Hybrid quantum-classical model achieves 100% detection and 99.56% identification accuracy for power quality disturbances, indicating potential for smart grid applications.
Key Points
Results indicate a 100% detection accuracy in identifying power quality disturbances.
The model uses a hierarchical framework with quantum convolutional layers to extract multiscale features.
Robust noise resistance maintains approximately 98% identification accuracy across various noise scenarios.
Experiments conducted on datasets adhering to IEEE Std 1159–2019 demonstrate high efficiency and scalability.