Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384937002> ?p ?o ?g. }
- W4384937002 endingPage "113377" @default.
- W4384937002 startingPage "113377" @default.
- W4384937002 abstract "Smart thermostats are increasingly popular in homes and buildings as they improve occupant comfort, lower energy use in heating and cooling systems, and reduce utility bills by automatically adjusting room temperature according to measurements of their built-in sensors. To maximize energy savings, many of these thermostats use machine learning (ML) for more accurate prediction and optimal control. These ML models must be trained for each individual building to ensure higher thermal comfort and energy savings, owing to the fact that buildings are custom-built, can be located in different climates, and may have unique occupancy patterns. This kind of training requires a significant amount of energy and sharing raw data emitted by the sensors in each building. To address these issues, we propose a novel methodology to train accurate and personalized thermal models for each home with a minimal energy footprint. Specifically, we use temporal and spatial abstraction to downsample sensor data and cluster homes with similar characteristics to train representative thermal models for each cluster. These models are customized for each home using meta-learning, achieving personalized models with high accuracy. Additionally, combining multi-step ahead prediction with our proposed abstraction technique would permit resource-constrained devices (e.g., microcontrollers) to accurately forecast indoor temperature for larger time intervals with negligible computation overhead. Experiments with smart thermostat data from 1,000 homes show that our methodology offers accurate and personalized thermal models with substantial savings in network bandwidth and training energy. To be specific, our methodology is approximately 384 (300) times more energy efficient than training an LSTM (RNN) model using the conventional approaches. Given the anticipated increase in the demand for smart thermostats and the fact that thermal models must be (re)trained regularly (e.g., every season), the proposed methodology could significantly reduce the environmental impact of training ML models for thermal comfort optimization in the long run." @default.
- W4384937002 created "2023-07-22" @default.
- W4384937002 creator A5006772417 @default.
- W4384937002 creator A5016454155 @default.
- W4384937002 creator A5023615606 @default.
- W4384937002 creator A5049321288 @default.
- W4384937002 creator A5079048464 @default.
- W4384937002 date "2023-10-01" @default.
- W4384937002 modified "2023-10-02" @default.
- W4384937002 title "Efficacy of temporal and spatial abstraction for training accurate machine learning models: A case study in smart thermostats" @default.
- W4384937002 cites W2005289033 @default.
- W4384937002 cites W2024081693 @default.
- W4384937002 cites W2029889874 @default.
- W4384937002 cites W2040640105 @default.
- W4384937002 cites W2049425685 @default.
- W4384937002 cites W2069143585 @default.
- W4384937002 cites W2074121977 @default.
- W4384937002 cites W2088563154 @default.
- W4384937002 cites W2163121678 @default.
- W4384937002 cites W2314153399 @default.
- W4384937002 cites W2395241182 @default.
- W4384937002 cites W2754252319 @default.
- W4384937002 cites W2807354412 @default.
- W4384937002 cites W2898978958 @default.
- W4384937002 cites W2902435213 @default.
- W4384937002 cites W2906033034 @default.
- W4384937002 cites W2951505812 @default.
- W4384937002 cites W3082211556 @default.
- W4384937002 cites W3094324443 @default.
- W4384937002 cites W3132397320 @default.
- W4384937002 cites W3181448069 @default.
- W4384937002 cites W3212486046 @default.
- W4384937002 cites W4224243992 @default.
- W4384937002 cites W4292551110 @default.
- W4384937002 cites W4306411322 @default.
- W4384937002 doi "https://doi.org/10.1016/j.enbuild.2023.113377" @default.
- W4384937002 hasPublicationYear "2023" @default.
- W4384937002 type Work @default.
- W4384937002 citedByCount "0" @default.
- W4384937002 crossrefType "journal-article" @default.
- W4384937002 hasAuthorship W4384937002A5006772417 @default.
- W4384937002 hasAuthorship W4384937002A5016454155 @default.
- W4384937002 hasAuthorship W4384937002A5023615606 @default.
- W4384937002 hasAuthorship W4384937002A5049321288 @default.
- W4384937002 hasAuthorship W4384937002A5079048464 @default.
- W4384937002 hasConcept C105795698 @default.
- W4384937002 hasConcept C111472728 @default.
- W4384937002 hasConcept C111919701 @default.
- W4384937002 hasConcept C119599485 @default.
- W4384937002 hasConcept C119857082 @default.
- W4384937002 hasConcept C121332964 @default.
- W4384937002 hasConcept C124304363 @default.
- W4384937002 hasConcept C127413603 @default.
- W4384937002 hasConcept C133913538 @default.
- W4384937002 hasConcept C138885662 @default.
- W4384937002 hasConcept C154945302 @default.
- W4384937002 hasConcept C186370098 @default.
- W4384937002 hasConcept C187819001 @default.
- W4384937002 hasConcept C2742236 @default.
- W4384937002 hasConcept C2779960059 @default.
- W4384937002 hasConcept C2780165032 @default.
- W4384937002 hasConcept C33923547 @default.
- W4384937002 hasConcept C41008148 @default.
- W4384937002 hasConcept C44154836 @default.
- W4384937002 hasConcept C78519656 @default.
- W4384937002 hasConcept C79403827 @default.
- W4384937002 hasConcept C97355855 @default.
- W4384937002 hasConceptScore W4384937002C105795698 @default.
- W4384937002 hasConceptScore W4384937002C111472728 @default.
- W4384937002 hasConceptScore W4384937002C111919701 @default.
- W4384937002 hasConceptScore W4384937002C119599485 @default.
- W4384937002 hasConceptScore W4384937002C119857082 @default.
- W4384937002 hasConceptScore W4384937002C121332964 @default.
- W4384937002 hasConceptScore W4384937002C124304363 @default.
- W4384937002 hasConceptScore W4384937002C127413603 @default.
- W4384937002 hasConceptScore W4384937002C133913538 @default.
- W4384937002 hasConceptScore W4384937002C138885662 @default.
- W4384937002 hasConceptScore W4384937002C154945302 @default.
- W4384937002 hasConceptScore W4384937002C186370098 @default.
- W4384937002 hasConceptScore W4384937002C187819001 @default.
- W4384937002 hasConceptScore W4384937002C2742236 @default.
- W4384937002 hasConceptScore W4384937002C2779960059 @default.
- W4384937002 hasConceptScore W4384937002C2780165032 @default.
- W4384937002 hasConceptScore W4384937002C33923547 @default.
- W4384937002 hasConceptScore W4384937002C41008148 @default.
- W4384937002 hasConceptScore W4384937002C44154836 @default.
- W4384937002 hasConceptScore W4384937002C78519656 @default.
- W4384937002 hasConceptScore W4384937002C79403827 @default.
- W4384937002 hasConceptScore W4384937002C97355855 @default.
- W4384937002 hasLocation W43849370021 @default.
- W4384937002 hasOpenAccess W4384937002 @default.
- W4384937002 hasPrimaryLocation W43849370021 @default.
- W4384937002 hasRelatedWork W1602410219 @default.
- W4384937002 hasRelatedWork W2023346859 @default.
- W4384937002 hasRelatedWork W2025004390 @default.
- W4384937002 hasRelatedWork W2029268337 @default.
- W4384937002 hasRelatedWork W2089393798 @default.
- W4384937002 hasRelatedWork W2914113010 @default.