Collections