.png){kind=icon}
.png){kind=icon}
Return
Conditional Generative Adversarial Networks for Dynamic Control-Parameter Selection in Power Systems
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3141804.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper describes the novel application of conditional Generative Adversarial Networks (cGANs) for real-time stability region determination (SRD) in power systems. As the network configuration changes during the course of operation, the availability of the stability region would enable the operator to suitably tune the control parameters to maintain stability while maximizing the dynamic performance. Here, the implementation of the cGANs-based SRD is described using transmission and microgrid case studies, where it is demonstrated to adaptively estimate the stability region for different network configurations with high accuracy. It is also shown that the cGANs approach has a significantly shorter execution time as compared to the conventional model-based method, demonstrating its value for real-time use in practical power systems.
Keywords:
Power system stability
Training
Generators
Numerical stability
Real-time systems
Power system dynamics
Circuit stability
Control parameter tuning
distributed generation
generative adversarial networks (GANs)
model-free approach
real-time control
small-signal stability
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W