Controls and Control Theory Commons^™

Power System Dynamic Control And Performance Improvement Based On Reinforcement Learning, Wei Gao

Electronic Theses and Dissertations

This dissertation investigates the feasibility and effectiveness of using Reinforcement Learning (RL) techniques for power system dynamic control, particularly voltage and frequency control. The conventional control strategies used in power systems are complex and time-consuming due to the complicated high-order nonlinearities of the system. RL, which is a type of neural network-based technique, has shown promise in solving these complex problems by fitting any nonlinear system with the proper network structure.

The proposed RL algorithm, called Guided Surrogate Gradient-based Evolution Strategy (GSES) determines the weights of the policy (which generates the action for our control reference signal) without back-propagation process …

Nonlinear Control And Observation Of Full-Variable Speed Wind Turbine Systems., Nicholas Hawkins

Electronic Theses and Dissertations

With increasing concern for the environmental effects of power generation from fossil fuels, wind energy is a competitive source for electrical power with higher efficiency than other clean sources. However, the nature of this power source makes controlling wind turbines difficult. The variability of wind as a source either requires highly accurate measurement equipment or sophisticated mathematical alternatives. In addition to the unknown quantities of the weather itself, the efficiency of power capture at the turbine blades is highly nonlinear in nature and difficult to ascertain. The ability of either determine these troublesome quantities, or control the system despite ignorance …