July 28, 2024Renewable EnergyOpen Access

Hybrid model for intra-day probabilistic PV power forecast

View Full Paper

Ask AI

Bookmark

Authors

JTJayesh ThakerCarl von Ossietzky Universität Oldenburg RHRobert HöllerUniversity of Applied Sciences Upper Austria

Discussion

Member takes

Implication

Comparative analysis demonstrates accurate intra-day power predictions across fixed and tracking photovoltaic plants, highlighting improved uncertainty estimation for grid management.

Key Points

A machine learning hybrid model demonstrates superior intra-day photovoltaic power prediction across 1 to 6 h horizons, outperforming conventional single-method approaches.
Assessment of fixed and single axis tracking PV systems uses model output statistics combined with post-processing Kalman filter techniques to refine multi-parameter solar forecasts.
Highlights the utility of probabilistic forecasting to quantify solar irradiance uncertainty, which may enable more reliable grid dispatching and integration for regional networks.

Cite This Study

Thaker et al. (2024) studied this question.

synapsesocial.com/papers/68e5ec3cb6db643587580bed https://doi.org/10.1016/j.renene.2024.121057

View Full Paper

Ask AI

Bookmark

Implication

Comparative analysis demonstrates accurate intra-day power predictions across fixed and tracking photovoltaic plants, highlighting improved uncertainty estimation for grid management.

Hybrid model for intra-day probabilistic PV power forecast

Discussion

Member takes

Implication

Key Points

Cite This Study

Hybrid model for intra-day probabilistic PV power forecast

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider