FORECASTING OF SOLAR RADIATION FOR SOLAR SYSTEM UNDER DIFFERENT CLIMATIC CONDITION

Basit Öğe Kaydı
dc.contributor.authorAl Musawi, Sura Saadi
dc.contributor.authorHamodat, Zaid Musaab
dc.contributor.authorBasheer, Ayman Ghassan
dc.date.accessioned2025-02-06T18:01:22Z
dc.date.available2025-02-06T18:01:22Z
dc.date.issued2023
dc.departmentAltınbaş Üniversitesien_US
dc.description.abstractSun oriented energy is a perfect, plentiful, and sustainable power source. The utilization of photovoltaic boards to produce power from sun-based energy is turning out to be more well known. Since sunlight-based energy is discontinuous, the produced power is variable. This vulnerability could be decreased by using energy stockpiling frameworks and exact sunlight-based power determining. The objective of this proposal is to carry out a sun-oriented figure module as a component of an improved Energy Management System (EMS). Measurable techniques, sky imagers, satellite imaging, and mathematical climate forecast are among the strategies examined (NWP). To meet EMS necessities, counterfeit brain organizations (ANNs), a subset of factual strategies, were picked as a forecast strategy. For the EMS to work appropriately, exact anticipating in the momentary expectation skyline is required. The expectation skyline is how much time coming down the line for which an expectation is required. Additionally, the paragraph mentions the Temporal Convolutional Network (TCN) architecture, which uses temporal convolutions to process sequential data and has shown promise for time-series analysis tasks. Albeit every one of the techniques referenced above give OK execution, TCN engineering gives additional promising outcomes. To enhance the accuracy of solar radiation predictions, the possibility of dividing the dataset into sub-datasets based on radiant and overcast weather conditions and implementing a dedicated prediction module for each sub-dataset is being investigated. The outcomes show that bunching the dataset further develops expectation exactness for all models. Besides, recreation results on datasets from various geological areas with fluctuating environment conditions show that forecast exactness is higher in regions with additional steady climate and bright days. © 2023, International Organization on 'Technical and Physical Problems of Engineering'. All rights reserved.en_US
dc.identifier.endpage277en_US
dc.identifier.issn2077-3528
dc.identifier.issue4en_US
dc.identifier.scopus2-s2.0-85183136506
dc.identifier.scopusqualityQ3en_US
dc.identifier.startpage270en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12939/5355
dc.identifier.volume15en_US
dc.indekslendigikaynakScopus
dc.language.isoenen_US
dc.publisherInternational Organization on 'Technical and Physical Problems of Engineering'en_US
dc.relation.ispartofInternational Journal on Technical and Physical Problems of Engineeringen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmzKA_Scopus_20250206
dc.subjectClimateen_US
dc.subjectMachine Learningen_US
dc.subjectSolar Energy Predictionsen_US
dc.subjectSolar Radiationen_US
dc.titleFORECASTING OF SOLAR RADIATION FOR SOLAR SYSTEM UNDER DIFFERENT CLIMATIC CONDITIONen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu