FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3170994518> ?p ?o ?g. }

• W3170994518 endingPage "104863" @default.
• W3170994518 startingPage "104863" @default.
• W3170994518 abstract "Accurate generation forecasting can effectively accelerate the use of renewable energy in hybrid energy systems, contributing significantly to the delivery of the net-zero emission target. Recently, neural-network-based quantile forecast models have shown superior performance on renewable energy generation forecasting, partially because they have subtly embedded quantile forecast evaluation metrics into their loss functions. However, the non-differentiability of involved metrics has rendered their metric-embedded loss functions not everywhere-derivable, resulting in inapplicability of gradient-based training approaches. Instead, they have resorted to heuristic searches for Neural Network (NN) training, bringing low training efficiency and a rigid restriction on the size of the resultant NN. In this paper, the Indicator Gradient Descent (IGD) is proposed to overcome the non-differentiability of involved metrics, and several metric-embedded loss functions are innovatively customized combining IGD, enabling NNs to be trained efficiently in a ‘gradient-descent-like’ manner. Moreover, the deep Bidirectional Long Short-Term Memory (BiLSTM) is adopted to capture the periodicity of renewable generation (diurnal and seasonal patterns), and the residual technique is used to improve the training efficiency of the deep BiLSTM. Finally, a Deep Quantile Forecast Network (DQFN) based on IGD and deep residual BiLSTM is developed for wind and solar power quantile forecasting. Practical experiments in four cases have verified the effectiveness and efficiency of DQFN and IGD, where DQFN has achieved the lowest average proportion deviations (all below 1.7%) and the highest skill scores. • First study on the differentiability of quantile forecast evaluation metrics. • The obstacles of applying deep learning to quantile forecast are revealed. • IGD is proposed to overcome the nondifferentiability of quantile evaluation metrics. • The IGD is GPU-compatible and time-efficient. • A deep-learning-based non-parametric quantile forecast model is developed." @default.
• W3170994518 created "2021-06-22" @default.
• W3170994518 creator A5006236325 @default.
• W3170994518 creator A5016564818 @default.
• W3170994518 creator A5059058846 @default.
• W3170994518 creator A5075852451 @default.
• W3170994518 creator A5079954554 @default.
• W3170994518 date "2021-09-01" @default.
• W3170994518 modified "2023-09-27" @default.
• W3170994518 title "Quantile forecast of renewable energy generation based on Indicator Gradient Descent and deep residual BiLSTM" @default.
• W3170994518 cites W1991420715 @default.
• W3170994518 cites W2002231816 @default.
• W3170994518 cites W2006558836 @default.
• W3170994518 cites W2019157375 @default.
• W3170994518 cites W2030132134 @default.
• W3170994518 cites W2046813720 @default.
• W3170994518 cites W2064675550 @default.
• W3170994518 cites W2068928057 @default.
• W3170994518 cites W2109762852 @default.
• W3170994518 cites W2114471530 @default.
• W3170994518 cites W2132477882 @default.
• W3170994518 cites W2155816288 @default.
• W3170994518 cites W2156604062 @default.
• W3170994518 cites W2165799067 @default.
• W3170994518 cites W2170517942 @default.
• W3170994518 cites W2194775991 @default.
• W3170994518 cites W2202062742 @default.
• W3170994518 cites W2322676867 @default.
• W3170994518 cites W2548694017 @default.
• W3170994518 cites W2554462191 @default.
• W3170994518 cites W2557248052 @default.
• W3170994518 cites W2560370080 @default.
• W3170994518 cites W2807030657 @default.
• W3170994518 cites W2889121747 @default.
• W3170994518 cites W2943809873 @default.
• W3170994518 cites W2978202285 @default.
• W3170994518 cites W2990479336 @default.
• W3170994518 cites W3012264837 @default.
• W3170994518 doi "https://doi.org/10.1016/j.conengprac.2021.104863" @default.
• W3170994518 hasPublicationYear "2021" @default.
• W3170994518 type Work @default.
• W3170994518 sameAs 3170994518 @default.
• W3170994518 citedByCount "17" @default.
• W3170994518 countsByYear W31709945182021 @default.
• W3170994518 countsByYear W31709945182022 @default.
• W3170994518 countsByYear W31709945182023 @default.
• W3170994518 crossrefType "journal-article" @default.
• W3170994518 hasAuthorship W3170994518A5006236325 @default.
• W3170994518 hasAuthorship W3170994518A5016564818 @default.
• W3170994518 hasAuthorship W3170994518A5059058846 @default.
• W3170994518 hasAuthorship W3170994518A5075852451 @default.
• W3170994518 hasAuthorship W3170994518A5079954554 @default.
• W3170994518 hasBestOaLocation W31709945182 @default.
• W3170994518 hasConcept C11413529 @default.
• W3170994518 hasConcept C118671147 @default.
• W3170994518 hasConcept C149782125 @default.
• W3170994518 hasConcept C153258448 @default.
• W3170994518 hasConcept C153294291 @default.
• W3170994518 hasConcept C154945302 @default.
• W3170994518 hasConcept C155512373 @default.
• W3170994518 hasConcept C188573790 @default.
• W3170994518 hasConcept C18903297 @default.
• W3170994518 hasConcept C205649164 @default.
• W3170994518 hasConcept C2776637919 @default.
• W3170994518 hasConcept C33923547 @default.
• W3170994518 hasConcept C39432304 @default.
• W3170994518 hasConcept C41008148 @default.
• W3170994518 hasConcept C50644808 @default.
• W3170994518 hasConcept C63817138 @default.
• W3170994518 hasConcept C86803240 @default.
• W3170994518 hasConceptScore W3170994518C11413529 @default.
• W3170994518 hasConceptScore W3170994518C118671147 @default.
• W3170994518 hasConceptScore W3170994518C149782125 @default.
• W3170994518 hasConceptScore W3170994518C153258448 @default.
• W3170994518 hasConceptScore W3170994518C153294291 @default.
• W3170994518 hasConceptScore W3170994518C154945302 @default.
• W3170994518 hasConceptScore W3170994518C155512373 @default.
• W3170994518 hasConceptScore W3170994518C188573790 @default.
• W3170994518 hasConceptScore W3170994518C18903297 @default.
• W3170994518 hasConceptScore W3170994518C205649164 @default.
• W3170994518 hasConceptScore W3170994518C2776637919 @default.
• W3170994518 hasConceptScore W3170994518C33923547 @default.
• W3170994518 hasConceptScore W3170994518C39432304 @default.
• W3170994518 hasConceptScore W3170994518C41008148 @default.
• W3170994518 hasConceptScore W3170994518C50644808 @default.
• W3170994518 hasConceptScore W3170994518C63817138 @default.
• W3170994518 hasConceptScore W3170994518C86803240 @default.
• W3170994518 hasLocation W31709945181 @default.
• W3170994518 hasLocation W31709945182 @default.
• W3170994518 hasOpenAccess W3170994518 @default.
• W3170994518 hasPrimaryLocation W31709945181 @default.
• W3170994518 hasRelatedWork W2079454017 @default.
• W3170994518 hasRelatedWork W2171769143 @default.
• W3170994518 hasRelatedWork W2224749288 @default.
• W3170994518 hasRelatedWork W2328874041 @default.
• W3170994518 hasRelatedWork W2563003513 @default.
• W3170994518 hasRelatedWork W2606485752 @default.
• W3170994518 hasRelatedWork W3007130393 @default.

• next