Publications
Detailed Information
Rule reduction for control of a building cooling system using explainable AI
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Seongkwon | - |
dc.contributor.author | Park, Cheol Soo | - |
dc.date.accessioned | 2022-10-07T01:43:40Z | - |
dc.date.available | 2022-10-07T01:43:40Z | - |
dc.date.created | 2022-08-18 | - |
dc.date.issued | 2022-11 | - |
dc.identifier.citation | Journal of Building Performance Simulation, Vol.15 No.6, pp.832-847 | - |
dc.identifier.issn | 1940-1493 | - |
dc.identifier.uri | https://hdl.handle.net/10371/185593 | - |
dc.description.abstract | Although it is widely acknowledged that reinforcement learning (RL) can be beneficial for building control, many RL-based control actions remain unexplainable in the daily practice of facility managers. This paper reports a rule reduction framework using explainable RL to enhance the practicality of the control strategy. First, deep Q-learning was applied to explore the optimal control strategies of a parallel cooling system (ice-based thermal system + geothermal heat pump system) of an existing office building. A set of modularized and interconnected data-driven models was developed using ANNs for pretraining an artificial agent. After exploring the control strategies, the decision-making rules of the agent were reduced using a decision tree. The performance of the reduced-order rule-based control proved comparable to the complex and uninterpretable control strategy of deep Q-learning. The difference in energy savings between the two is marginal at 1.2%. | - |
dc.language | 영어 | - |
dc.publisher | Taylor & Francis | - |
dc.title | Rule reduction for control of a building cooling system using explainable AI | - |
dc.type | Article | - |
dc.identifier.doi | 10.1080/19401493.2022.2103586 | - |
dc.citation.journaltitle | Journal of Building Performance Simulation | - |
dc.identifier.wosid | 000835965300001 | - |
dc.identifier.scopusid | 2-s2.0-85135473811 | - |
dc.citation.endpage | 847 | - |
dc.citation.number | 6 | - |
dc.citation.startpage | 832 | - |
dc.citation.volume | 15 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Park, Cheol Soo | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.