Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293318869> ?p ?o ?g. }
- W4293318869 abstract "Accurately forecasting solar plants production is critical for balancing supply and demand and for scheduling distribution networks operation in the context of inclusive smart cities and energy communities. However, the problem becomes more demanding, when there is insufficient amount of data to adequately train forecasting models, due to plants being recently installed or because of lack of smart-meters. Transfer learning (TL) offers the capability of transferring knowledge from the source domain to different target domains to resolve related problems. This study uses the stacked Long Short-Term Memory (LSTM) model with three TL strategies to provide accurate solar plant production forecasts. TL is exploited both for weight initialization of the LSTM model and for feature extraction, using different freezing approaches. The presented TL strategies are compared to the conventional non-TL model, as well as to the smart persistence model, at forecasting the hourly production of 6 solar plants. Results indicate that TL models significantly outperform the conventional one, achieving 12.6% accuracy improvement in terms of RMSE and 16.3% in terms of forecast skill index with 1 year of training data. The gap between the two approaches becomes even bigger when fewer training data are available (especially in the case of a 3-month training set), breaking new ground in power production forecasting of newly installed solar plants and rendering TL a reliable tool in the hands of self-producers towards the ultimate goal of energy balancing and demand response management from an early stage." @default.
- W4293318869 created "2022-08-27" @default.
- W4293318869 creator A5008411897 @default.
- W4293318869 creator A5026215572 @default.
- W4293318869 creator A5058865022 @default.
- W4293318869 creator A5059115129 @default.
- W4293318869 creator A5079676696 @default.
- W4293318869 date "2022-08-27" @default.
- W4293318869 modified "2023-09-27" @default.
- W4293318869 title "Transfer learning strategies for solar power forecasting under data scarcity" @default.
- W4293318869 cites W1966808540 @default.
- W4293318869 cites W1981873099 @default.
- W4293318869 cites W1986614398 @default.
- W4293318869 cites W2001863701 @default.
- W4293318869 cites W2031939255 @default.
- W4293318869 cites W2057961985 @default.
- W4293318869 cites W2064675550 @default.
- W4293318869 cites W2069143585 @default.
- W4293318869 cites W2075728230 @default.
- W4293318869 cites W2079547580 @default.
- W4293318869 cites W2091161129 @default.
- W4293318869 cites W2114668738 @default.
- W4293318869 cites W2136848157 @default.
- W4293318869 cites W2143612262 @default.
- W4293318869 cites W2165698076 @default.
- W4293318869 cites W2207398520 @default.
- W4293318869 cites W2321449197 @default.
- W4293318869 cites W2395579298 @default.
- W4293318869 cites W2469734051 @default.
- W4293318869 cites W2610219179 @default.
- W4293318869 cites W2614843160 @default.
- W4293318869 cites W2752788177 @default.
- W4293318869 cites W2753588254 @default.
- W4293318869 cites W2754252319 @default.
- W4293318869 cites W2760948241 @default.
- W4293318869 cites W2792046648 @default.
- W4293318869 cites W2803000678 @default.
- W4293318869 cites W2887280559 @default.
- W4293318869 cites W2888945543 @default.
- W4293318869 cites W2907788173 @default.
- W4293318869 cites W2917491574 @default.
- W4293318869 cites W2941116662 @default.
- W4293318869 cites W2942656280 @default.
- W4293318869 cites W2943571340 @default.
- W4293318869 cites W2947936356 @default.
- W4293318869 cites W2948490758 @default.
- W4293318869 cites W2982191044 @default.
- W4293318869 cites W2999491213 @default.
- W4293318869 cites W3016208458 @default.
- W4293318869 cites W3020215048 @default.
- W4293318869 cites W3021308819 @default.
- W4293318869 cites W3024509612 @default.
- W4293318869 cites W3033993664 @default.
- W4293318869 cites W3049740698 @default.
- W4293318869 cites W3119379445 @default.
- W4293318869 cites W3125093885 @default.
- W4293318869 cites W3126094341 @default.
- W4293318869 cites W3130233092 @default.
- W4293318869 cites W3155126723 @default.
- W4293318869 cites W3189040769 @default.
- W4293318869 cites W4200623431 @default.
- W4293318869 cites W4206106088 @default.
- W4293318869 cites W4225380154 @default.
- W4293318869 cites W4255421341 @default.
- W4293318869 doi "https://doi.org/10.1038/s41598-022-18516-x" @default.
- W4293318869 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36030346" @default.
- W4293318869 hasPublicationYear "2022" @default.
- W4293318869 type Work @default.
- W4293318869 citedByCount "8" @default.
- W4293318869 countsByYear W42933188692022 @default.
- W4293318869 countsByYear W42933188692023 @default.
- W4293318869 crossrefType "journal-article" @default.
- W4293318869 hasAuthorship W4293318869A5008411897 @default.
- W4293318869 hasAuthorship W4293318869A5026215572 @default.
- W4293318869 hasAuthorship W4293318869A5058865022 @default.
- W4293318869 hasAuthorship W4293318869A5059115129 @default.
- W4293318869 hasAuthorship W4293318869A5079676696 @default.
- W4293318869 hasBestOaLocation W42933188691 @default.
- W4293318869 hasConcept C109747225 @default.
- W4293318869 hasConcept C114466953 @default.
- W4293318869 hasConcept C119599485 @default.
- W4293318869 hasConcept C119857082 @default.
- W4293318869 hasConcept C127413603 @default.
- W4293318869 hasConcept C150899416 @default.
- W4293318869 hasConcept C151730666 @default.
- W4293318869 hasConcept C154945302 @default.
- W4293318869 hasConcept C162324750 @default.
- W4293318869 hasConcept C175444787 @default.
- W4293318869 hasConcept C188573790 @default.
- W4293318869 hasConcept C193809577 @default.
- W4293318869 hasConcept C199360897 @default.
- W4293318869 hasConcept C206729178 @default.
- W4293318869 hasConcept C21547014 @default.
- W4293318869 hasConcept C2779343474 @default.
- W4293318869 hasConcept C41008148 @default.
- W4293318869 hasConcept C41291067 @default.
- W4293318869 hasConcept C42475967 @default.
- W4293318869 hasConcept C86803240 @default.
- W4293318869 hasConceptScore W4293318869C109747225 @default.
- W4293318869 hasConceptScore W4293318869C114466953 @default.