Show simple item record

dc.contributor.authorDairi, Abdelkader
dc.contributor.authorHarrou, Fouzi
dc.contributor.authorSun, Ying
dc.date.accessioned2021-10-13T11:54:37Z
dc.date.available2021-10-13T11:54:37Z
dc.date.issued2021-10-11
dc.identifier.citationDairi, A., Harrou, F., & Sun, Y. (2021). A deep attention-driven model to forecast solar irradiance. 2021 IEEE 19th International Conference on Industrial Informatics (INDIN). doi:10.1109/indin45523.2021.9557405
dc.identifier.isbn978-1-7281-4396-5
dc.identifier.doi10.1109/INDIN45523.2021.9557405
dc.identifier.urihttp://hdl.handle.net/10754/672827
dc.description.abstractAccurately forecasting solar irradiance is indispensable in optimally managing and designing photovoltaic systems. It enables the efficient integration of photovoltaic systems in the smart grid. This paper introduces an innovative deep attention-driven model for solar irradiance forecasting. Notably, an extended version of the variational autoencoder (VAE) is introduced by amalgamating the desirable characteristics of the bidirectional LSTM (BiLSTM) and attention mechanism with the VAE model. Specifically, the introduced approach enables the conventional VAE’s ability to model temporal dependencies by incorporating BiLSTM at the VAE’s encoder side to better extract and learn temporal dependencies embed on the solar irradiance concentration measurements. In addition, the self-attention mechanism is embedded in the VAE’s encoder side following the BiLSTM to highlight pertinent features. The performance of the proposed model is evaluated through comparisons with the recurrent neural network (RNN), gated recurrent unit (GRU), LSTM, and BiLSTM. Measurements of solar irradiance in the US and Turkey are used to evaluate the investigated models. Results confirm the superior performance of the proposed model for solar irradiance forecasting over the other models (i.e., RNN, GRU, LSTM, and BiLSTM).
dc.publisherIEEE
dc.relation.urlhttps://ieeexplore.ieee.org/document/9557405/
dc.relation.urlhttps://ieeexplore.ieee.org/document/9557405/
dc.relation.urlhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9557405
dc.rightsArchived with thanks to IEEE
dc.subjectVariational auto encoder
dc.subjectself-attention
dc.subjectsolar irradiation
dc.subjectforecasting
dc.subjectbidirectional recurrent neural network
dc.titleA deep attention-driven model to forecast solar irradiance
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentStatistics Program
dc.conference.date21-23 July 2021
dc.conference.name2021 IEEE 19th International Conference on Industrial Informatics (INDIN)
dc.conference.locationPalma de Mallorca, Spain
dc.eprint.versionPost-print
dc.contributor.institutionUniversity of Science and Technology of Oran-Mohamed Boudiaf (USTO-MB),Computer Science department Signal, image and speech laboratory (SIMPA) laboratory,Oran,Algeria,31000
kaust.personHarrou, Fouzi
kaust.personSun, Ying
refterms.dateFOA2021-10-13T12:03:20Z
dc.date.published-online2021-10-11
dc.date.published-print2021-07-21


Files in this item

Thumbnail
Name:
003964.pdf
Size:
735.0Kb
Format:
PDF
Description:
Accepted manuscript

This item appears in the following Collection(s)

Show simple item record