Reinforcement learning techniques for controlling resources in power networks

Kowli, Anupama

Permalink

https://hdl.handle.net/2142/45328 Copy

Description

Title

Reinforcement learning techniques for controlling resources in power networks

Author(s)

Kowli, Anupama

Issue Date

2013-08-22T16:36:46Z

Director of Research (if dissertation) or Advisor (if thesis)

Meyn, Sean P.

Doctoral Committee Chair(s)

Meyn, Sean P.

Committee Member(s)

• Sauer, Peter W.
• Domínguez-García, Alejandro D.
• Sanders, William H.

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

Ph.D.

Degree Level

Dissertation

Keyword(s)

• ancillary services
• approximate dynamic programming
• demand response
• economic dispatch
• energy storage
• Markov decision theory
• model predictive control
• power networks
• reinforcement learning
• renewable integration
• smart grid
• stochastic control
• unit commitment
• wind power

Abstract

"As power grids transition towards increased reliance on renewable generation, energy storage and demand response resources, an effective control architecture is required to harness the full functionalities of these resources. There is a critical need for control techniques that recognize the unique characteristics of the different resources and exploit the flexibility afforded by them to provide ancillary services to the grid. The work presented in this dissertation addresses these needs. Specifically, new algorithms are proposed, which allow control synthesis in settings wherein the precise distribution of the uncertainty and its temporal statistics are not known. These algorithms are based on recent developments in Markov decision theory, approximate dynamic programming and reinforcement learning. They impose minimal assumptions on the system model and allow the control to be ""learned"" based on the actual dynamics of the system. Furthermore, they can accommodate complex constraints such as capacity and ramping limits on generation resources, state-of-charge constraints on storage resources, comfort-related limitations on demand response resources and power flow limits on transmission lines. Numerical studies demonstrating applications of these algorithms to practical control problems in power systems are discussed. Results demonstrate how the proposed control algorithms can be used to improve the performance and reduce the computational complexity of the economic dispatch mechanism in a power network. We argue that the proposed algorithms are eminently suitable to develop operational decision-making tools for large power grids with many resources and many sources of uncertainty."

Graduation Semester

2013-08

Permalink

http://hdl.handle.net/2142/45328

Copyright and License Information

Copyright 2013 Anupama Sunil Kowli

Owning Collections