Zeros-MTL-CLDBN: A Robust Multitask Deep-Learning Framework via Deep-Belief Network with Correntropy Loss for Ultrashort-Term Multistep Wind Power Forecasting

dc.contributor.author	Ma, Wentao
dc.contributor.author	Dai, Jiahui
dc.contributor.author	Chen, Xi
dc.contributor.author	Dong, Yuzhuo
dc.date.accessioned	2026-08-20T11:18:35Z
dc.date.available	2026-08-20T11:18:35Z
dc.date.copyright	2026/04/27
dc.date.issued	2026
dc.identifier.other	JLEED9.EYENG-6260.pdf
dc.identifier.uri	http://yetl.yabesh.ir/yetl1/handle/yetl/4312008
dc.description.abstract	AbstractAccurate ultrashort-term multistep wind power forecasting (WPF) remains a critical challenge in renewable energy systems due to the inherent stochasticity, non-Gaussian fluctuations, and volatility of wind energy. To address this challenge, this ...
dc.publisher	American Society of Civil Engineers
dc.title	Zeros-MTL-CLDBN: A Robust Multitask Deep-Learning Framework via Deep-Belief Network with Correntropy Loss for Ultrashort-Term Multistep Wind Power Forecasting
dc.type	Journal Article
dc.journal.volume	152
dc.journal.issue	4
dc.journal.title	Journal of Energy Engineering
dc.identifier.doi	10.1061/JLEED9.EYENG-6260
dc.journal.fristpage	04026028-1
dc.journal.lastpage	04026028-15
dc.page	15
dc.tree	Journal of Energy Engineering:;2026:;Volume ( 152 ):;issue: 004
dc.contenttype	Fulltext