Machine Learning Approaches to Improving the Transient Stability of Voltage-Source Converters in Weak Grids

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
School of Electrical Engineering | Doctoral thesis (article-based) | Defence date: 2023-04-28
Degree programme
84 + app. 70
Aalto University publication series DOCTORAL THESES, 45/2023
With the proliferation of converter-interfaced generation in modern power systems, grid-forming converters are viewed as a solution to improve system stability and resilience in weak power grids. However, the dynamic behaviour of the grid-converter systems is strongly influenced by inevitable disturbances and transients in weak power grids (e.g. short circuit faults). Moreover, grid-converter systems are prone to harmonic instability due to the interactions between the converters and passive elements. These issues pose security risks and limit the further integration of renewable generation into the modern power system. Therefore, this thesis aims to improve the transient stability and harmonic stability of grid-converter systems by employing deep-learning and analytic methods for developing power synchronization control (PSC) in weak power grids. First, the internal structure of the synchronization loop in PSC is modified to reduce vulnerability to grid transients by utilizing a back-calculation scheme. Also, the damping characteristics of PSC are enhanced to mitigate the decaying DC offset current of the converter. Second, the internal reference calculation is developed by embedding a long short-term memory (LSTM) neural network into PSC. The LSTM neural network is trained to extract and predict the grid voltage trajectory based on the converter dynamics and grid strength. Thus, the control system updates the internal references dynamically to meet the low-voltage ride-through (LVRT) requirements and prevent synchronization loss. Third, by employing deep learning methods and neural networks, an encoder-stacked classifier is introduced for early detection of synchronization instability. This allows time for corrective control actions to be taken and prevents synchronization loss in the grid-converter system. The applied neural networks are trained to be robust against data corruption and added noise. Finally, the admittance characteristics of converters are studied and necessary conditions are outlined for achieving harmonic stability with PSC in weak grids. Moreover, a 12.5-kVA three-phase back-to-back converter system is implemented under weak grid conditions for the experimental evaluation of the results and future works.
Supervising professor
Pouresmaeil, Edris, Assoc. Prof., Aalto University, Department of Electrical Engineering and Automation, Finland
Thesis advisor
Routimo, Mikko, Prof., Aalto University, Finland
deep learning, grid faults, grid-forming converters, harmonic stability, machine learning, neural networks, power electronics, power synchronization control, transient stability, weak power grids
Other note
  • [Publication 1]: Amir Sepehr, Oriol Gomis-Bellmunt, Edris Pouresmaeil. Employing Machine Learning for Enhancing Transient Stability of Power Synchronization Control During Fault Conditions in Weak Grids. IEEE Transactions on Smart Grid, vol. 13, issue 3, pp. 2121-2131, May 2022.
    Full text in Acris/Aaltodoc:
    DOI: 10.1109/TSG.2022.3148590 View at publisher
  • [Publication 2]: Amir Sepehr, Mobina Pouresmaeil, Edris Pouresmaeil. Enhancing Transient Stability of Power Synchronization Control via Deep Learning. In 23rd European Conference on Power Electronics and Applications (EPE’21 ECCE Europe), Ghent, Belgium, pp. 1-10, September 2021.
    Full text in Acris/Aaltodoc:
    DOI: 10.23919/EPE21ECCEEurope50061.2021.9570417 View at publisher
  • [Publication 3]: Amir Sepehr, Mobina Pouresmaeil, Mojgan Hojabri, Frede Blaabjerg, Edris Pouresmaeil. Improving Transient Stability of Power Synchronization Control for Weak Grid Applications. In IEEE 21st Workshop on Control and Modeling for Power Electronics (COMPEL), Aalborg, Denmark, pp. 1-6, November 2020.
    DOI: 10.1109/COMPEL49091.2020.9265786 View at publisher
  • [Publication 4]: Amir Sepehr, Mobina Pouresmaeil, Edris Pouresmaeil. Harmonic Stability Analysis of Grid-Connected Converters with Power Synchronization Control. In IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe), Espoo, Finland, pp. 1-6, October 2021.
    Full text in Acris/Aaltodoc:
    DOI: 10.1109/ISGTEurope52324.2021.9640199 View at publisher
  • [Publication 5]: Mobina Pouresmaeil, Amir Sepehr, Reza Sangrody, Shamsodin Taheri, Edris Pouresmaeil. Control of Multilevel Converters for High Penetration of Renewable Energies. In IEEE 12th International Symposium on Power Electronics for Distributed Generation Systems (PEDG), Chicago, IL, USA, pp. 1-5, June-July 2021.
    Full text in Acris/Aaltodoc:
    DOI: 10.1109/PEDG51384.2021.9494249 View at publisher
  • [Publication 6]: Mobina Pouresmaeil, Meysam Saeedian, Amir Sepehr, Reza Sangrody, Edris Pouresmaeil. Fault-Ride-Through Capability of VSGBased Grid-Forming Converters. In 23rd European Conference on Power Electronics and Applications (EPE’21 ECCE Europe), Ghent, Belgium, pp. 1-7, September 2021.
    Full text in Acris/Aaltodoc:
    DOI: 10.23919/EPE21ECCEEurope50061.2021.9570556 View at publisher
  • [Publication 7]: Mobina Pouresmaeil, Amir Sepehr, Basit Ali khan, Jafar Adabi, Edris Pouresmaeil. Model predictive-based control technique for fault-idethrough capability of VSG-based grid-forming converter. In 24th European Conference on Power Electronics and Applications (EPE’22ECCE Europe), Hannover, Germany, pp. 1-6, September 2022
    Full text in Acris/Aaltodoc: