FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284887160> ?p ?o ?g. }

• W4284887160 endingPage "112278" @default.
• W4284887160 startingPage "112278" @default.
• W4284887160 abstract "Reliable building simulation models are key to optimizing building performance and reducing greenhouse gas emissions. Informed decision making requires simulation models to be accurate, extrapolatable, and interpretable, all of which require calibrating model simulations to ground truth. Complicated building dynamics and highly uncertain exogenous disturbances make the model calibration process challenging and expensive; hence, a scalable and efficient calibration approach is needed to enable actual application. Current automatic calibration algorithms do not leverage data collected from multiple sources: for example, data obtained from previous calibration tasks on other buildings. In this paper, we employ probabilistic deep learning to meta-learn a distribution using multi-source data acquired during previous calibration. Subsequently, the meta-learned Bayesian optimizer accelerates calibration of new, unseen tasks. The few-shot (that is, requiring few model simulations) nature of the proposed algorithm is demonstrated on a Modelica library of residential buildings validated by the United States Department of Energy (USDoE). The proposed algorithm is compared against classical Bayesian optimization-based calibration, and it is shown that ANP significantly sped up the calibration procedure: the optimal model parameters are identified with 40–60% less simulations compared to the baseline." @default.
• W4284887160 created "2022-07-09" @default.
• W4284887160 creator A5005955195 @default.
• W4284887160 creator A5069430909 @default.
• W4284887160 creator A5074220429 @default.
• W4284887160 creator A5081453619 @default.
• W4284887160 creator A5086940921 @default.
• W4284887160 date "2022-09-01" @default.
• W4284887160 modified "2023-09-28" @default.
• W4284887160 title "Calibrating building simulation models using multi-source datasets and meta-learned Bayesian optimization" @default.
• W4284887160 cites W2028962976 @default.
• W4284887160 cites W2247885690 @default.
• W4284887160 cites W2330492788 @default.
• W4284887160 cites W2512816756 @default.
• W4284887160 cites W2568283272 @default.
• W4284887160 cites W2746142811 @default.
• W4284887160 cites W2750869373 @default.
• W4284887160 cites W2810532979 @default.
• W4284887160 cites W2937535234 @default.
• W4284887160 cites W2952907678 @default.
• W4284887160 cites W2967522383 @default.
• W4284887160 cites W2970667563 @default.
• W4284887160 cites W2997051579 @default.
• W4284887160 cites W3007023248 @default.
• W4284887160 cites W3029097710 @default.
• W4284887160 cites W3047806272 @default.
• W4284887160 cites W3085257246 @default.
• W4284887160 cites W3097240822 @default.
• W4284887160 cites W3123621884 @default.
• W4284887160 cites W3136282444 @default.
• W4284887160 cites W3185248144 @default.
• W4284887160 cites W3203675700 @default.
• W4284887160 cites W3211439419 @default.
• W4284887160 cites W4214478937 @default.
• W4284887160 cites W4220757995 @default.
• W4284887160 doi "https://doi.org/10.1016/j.enbuild.2022.112278" @default.
• W4284887160 hasPublicationYear "2022" @default.
• W4284887160 type Work @default.
• W4284887160 citedByCount "4" @default.
• W4284887160 countsByYear W42848871602023 @default.
• W4284887160 crossrefType "journal-article" @default.
• W4284887160 hasAuthorship W4284887160A5005955195 @default.
• W4284887160 hasAuthorship W4284887160A5069430909 @default.
• W4284887160 hasAuthorship W4284887160A5074220429 @default.
• W4284887160 hasAuthorship W4284887160A5081453619 @default.
• W4284887160 hasAuthorship W4284887160A5086940921 @default.
• W4284887160 hasConcept C105795698 @default.
• W4284887160 hasConcept C107673813 @default.
• W4284887160 hasConcept C111368507 @default.
• W4284887160 hasConcept C111919701 @default.
• W4284887160 hasConcept C119857082 @default.
• W4284887160 hasConcept C124101348 @default.
• W4284887160 hasConcept C12725497 @default.
• W4284887160 hasConcept C127313418 @default.
• W4284887160 hasConcept C153083717 @default.
• W4284887160 hasConcept C154945302 @default.
• W4284887160 hasConcept C160234255 @default.
• W4284887160 hasConcept C165838908 @default.
• W4284887160 hasConcept C26517878 @default.
• W4284887160 hasConcept C2778049539 @default.
• W4284887160 hasConcept C33923547 @default.
• W4284887160 hasConcept C38652104 @default.
• W4284887160 hasConcept C41008148 @default.
• W4284887160 hasConcept C44154836 @default.
• W4284887160 hasConcept C48044578 @default.
• W4284887160 hasConcept C49937458 @default.
• W4284887160 hasConcept C77088390 @default.
• W4284887160 hasConcept C98045186 @default.
• W4284887160 hasConceptScore W4284887160C105795698 @default.
• W4284887160 hasConceptScore W4284887160C107673813 @default.
• W4284887160 hasConceptScore W4284887160C111368507 @default.
• W4284887160 hasConceptScore W4284887160C111919701 @default.
• W4284887160 hasConceptScore W4284887160C119857082 @default.
• W4284887160 hasConceptScore W4284887160C124101348 @default.
• W4284887160 hasConceptScore W4284887160C12725497 @default.
• W4284887160 hasConceptScore W4284887160C127313418 @default.
• W4284887160 hasConceptScore W4284887160C153083717 @default.
• W4284887160 hasConceptScore W4284887160C154945302 @default.
• W4284887160 hasConceptScore W4284887160C160234255 @default.
• W4284887160 hasConceptScore W4284887160C165838908 @default.
• W4284887160 hasConceptScore W4284887160C26517878 @default.
• W4284887160 hasConceptScore W4284887160C2778049539 @default.
• W4284887160 hasConceptScore W4284887160C33923547 @default.
• W4284887160 hasConceptScore W4284887160C38652104 @default.
• W4284887160 hasConceptScore W4284887160C41008148 @default.
• W4284887160 hasConceptScore W4284887160C44154836 @default.
• W4284887160 hasConceptScore W4284887160C48044578 @default.
• W4284887160 hasConceptScore W4284887160C49937458 @default.
• W4284887160 hasConceptScore W4284887160C77088390 @default.
• W4284887160 hasConceptScore W4284887160C98045186 @default.
• W4284887160 hasLocation W42848871601 @default.
• W4284887160 hasOpenAccess W4284887160 @default.
• W4284887160 hasPrimaryLocation W42848871601 @default.
• W4284887160 hasRelatedWork W1535019556 @default.
• W4284887160 hasRelatedWork W2010134675 @default.
• W4284887160 hasRelatedWork W2464761573 @default.
• W4284887160 hasRelatedWork W2724199550 @default.
• W4284887160 hasRelatedWork W2912860240 @default.

• next