Hu, Rui
(2020)
A Distributed Energy Management Strategy for Renewable Powered Communication Microgrid using Game Theory and Reinforcement Learning.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
Abstract
This dissertation explores distributed energy management strategies for base stations in a communication microgrid, which is intended to be operating in island mode powered exclusively by renewable power sources. The energy management strategy aims at searching for an optimal energy consumption plan considering both communication quality and energy availability. In this dissertation, the objective is to accomplish such energy management using distributed control architecture, because such architecture is more durable and robust compared to a central controller. Three approaches have been proposed: multi-player game, reinforcement learning, and a hierarchical load-ratio updating algorithm. The modelings, mechanisms, performance, and applicable conditions of the three algorithms are discussed and compared. Numerical simulation results of communication microgrids in multiple cases implemented with the three algorithms were conducted. As the numerical results show, the hierarchical game-learning algorithm has a better performance compared to the multi-player game approach in terms of computation complexity and faster-converging speed compared to that of the reinforcement learning approach.
Share
Citation/Export: |
|
Social Networking: |
|
Details
Item Type: |
University of Pittsburgh ETD
|
Status: |
Unpublished |
Creators/Authors: |
|
ETD Committee: |
|
Date: |
29 January 2020 |
Date Type: |
Publication |
Defense Date: |
8 November 2019 |
Approval Date: |
29 January 2020 |
Submission Date: |
18 September 2019 |
Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
Number of Pages: |
161 |
Institution: |
University of Pittsburgh |
Schools and Programs: |
Swanson School of Engineering > Electrical and Computer Engineering |
Degree: |
PhD - Doctor of Philosophy |
Thesis Type: |
Doctoral Dissertation |
Refereed: |
Yes |
Uncontrolled Keywords: |
Microgrid, energy management, communication system, game theory, reinforcement learning, multi-agent system |
Date Deposited: |
29 Jan 2020 16:07 |
Last Modified: |
29 Jan 2020 16:07 |
URI: |
http://d-scholarship.pitt.edu/id/eprint/37655 |
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |