SCALEX: SCALability EXploration of multi-agent reinforcement learning agents in grid-interactive efficient buildings

dc.contributor.advisorNagy, Gyorgy Zoltan
dc.creatorAlmilaify, Yara Sami
dc.date.accessioned2024-04-19T22:13:11Z
dc.date.available2024-04-19T22:13:11Z
dc.date.issued2023-08
dc.date.submittedAugust 2023
dc.date.updated2024-04-19T22:13:11Z
dc.description.abstractThe transition to renewable energy sources and the decarbonization of buildings bring new challenges to grid-interactive efficient building (GEB) communities such as grid stability issues and energy system integration. The dynamic and stochastic nature of intermittent renewable energy production makes it challenging for conventional building control systems to maximize them. To overcome this, advanced control architecture and energy storage are utilized to achieve energy flexibility. Reinforcement learning (RL) offers potential solutions, but its scalability and computational demands in large-scale settings remain unclear. This thesis examines the scalability of Soft-Actor Critic (SAC) in multi-agent systems, comparing decentralized-independent SACs and centralized SACs using CityLearn, an OpenAI Gym environment. We consider neighborhoods consisting of 2 to 64 single-family residential buildings, each equipped with cooling and heating storage devices, domestic hot water storage devices, electrical storage devices, and solar PV systems. In this work, we delve into the challenges faced by these controllers when scaled in a multi-agent system. Our findings suggest that decentralized-independent controllers outperform the centralized controller with an increasing number of buildings. We also show that the performance on the building level can differ from the aggregated performance.
dc.description.departmentCivil, Architectural, and Environmental Engineering
dc.format.mimetypeapplication/pdf
dc.identifier.uri
dc.identifier.urihttps://hdl.handle.net/2152/124879
dc.identifier.urihttps://doi.org/10.26153/tsw/51481
dc.language.isoen
dc.subjectReinforcement learning
dc.subjectEnergy flexibility
dc.subjectMulti-agent system
dc.subjectDemand response
dc.titleSCALEX: SCALability EXploration of multi-agent reinforcement learning agents in grid-interactive efficient buildings
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentCivil, Architectural, and Environmental Engineering
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.nameMaster of Science in Engineering
thesis.degree.programBuilding Energy and Environments

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
ALMILAIFY-PRIMARY-2024-1.pdf
Size:
7.2 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.84 KB
Format:
Plain Text
Description:
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.45 KB
Format:
Plain Text
Description: