An interpretable hybrid spatiotemporal fusion method for ultra-short-term photovoltaic power prediction

[Display omitted] •APSTFNet combines spatial modules for sequences. Temporal network merges BiLSTM and self-attention.•DAWCHOA optimizes APSTFNet's hyperparameters, enhancing its performance significantly.•Interpretability framework explains deep learning predictions; DAWCHOA-APSTFNet excels in...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) 2024-11, Vol.308, p.132969, Article 132969
Main Authors: Gong, Bin, An, Aimin, Shi, Yaoke, Guan, Haijiao, Jia, Wenchao, Yang, Fazhi
Format: Article
Language:English
Subjects:
Adaptive parallel spatiotemporal fusion network
Deep learning interpretability
Hyperparameter group optimization
PV systems
Ultra-short-term power prediction
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:[Display omitted] •APSTFNet combines spatial modules for sequences. Temporal network merges BiLSTM and self-attention.•DAWCHOA optimizes APSTFNet's hyperparameters, enhancing its performance significantly.•Interpretability framework explains deep learning predictions; DAWCHOA-APSTFNet excels in PV systems.
ISSN:0360-5442
DOI:10.1016/j.energy.2024.132969