Matches in SemOpenAlex for { <https://semopenalex.org/work/W4207014241> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4207014241 endingPage "253" @default.
- W4207014241 startingPage "241" @default.
- W4207014241 abstract "Day-ahead energy forecasting systems struggle to provide accurate demand predictions due to pandemic mitigation measures. Decomposition-Residuals Deep Neural Networks (DR-DNN) are hybrid point-forecasting models that can provide more accurate electricity demand predictions than single models within the COVID-19 era. DR-DNN is a novel two-layer hybrid architecture with: a decomposition and a nonlinear layer. Based on statistical tests, decomposition applies robust signal extraction and filtering of input data into: trend, seasonal and residuals signals. Utilizing calendar information, temporal signals are added: sinusoidal day/night cycles, weekend/weekday, etc. The nonlinear layer learns unknown complex patterns from all those signals, with the usage of well-established deep neural networks. DR-DNN outperformed baselines and state-of-the-art deep neural networks on next-day electricity forecasts within the COVID-19 era (from September 2020 to February 2021), both with fixed and Bayesian optimized hyperparameters. Additionally, model interpretability is improved, by indicating which endogenous or exogenous inputs contribute the most to specific hour-ahead forecasts. Residual signals are very important on the first hour ahead, whereas seasonal patterns on the 24th. Some calendar features also ranked high: whether it is day or night, weekend or weekday and the hour of the day. Temperature was the most important exogenous factor." @default.
- W4207014241 created "2022-01-26" @default.
- W4207014241 creator A5012821752 @default.
- W4207014241 creator A5018814006 @default.
- W4207014241 creator A5024267406 @default.
- W4207014241 creator A5066047272 @default.
- W4207014241 date "2022-01-01" @default.
- W4207014241 modified "2023-10-01" @default.
- W4207014241 title "Decomposition-Residuals Neural Networks: Hybrid System Identification Applied to Electricity Demand Forecasting" @default.
- W4207014241 cites W1498436455 @default.
- W4207014241 cites W1530342954 @default.
- W4207014241 cites W1588163064 @default.
- W4207014241 cites W1902237438 @default.
- W4207014241 cites W1995341919 @default.
- W4207014241 cites W2001506129 @default.
- W4207014241 cites W2064675550 @default.
- W4207014241 cites W2117922789 @default.
- W4207014241 cites W2157331557 @default.
- W4207014241 cites W2181523240 @default.
- W4207014241 cites W2342249984 @default.
- W4207014241 cites W2728073923 @default.
- W4207014241 cites W2754252319 @default.
- W4207014241 cites W2794778778 @default.
- W4207014241 cites W2802586787 @default.
- W4207014241 cites W2892741787 @default.
- W4207014241 cites W2962752580 @default.
- W4207014241 cites W2963507686 @default.
- W4207014241 cites W2971724044 @default.
- W4207014241 cites W3011590044 @default.
- W4207014241 cites W3024158773 @default.
- W4207014241 cites W3025111165 @default.
- W4207014241 cites W3143320143 @default.
- W4207014241 cites W3171884590 @default.
- W4207014241 cites W3198282457 @default.
- W4207014241 cites W4239281537 @default.
- W4207014241 doi "https://doi.org/10.1109/oajpe.2022.3145520" @default.
- W4207014241 hasPublicationYear "2022" @default.
- W4207014241 type Work @default.
- W4207014241 citedByCount "3" @default.
- W4207014241 countsByYear W42070142412023 @default.
- W4207014241 crossrefType "journal-article" @default.
- W4207014241 hasAuthorship W4207014241A5012821752 @default.
- W4207014241 hasAuthorship W4207014241A5018814006 @default.
- W4207014241 hasAuthorship W4207014241A5024267406 @default.
- W4207014241 hasAuthorship W4207014241A5066047272 @default.
- W4207014241 hasBestOaLocation W42070142411 @default.
- W4207014241 hasConcept C107673813 @default.
- W4207014241 hasConcept C11413529 @default.
- W4207014241 hasConcept C119857082 @default.
- W4207014241 hasConcept C124101348 @default.
- W4207014241 hasConcept C149782125 @default.
- W4207014241 hasConcept C154945302 @default.
- W4207014241 hasConcept C155512373 @default.
- W4207014241 hasConcept C2781067378 @default.
- W4207014241 hasConcept C33923547 @default.
- W4207014241 hasConcept C41008148 @default.
- W4207014241 hasConcept C50644808 @default.
- W4207014241 hasConcept C8642999 @default.
- W4207014241 hasConceptScore W4207014241C107673813 @default.
- W4207014241 hasConceptScore W4207014241C11413529 @default.
- W4207014241 hasConceptScore W4207014241C119857082 @default.
- W4207014241 hasConceptScore W4207014241C124101348 @default.
- W4207014241 hasConceptScore W4207014241C149782125 @default.
- W4207014241 hasConceptScore W4207014241C154945302 @default.
- W4207014241 hasConceptScore W4207014241C155512373 @default.
- W4207014241 hasConceptScore W4207014241C2781067378 @default.
- W4207014241 hasConceptScore W4207014241C33923547 @default.
- W4207014241 hasConceptScore W4207014241C41008148 @default.
- W4207014241 hasConceptScore W4207014241C50644808 @default.
- W4207014241 hasConceptScore W4207014241C8642999 @default.
- W4207014241 hasLocation W42070142411 @default.
- W4207014241 hasLocation W42070142412 @default.
- W4207014241 hasOpenAccess W4207014241 @default.
- W4207014241 hasPrimaryLocation W42070142411 @default.
- W4207014241 hasRelatedWork W3006943036 @default.
- W4207014241 hasRelatedWork W4206534706 @default.
- W4207014241 hasRelatedWork W4210794429 @default.
- W4207014241 hasRelatedWork W4223456145 @default.
- W4207014241 hasRelatedWork W4229079080 @default.
- W4207014241 hasRelatedWork W4295309597 @default.
- W4207014241 hasRelatedWork W4385572946 @default.
- W4207014241 hasRelatedWork W4385957992 @default.
- W4207014241 hasRelatedWork W4385965371 @default.
- W4207014241 hasRelatedWork W4386025632 @default.
- W4207014241 hasVolume "9" @default.
- W4207014241 isParatext "false" @default.
- W4207014241 isRetracted "false" @default.
- W4207014241 workType "article" @default.