Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction

Sadman Sakib; Mahin Khan Mahadi; Samiur Rashid Abir; Al-Muzadded Moon; Ahmad Shafiullah; Sanjida Ali; Fahim Faisal; Mirza Muntasir Nishat

doi:10.1016/j.heliyon.2024.e27795

March 1, 2024HeliyonOpen Access

Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction

View Full Paper

Ask AI

Bookmark

Share

Key Points

Temporal Fusion Transformer architectures achieve superior multi-step solar irradiation prediction accuracy and robustness, outperforming standard attention models across long sequences.
Model evaluations predict over 24 steps ahead at 30-minute intervals, yielding lower mean square error and mean absolute error across fluctuating meteorological time series.
Analysis of multivariate time series from subtropical sites validates deep attention architectures, supporting enhanced supply balancing in grid-connected photovoltaic systems.

No abstract yet

We only have this paper's title and publication details.

Read it at the source

Implication

Comparative analysis reveals superior multi-step solar irradiance forecasting with temporal fusion transformers in grid-connected systems, highlighting improved photovoltaic power management.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Sakib et al. (2024) studied this question.

synapsesocial.com/papers/68e761b8b6db6435876d7b46 https://doi.org/10.1016/j.heliyon.2024.e27795

View Full Paper

Ask AI

Bookmark

Share

Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction

Key Points

No abstract yet

Implication

Discussion

Cite This Study

Attention-Based Models for Multivariate Time Series Forecasting: Multi-step Solar Irradiation Prediction

Key Points

No abstract yet

Implication

Discussion

Cite This Study

Keep reading

More related papers

More from Heliyon

Keep reading

More related papers

More from Heliyon