Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Get UK Target data #2

Open
Tracked by #5
peterdudfield opened this issue Dec 4, 2024 · 22 comments
Open
Tracked by #5

Get UK Target data #2

peterdudfield opened this issue Dec 4, 2024 · 22 comments

Comments

@peterdudfield
Copy link
Contributor

peterdudfield commented Dec 4, 2024

We would suggest using the UK PVlive national solar generation as target data. This can be retrieved by API and is fairly easy to use.

Context: At OCF we actually predict GSP level solar generation and use a small ML model to sum it up.

I suggest for this project we start simple, with just the UK national. Also note that the capacity changes, so we need to collect that too, which is possible via API above.

OCF might have a script for collecting this already, and can share.

We should think of a place where we can store the data publicly. Becasue its time series data, its shouldn't be too big

@peterdudfield peterdudfield changed the title Target data. I would suggest using the UK PVlive national solar generation as target data. This can be retrieved by API and is fairly easy to use. Context: At OCF we actually predict GSP level solar generation and use a small ML model to sum it up. I suggest for this project we start simple, with just the UK national. Also note that the capacity changes, so we need to collect that to, this is possible via API above. Get Target data Dec 4, 2024
@peterdudfield peterdudfield transferred this issue from openclimatefix/PVNet Dec 4, 2024
@jcamier
Copy link
Collaborator

jcamier commented Dec 7, 2024

@peterdudfield peterdudfield moved this to Todo in Open Data PVNet Dec 9, 2024
@peterdudfield
Copy link
Contributor Author

Potential data source: https://www.metoffice.gov.uk/services/data/met-office-data-for-reuse/discovery

yea this would be good for the NWP gridded data #3. For the target data we should use PVLive - https://www.solar.sheffield.ac.uk/pvlive/, they have an api and python package e.t.c

@jcamier
Copy link
Collaborator

jcamier commented Dec 18, 2024

Have you guys ever tried this API for PV predictions? I just found it today as I was researching our project...

https://joint-research-centre.ec.europa.eu/photovoltaic-geographical-information-system-pvgis/getting-started-pvgis/api-non-interactive-service_en

@peterdudfield
Copy link
Contributor Author

We have. script here https://github.com/openclimatefix/uk-pv-backtest/blob/main/scripts/get_pvlive_data.py, that should collect the PVLive data. This might need modifitying so it only collections National Solar generation, i.e gsp_id=0

@jcamier
Copy link
Collaborator

jcamier commented Dec 18, 2024

This is great. Do you want us to use this library then to get the target data and maybe extend it or use this as a baseline in for a specific utility function in open data PVNet?

@peterdudfield
Copy link
Contributor Author

Sorry, I'm not sure what you mean?

@jcamier
Copy link
Collaborator

jcamier commented Dec 19, 2024

There are two approaches we can take with open-data-pvnet:

  1. Extend the uk-pv-backtest repository:
  • We can enhance the features of the get_pvlive_data.py module or add a new module dedicated to collecting National Solar generation data.
  • The enhanced or new module would then be included as a dependency in open-data-pvnet.
  1. Develop directly within open-data-pvnet:
  • Create a new module within open-data-pvnet itself to handle the collection of National Solar generation data.
  • This keeps everything self-contained within open-data-pvnet.

@peterdudfield
Copy link
Contributor Author

I would go for 2. the uk-pv-bactest repo is what we use internal to generate our backtests and can change quite a lot.
I would pull this script into open-data-pvnet and develop / tidy it up there

@alirashidAR alirashidAR mentioned this issue Jan 7, 2025
6 tasks
@jcamier
Copy link
Collaborator

jcamier commented Jan 8, 2025

@alirashidAR I added a review comment on your PR.

@peterdudfield
Copy link
Contributor Author

Thanks @alirashidAR for doing the PR.
Would you like to collect the data too. We can then put it on an public s3 bucket ready for everyone to use

@alirashidAR
Copy link
Contributor

Thanks @alirashidAR for doing the PR. Would you like to collect the data too. We can then put it on an public s3 bucket ready for everyone to use

yes I would like to work on that . Thank you !

@alirashidAR
Copy link
Contributor

alirashidAR commented Jan 13, 2025

@peterdudfield
We would collect this data in the bucket and then create samples, right?
And what should the time frame of the collected data be?

@peterdudfield
Copy link
Contributor Author

2020 onwards? to be safe

@alirashidAR
Copy link
Contributor

The target data should be stored in which format ?

@peterdudfield
Copy link
Contributor Author

We tried in the past to stored it as netcdf file.

Just to note it would be good to get the power generation, and also the capacity. The capacity can be got from PVLive too. This changes in time, as more PV systems come online

@alirashidAR alirashidAR mentioned this issue Jan 13, 2025
5 tasks
@peterdudfield peterdudfield changed the title Get Target data Get UK Target data Jan 14, 2025
@sadavaidya
Copy link

Hello there,

I’m really interested in contributing to this project and would love to help with this issue of getting UK target data. Could you please confirm if this issue is still open and if there’s any existing work or specific guidelines I should be aware of before getting started?

I understand that @alirashidAR has already worked on a script to download the data in the required format using the Python API. I’d love to know how I can further contribute or build upon that work.

Looking forward to your guidance!

Best regards,
Sadashiv

@MAYANK12SHARMA
Copy link
Contributor

Hi @peterdudfield, is there anything left to do? I’d be happy to do it?

@jcamier
Copy link
Collaborator

jcamier commented Mar 2, 2025

@alirashidAR I believe you are almost done with this issue. Can you let @MAYANK12SHARMA @sadavaidya if there any assistance you may need?

@MAYANK12SHARMA
Copy link
Contributor

Hii @jcamier can you please take a moment for review the latest PR of mine for the issue #65

@MAYANK12SHARMA
Copy link
Contributor

@alirashidAR I believe you are almost done with this issue. Can you let @MAYANK12SHARMA @sadavaidya if there any assistance you may need?
Yes, @alirashidAR, please let me know if you need any assistance from my side.

@alirashidAR
Copy link
Contributor

Hey @MAYANK12SHARMA @sadavaidya, this issue is almost complete. Thank you, but there isn't much left to work on right now.

@sadavaidya
Copy link

Thank you @alirashidAR , for letting us know. I will see if I can contribute to any other issue.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Todo
Development

No branches or pull requests

5 participants