FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386534822> ?p ?o ?g. }

• W4386534822 endingPage "109810" @default.
• W4386534822 startingPage "109810" @default.
• W4386534822 abstract "Due to the ongoing sustainability drives, nanogrids (NGs) are getting attention. Despite its perceived advantages, NG's high load volatility poses a risk to the stability of the connected power network. This is exacerbated by the user's various energy usage behaviors and the uncertain nature of meteorological events, leading to difficulties in load prediction. If the NG shiftable load can be well predicted, the user may move it from peak to off-peak hours to reduce energy costs, but at the expense of comfort. Existing demand-side management models are predominantly focused on MGs with lesser volatile loads and available shiftable loads, and comfort is not well studied in these models. In addition, most NGs have either limited or no data about their shiftable loads’ operations. To address the above challenges, a comprehensive predictive demand-side management (PDSM) approach with two components is developed in this paper. The first component is to predict the day-ahead shiftable load where the Stacked-Long Short-Term Memory (SLSTM), Artificial Neural Network (ANN), and Shiftable Equipment Matrix (SEM) modules are integrated. The SLSTM module predicts day-ahead load variations (%) using load time series data which is segregated by the percentile-based method. The ANN module with dynamic feature selection predicts day-ahead load (kW) using k-means based on historical meteorological and load data. The SEM module derives the average percentage shiftable equipment load using electric data from neighboring NGs. The second component is user-centric multi-objective optimization through load shifting. A user-centric Mixed Integer Quadratic Programming optimization model is developed to shift the predicted shiftable load to minimize the energy cost and discomfort for the user. Results show that the SLSTM predicts variations with R2 of 97.6%, MAPE of 9.7%, and MSE of 0.0274% and the integrated approach predicts shiftable load with R2 of 95.84%. In addition, daily energy costs can be saved up to 5.17% through user-centric multi-objective optimization." @default.
• W4386534822 created "2023-09-09" @default.
• W4386534822 creator A5001651510 @default.
• W4386534822 creator A5076463582 @default.
• W4386534822 date "2023-12-01" @default.
• W4386534822 modified "2023-10-16" @default.
• W4386534822 title "User-centric predictive demand-side management for nanogrids via machine learning and multi-objective optimization" @default.
• W4386534822 cites W1971473054 @default.
• W4386534822 cites W2002522387 @default.
• W4386534822 cites W2062582534 @default.
• W4386534822 cites W2100294654 @default.
• W4386534822 cites W2543710792 @default.
• W4386534822 cites W2782410986 @default.
• W4386534822 cites W2783175590 @default.
• W4386534822 cites W2808554454 @default.
• W4386534822 cites W2810793652 @default.
• W4386534822 cites W2883310506 @default.
• W4386534822 cites W2893381612 @default.
• W4386534822 cites W2920048877 @default.
• W4386534822 cites W2943207293 @default.
• W4386534822 cites W2966459372 @default.
• W4386534822 cites W2988496442 @default.
• W4386534822 cites W2990877300 @default.
• W4386534822 cites W3011858035 @default.
• W4386534822 cites W3023335632 @default.
• W4386534822 cites W3081576544 @default.
• W4386534822 cites W3120459600 @default.
• W4386534822 cites W3129535257 @default.
• W4386534822 cites W3132877612 @default.
• W4386534822 cites W3134346520 @default.
• W4386534822 cites W3139810680 @default.
• W4386534822 cites W3173236616 @default.
• W4386534822 cites W3198029030 @default.
• W4386534822 cites W3205101400 @default.
• W4386534822 cites W4200152811 @default.
• W4386534822 cites W4206919553 @default.
• W4386534822 cites W4224544514 @default.
• W4386534822 cites W4229016095 @default.
• W4386534822 cites W4280631645 @default.
• W4386534822 cites W4282580395 @default.
• W4386534822 cites W4285795677 @default.
• W4386534822 cites W4295796174 @default.
• W4386534822 cites W4308719015 @default.
• W4386534822 cites W4310691170 @default.
• W4386534822 cites W4323044599 @default.
• W4386534822 cites W4378841640 @default.
• W4386534822 doi "https://doi.org/10.1016/j.epsr.2023.109810" @default.
• W4386534822 hasPublicationYear "2023" @default.
• W4386534822 type Work @default.
• W4386534822 citedByCount "0" @default.
• W4386534822 crossrefType "journal-article" @default.
• W4386534822 hasAuthorship W4386534822A5001651510 @default.
• W4386534822 hasAuthorship W4386534822A5076463582 @default.
• W4386534822 hasConcept C105795698 @default.
• W4386534822 hasConcept C119599485 @default.
• W4386534822 hasConcept C119857082 @default.
• W4386534822 hasConcept C127413603 @default.
• W4386534822 hasConcept C138959212 @default.
• W4386534822 hasConcept C147940328 @default.
• W4386534822 hasConcept C149782125 @default.
• W4386534822 hasConcept C154945302 @default.
• W4386534822 hasConcept C162324750 @default.
• W4386534822 hasConcept C175444787 @default.
• W4386534822 hasConcept C186370098 @default.
• W4386534822 hasConcept C187691185 @default.
• W4386534822 hasConcept C200601418 @default.
• W4386534822 hasConcept C206658404 @default.
• W4386534822 hasConcept C2524010 @default.
• W4386534822 hasConcept C2777908891 @default.
• W4386534822 hasConcept C2779370713 @default.
• W4386534822 hasConcept C3020254827 @default.
• W4386534822 hasConcept C33923547 @default.
• W4386534822 hasConcept C41008148 @default.
• W4386534822 hasConcept C50644808 @default.
• W4386534822 hasConcept C7817414 @default.
• W4386534822 hasConcept C91602232 @default.
• W4386534822 hasConceptScore W4386534822C105795698 @default.
• W4386534822 hasConceptScore W4386534822C119599485 @default.
• W4386534822 hasConceptScore W4386534822C119857082 @default.
• W4386534822 hasConceptScore W4386534822C127413603 @default.
• W4386534822 hasConceptScore W4386534822C138959212 @default.
• W4386534822 hasConceptScore W4386534822C147940328 @default.
• W4386534822 hasConceptScore W4386534822C149782125 @default.
• W4386534822 hasConceptScore W4386534822C154945302 @default.
• W4386534822 hasConceptScore W4386534822C162324750 @default.
• W4386534822 hasConceptScore W4386534822C175444787 @default.
• W4386534822 hasConceptScore W4386534822C186370098 @default.
• W4386534822 hasConceptScore W4386534822C187691185 @default.
• W4386534822 hasConceptScore W4386534822C200601418 @default.
• W4386534822 hasConceptScore W4386534822C206658404 @default.
• W4386534822 hasConceptScore W4386534822C2524010 @default.
• W4386534822 hasConceptScore W4386534822C2777908891 @default.
• W4386534822 hasConceptScore W4386534822C2779370713 @default.
• W4386534822 hasConceptScore W4386534822C3020254827 @default.
• W4386534822 hasConceptScore W4386534822C33923547 @default.
• W4386534822 hasConceptScore W4386534822C41008148 @default.
• W4386534822 hasConceptScore W4386534822C50644808 @default.
• W4386534822 hasConceptScore W4386534822C7817414 @default.

• next