Electrical and Computer Engineering ETDs

Publication Date

Fall 12-17-2022

Abstract

In this thesis, we introduce a reinforcement learning-based price-driven Demand Response Management (DRM) mechanism in smart grid systems consisting of prosumers. Our proposed approach accounts for the prosumers behavioral characteristics and models the emerging interactions among all the involved actors in the smart grid system, i.e., prosumers, Energy Management System (EMS) and utility companies. In particular, an off-policy reinforcement learning is introduced enabling the EMS to determine the optimal price that should be announced to the prosumers on an hourly-basis towards minimizing the overall systems cost. In this process, the utility companies hourly-based wholesale price and the prosumers energy generation and consumption characteristics are considered as input. At the same time, the prosumers optimal amount of purchased energy is determined in a real-time manner. The performance evaluation of the proposed approach is achieved via modeling and simulation. The presented numerical results demonstrate not only the operation and performance of the proposed mechanism, but also its effectiveness in accommodating prosumer populations of different behavioral characteristics in terms of purchasing energy patterns. Finally, a detailed comparative evaluation against other price-based DRM approaches is realized showing the key benefits and tradeoffs of our proposed model.

Keywords

Smart Grid Systems, Reinforcement Learning, System Modeling, Prosumers, Decision-making, Demand Response Management

Document Type

Thesis

Language

English

Degree Name

Computer Engineering

Level of Degree

Masters

Department Name

Electrical and Computer Engineering

First Committee Member (Chair)

Eirini Eleni Tsiropoulou

Second Committee Member

James Plusquellic

Third Committee Member

Symeon Papavassiliou

Download

Share

COinS