FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297282162> ?p ?o ?g. }

• W4297282162 endingPage "109556" @default.
• W4297282162 startingPage "109556" @default.
• W4297282162 abstract "Solar forecasting is a crucial and cost-effective tool for better utilization of solar energy for smart environment design. Artificial intelligence (AI) technologies, such as machine learning (ML) and deep learning (DL), have gained great popularity and been widely applied in solar forecasting in recent years. However, conventional AI-based forecasting methods suffer from high variability and stochasticity of solar irradiation, making unreliable predictions due to heterogeneous solar resources. Moreover, the training process of DL models is less flexible and requires immense data. Even for a well-trained model, it can still yield deteriorated performances on other datasets of varying data distributions. To tackle the deficiencies of AI forecasting models, we present a flexible distributed solar forecasting framework based on a novel spatial and temporal attention-based neural network (STANN) in conjunction with federated learning (FL) technique, considering multi-horizon forecasting scenario from 5–30 min. The STANN model consists of a feature extractor and a forecaster, which can be respectively trained on various local datasets for better localization, and updated to further improve forecasting accuracy through global parameter aggregation under the proposed framework without data gathering. We evaluate effectiveness of the proposed method by conducting extensive experiments on real-world datasets and compare it to other popular forecasting models. The results demonstrate that our approach outperforms the other benchmarks with higher forecasting accuracy for all forecast horizons and better generalization on various datasets, achieving the highest forecast skill of 28.83% at 30 min horizon and an improvement of 11.2% compared with the centralized, localized, and conventional FL training methods." @default.
• W4297282162 created "2022-09-28" @default.
• W4297282162 creator A5014048532 @default.
• W4297282162 creator A5037042853 @default.
• W4297282162 creator A5058197553 @default.
• W4297282162 creator A5074505893 @default.
• W4297282162 creator A5077392308 @default.
• W4297282162 creator A5084387930 @default.
• W4297282162 creator A5085556113 @default.
• W4297282162 date "2022-11-01" @default.
• W4297282162 modified "2023-10-14" @default.
• W4297282162 title "A solar forecasting framework based on federated learning and distributed computing" @default.
• W4297282162 cites W1668963720 @default.
• W4297282162 cites W1970463904 @default.
• W4297282162 cites W2017377889 @default.
• W4297282162 cites W2019495121 @default.
• W4297282162 cites W2031939255 @default.
• W4297282162 cites W2043167037 @default.
• W4297282162 cites W2056192250 @default.
• W4297282162 cites W2057132495 @default.
• W4297282162 cites W2063978378 @default.
• W4297282162 cites W2469734051 @default.
• W4297282162 cites W2596056971 @default.
• W4297282162 cites W2614843160 @default.
• W4297282162 cites W2801973365 @default.
• W4297282162 cites W2886034547 @default.
• W4297282162 cites W2889814654 @default.
• W4297282162 cites W2949062675 @default.
• W4297282162 cites W2960560113 @default.
• W4297282162 cites W2980994438 @default.
• W4297282162 cites W2989289980 @default.
• W4297282162 cites W3010852232 @default.
• W4297282162 cites W3016208458 @default.
• W4297282162 cites W3018306781 @default.
• W4297282162 cites W3096577976 @default.
• W4297282162 cites W3107178372 @default.
• W4297282162 cites W3112524728 @default.
• W4297282162 cites W3113923032 @default.
• W4297282162 cites W3129957816 @default.
• W4297282162 cites W3156459836 @default.
• W4297282162 cites W3163893137 @default.
• W4297282162 cites W3185003435 @default.
• W4297282162 cites W3201747364 @default.
• W4297282162 cites W3211338353 @default.
• W4297282162 cites W3214919557 @default.
• W4297282162 cites W4226120850 @default.
• W4297282162 cites W4294106961 @default.
• W4297282162 doi "https://doi.org/10.1016/j.buildenv.2022.109556" @default.
• W4297282162 hasPublicationYear "2022" @default.
• W4297282162 type Work @default.
• W4297282162 citedByCount "6" @default.
• W4297282162 countsByYear W42972821622023 @default.
• W4297282162 crossrefType "journal-article" @default.
• W4297282162 hasAuthorship W4297282162A5014048532 @default.
• W4297282162 hasAuthorship W4297282162A5037042853 @default.
• W4297282162 hasAuthorship W4297282162A5058197553 @default.
• W4297282162 hasAuthorship W4297282162A5074505893 @default.
• W4297282162 hasAuthorship W4297282162A5077392308 @default.
• W4297282162 hasAuthorship W4297282162A5084387930 @default.
• W4297282162 hasAuthorship W4297282162A5085556113 @default.
• W4297282162 hasConcept C111919701 @default.
• W4297282162 hasConcept C119857082 @default.
• W4297282162 hasConcept C124101348 @default.
• W4297282162 hasConcept C134306372 @default.
• W4297282162 hasConcept C154945302 @default.
• W4297282162 hasConcept C177148314 @default.
• W4297282162 hasConcept C33923547 @default.
• W4297282162 hasConcept C41008148 @default.
• W4297282162 hasConcept C50644808 @default.
• W4297282162 hasConcept C98045186 @default.
• W4297282162 hasConceptScore W4297282162C111919701 @default.
• W4297282162 hasConceptScore W4297282162C119857082 @default.
• W4297282162 hasConceptScore W4297282162C124101348 @default.
• W4297282162 hasConceptScore W4297282162C134306372 @default.
• W4297282162 hasConceptScore W4297282162C154945302 @default.
• W4297282162 hasConceptScore W4297282162C177148314 @default.
• W4297282162 hasConceptScore W4297282162C33923547 @default.
• W4297282162 hasConceptScore W4297282162C41008148 @default.
• W4297282162 hasConceptScore W4297282162C50644808 @default.
• W4297282162 hasConceptScore W4297282162C98045186 @default.
• W4297282162 hasLocation W42972821621 @default.
• W4297282162 hasOpenAccess W4297282162 @default.
• W4297282162 hasPrimaryLocation W42972821621 @default.
• W4297282162 hasRelatedWork W1630076647 @default.
• W4297282162 hasRelatedWork W1992324151 @default.
• W4297282162 hasRelatedWork W2048963458 @default.
• W4297282162 hasRelatedWork W2080152487 @default.
• W4297282162 hasRelatedWork W2120455979 @default.
• W4297282162 hasRelatedWork W2239445980 @default.
• W4297282162 hasRelatedWork W2359952343 @default.
• W4297282162 hasRelatedWork W2371138613 @default.
• W4297282162 hasRelatedWork W2922249299 @default.
• W4297282162 hasRelatedWork W43109613 @default.
• W4297282162 hasVolume "225" @default.
• W4297282162 isParatext "false" @default.
• W4297282162 isRetracted "false" @default.
• W4297282162 workType "article" @default.