EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantum deep reinforcement learning-augmented pelican optimization for robust UPQC control in wind-grid integrated DFIG systems

P. V. S. S. A. Parimala, Narendra Babu P

AIP Advances · 01.09.2025 · 15 (9)

DOI: 10.1063/5.0287494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AIP Advances, online erschienen am 24.09.2025. Verfasst von P. V. S. S. A. Parimala und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes an enhanced Pelican Optimization with Quantum Process Deep Reinforcement Learning algorithm (POQPDRL) control framework for the synergized control of a grid-connected DFIG-based wind energy system integrated with a Unified Power Quality Conditioner (UPQC) to enhance voltage stability and power quality. The performance of the UPQC is optimized to improve power quality and enhance the system’s dynamic response. The shunt converter compensates for reactive power and mitigates harmonics, while the series converter mitigates voltage sags or swells by implementing POQPDRL, a bio-inspired algorithm influenced by the hunting behavior of pelicans. The proposed system is modeled and simulated in MATLAB/Simulink, where grid disturbances, faults, and variations in wind speed are introduced to validate the effectiveness of the control strategy. Simulation results indicate a considerable improvement in system stability, a reduction in harmonics, and effective reactive power compensation. The system achieves a significantly reduced load voltage total harmonic distortion (THD) of 0.70% and a load current THD of 0.63%, which are well within IEEE 519 standards. In addition, the system exhibits improved voltage stability, reactive power compensation, and faster convergence compared to Pelican optimization (POA), Particle swarm optimization (PSO), Genetic Algorithm (GA), and Wind Driven Optimization (WDO).

Zitieren

APA

Parimala, P. V. S. S. A., & P, N. B. (2025). Quantum deep reinforcement learning-augmented pelican optimization for robust UPQC control in wind-grid integrated DFIG systems. AIP Advances, 15(9). https://doi.org/10.1063/5.0287494

Vancouver

Parimala PVSSA, P NB. Quantum deep reinforcement learning-augmented pelican optimization for robust UPQC control in wind-grid integrated DFIG systems. AIP Advances. 2025;15(9). doi:10.1063/5.0287494

BibTeX
@article{Parimala2025,
  author = {Parimala, P. V. S. S. A. and P, Narendra Babu},
  title = {Quantum deep reinforcement learning-augmented pelican optimization for robust UPQC control in wind-grid integrated DFIG systems},
  journal = {AIP Advances},
  year = {2025},
  volume = {15},
  number = {9},
  doi = {10.1063/5.0287494}
}
Kostenlos starten →