Power and Energy 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 …

A Four-Port Bidirectional Dc-Dc Converter For Renewable Energy System And Microgrid, Xia Du

All Graduate Theses, Dissertations, and Other Capstone Projects

Renewable energy has nowadays become important in electrical power applications. Power converters play an important role in integrating these distributed energy sources. However, due to their intermittence characteristics, e.g., the output power provided by the PV and wind turbine is not stable, either an energy storage system will be used or microgrid is formed between the main grid and the sources. To integrate these renewable energy sources and manage the power flow, a multiport converter is preferred because it is highly beneficial and cost-efficiently than the traditional solution that using multiple individual power converter for each source. This thesis proposed …

A Novel Power Sharing Control Method For Distributed Generators In Dc Networks, Christina James

Electrical & Computer Engineering Theses & Dissertations

The power sharing control method is a desirable solution to integrate multiple renewable energy generators into the grid and to keep them working synchronously. Power sharing control between different distributed generators is an important consideration for the stabilized operation of the power grid network. In this thesis work, a novel method is used with the concept of droop control technique and is designed to control power from each individual generator in DC network particularly. The proposed power sharing control method can be widely applied to grid connected network and to islanded power grid network for obtaining high efficiency of power …

Robust Power Interface For Smart Grid With Renewable Energy Source-To-Grid Functionality, Bohyun Ahn

All Graduate Theses, Dissertations, and Other Capstone Projects

Many renewable energy companies design wind turbine generators, solar panels, or electrical car batteries with different specifications according to their management philosophy. And typical commercial power converters are not universally designed for all different types of renewable energy systems. Because of this lack of flexibility and interoperability, a universal and scalable smart grid power converter design is desirable. Designing a robust controlled bi-directional power converter is the motivation for this thesis as the first step to develop a more universal converter topology connecting renewable energy sources and the electrical smart-grid of the future.

Renewable energy such as wind or solar …