Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200626580> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4200626580 endingPage "012107" @default.
- W4200626580 startingPage "012107" @default.
- W4200626580 abstract "Abstract The building sector is responsible for approximately one-third of the total energy consumption, worldwide. This sector is undergoing a major digital transformation, buildings being more and more equipped with connected devices such as smart meters and IoT devices. This transformation offers the opportunity to better monitor and optimize building operations. In the province of Quebec (Canada), most buildings are equipped with smart meters providing electricity usage data every 15 minutes. A current major challenge is to disaggregate the different energy use from smart meter data, a discipline called non-intrusive load monitoring in literature. In this work, the aim is to develop and validate a potentially generalizable model for all houses that identifies the daily share of each energy use based on building information, weather data and smart meter data. Input features are selected and ordered using an aggregated score composed of the correlation coefficient, the feature importance given by a decision tree, and the predictive power score. Two modelling methods based on quantile regression are tested: linear regression (LR) and gradient boosted decision trees (GBDT). Compared to ordinary least squares regression, quantile methods inherently provide more robustness and confidence intervals. Both models are trained and validated using separate datasets collected in 8 houses in Canada where metering and sub-metering were performed during a whole year. Results on the test dataset indicate a better performance of the GBDT model, compared to the LR model, with a coefficient of determination of 0.88 (vs. 0.78), a mean absolute error of 6.34 % (vs. 8.89 %) and a maximum absolute error between the actual and predicted values in 95 % of the cases of 17.2 % (vs. 23.1 %)." @default.
- W4200626580 created "2021-12-31" @default.
- W4200626580 creator A5014421473 @default.
- W4200626580 creator A5018610209 @default.
- W4200626580 creator A5021265916 @default.
- W4200626580 creator A5049442271 @default.
- W4200626580 date "2021-11-01" @default.
- W4200626580 modified "2023-09-30" @default.
- W4200626580 title "Quantile regression using gradient boosted decision trees for daily residential energy load disaggregation" @default.
- W4200626580 cites W1970954003 @default.
- W4200626580 cites W1994042232 @default.
- W4200626580 cites W1995190797 @default.
- W4200626580 cites W2123910460 @default.
- W4200626580 cites W2151729265 @default.
- W4200626580 cites W2276149250 @default.
- W4200626580 cites W2619907041 @default.
- W4200626580 cites W2898355855 @default.
- W4200626580 cites W2942701956 @default.
- W4200626580 cites W2948816168 @default.
- W4200626580 cites W3080957353 @default.
- W4200626580 doi "https://doi.org/10.1088/1742-6596/2069/1/012107" @default.
- W4200626580 hasPublicationYear "2021" @default.
- W4200626580 type Work @default.
- W4200626580 citedByCount "0" @default.
- W4200626580 crossrefType "journal-article" @default.
- W4200626580 hasAuthorship W4200626580A5014421473 @default.
- W4200626580 hasAuthorship W4200626580A5018610209 @default.
- W4200626580 hasAuthorship W4200626580A5021265916 @default.
- W4200626580 hasAuthorship W4200626580A5049442271 @default.
- W4200626580 hasBestOaLocation W42006265801 @default.
- W4200626580 hasConcept C105795698 @default.
- W4200626580 hasConcept C118671147 @default.
- W4200626580 hasConcept C119599485 @default.
- W4200626580 hasConcept C119857082 @default.
- W4200626580 hasConcept C124101348 @default.
- W4200626580 hasConcept C127413603 @default.
- W4200626580 hasConcept C206658404 @default.
- W4200626580 hasConcept C2779510800 @default.
- W4200626580 hasConcept C30905978 @default.
- W4200626580 hasConcept C33923547 @default.
- W4200626580 hasConcept C41008148 @default.
- W4200626580 hasConcept C48921125 @default.
- W4200626580 hasConcept C63817138 @default.
- W4200626580 hasConcept C78519656 @default.
- W4200626580 hasConcept C84525736 @default.
- W4200626580 hasConceptScore W4200626580C105795698 @default.
- W4200626580 hasConceptScore W4200626580C118671147 @default.
- W4200626580 hasConceptScore W4200626580C119599485 @default.
- W4200626580 hasConceptScore W4200626580C119857082 @default.
- W4200626580 hasConceptScore W4200626580C124101348 @default.
- W4200626580 hasConceptScore W4200626580C127413603 @default.
- W4200626580 hasConceptScore W4200626580C206658404 @default.
- W4200626580 hasConceptScore W4200626580C2779510800 @default.
- W4200626580 hasConceptScore W4200626580C30905978 @default.
- W4200626580 hasConceptScore W4200626580C33923547 @default.
- W4200626580 hasConceptScore W4200626580C41008148 @default.
- W4200626580 hasConceptScore W4200626580C48921125 @default.
- W4200626580 hasConceptScore W4200626580C63817138 @default.
- W4200626580 hasConceptScore W4200626580C78519656 @default.
- W4200626580 hasConceptScore W4200626580C84525736 @default.
- W4200626580 hasIssue "1" @default.
- W4200626580 hasLocation W42006265801 @default.
- W4200626580 hasOpenAccess W4200626580 @default.
- W4200626580 hasPrimaryLocation W42006265801 @default.
- W4200626580 hasRelatedWork W1976663376 @default.
- W4200626580 hasRelatedWork W2134463589 @default.
- W4200626580 hasRelatedWork W2365750359 @default.
- W4200626580 hasRelatedWork W2381759556 @default.
- W4200626580 hasRelatedWork W2793775341 @default.
- W4200626580 hasRelatedWork W2930818372 @default.
- W4200626580 hasRelatedWork W3152451540 @default.
- W4200626580 hasRelatedWork W3205772889 @default.
- W4200626580 hasRelatedWork W4200626580 @default.
- W4200626580 hasRelatedWork W4223551069 @default.
- W4200626580 hasVolume "2069" @default.
- W4200626580 isParatext "false" @default.
- W4200626580 isRetracted "false" @default.
- W4200626580 workType "article" @default.