openclimatefix-models/pvnet_nl

PVNet Netherlands

Model Description

This model uses only pv data to predict regional production of solar power in Netherlands. Predictions are done with 15 minutely resolution from 15 minutes to 36 hours ahead.

• Developed by: openclimatefix
• Model type: Fusion model
• Language(s) (NLP): en
• License: mit

Training Details

Data

This model was trained on data from 2019-2023 and validated on data from 2024. See the data_config.yaml file for more information on the channels and window-size used for each input data source.

Preprocessing

Data is prepared with the ocf_data_sampler/torch_datasets/datasets/pvnet_uk Dataset [2].

Results

The training logs for this model commit can be found here:

• https://wandb.ai/openclimatefix/NL-Solar/runs/rznhezbg

Hardware

Trained on a single NVIDIA Tesla T4

Software

This model was trained using the following Open Climate Fix packages:

• [1] https://github.com/openclimatefix/PVNet
• [2] https://github.com/openclimatefix/ocf-data-sampler

The versions of these packages can be found below:

• pvnet==5.3.4.post9+git.1e92e543.dirty
• ocf-data-sampler==1.0.6