Site Forecast App

Runs forecasts for renewable generation sites, currently just uses PVnet based models but this may change in the future, saves results to a DB.

The model

The ML models are from PVnet and uses ocf_data_sampler for the data processing We use NWP data such as ECMWF's IFS forecast and live generation values as input, to predict up to 48 hours into the future.

PV

We are currently running a Netherlands solar model. The configuration is stored here

We are also running an India sites solar model.

Adjuster

A post-processing adjustment method is used to correct systemic biases in the forecast see the adjuster for more detail.

Environment variables

The following environment variables are required to run the app:

• DB_URL: The database connection string to connect to the database
• NWP_ECMWF_ZARR_PATH: The path to the ECWMF NWP zarr file, this can be a local path or a remote path
• NWP_MO_GLOBAL_ZARR_PATH: The path to the Met Office NWP zarr file, this can be a local path or a remote path
• SATELLITE_ZARR_PATH: The path to the satellite zarr file, this can be a local path or a remote path
• SAVE_BATCHES_DIR: The directory to save the batches to, this is required to save the batches of data that are processed by the app- SAVE_BATCHES_DIR: The directory to save the batches to, this is required to save the batches of data that are processed by the app
• HUGGINGFACE_TOKEN: Token used for private models
• COUNTRY: Can be nl for Netherlands, or india for India.
• CLIENT_NAME: The name of the client, this is used to the sites that should be run
• SATELLITE_SCALE_FACTOR: The scale factor for the satellite data. Defaults to 1023
• SATELLITE_BACKUP_ZARR_PATH: Back up satellite data source. Defaults to None

Here are some temporary ones

• MO_GLOBAL_SCALE_CLOUDS: The scale factor for the Met Office global clouds, this is used to scale the clouds in the Met Office NWP data
• MO_GLOBAL_ZERO_TOTAL_CLOUD_COVER: Whether to set the total cloud cover to zero in the Met Office global NWP data, this is used to set the total cloud cover to zero in the Met Office global NWP data

Linting and formatting

Lint with:

make lint

Format code with:

make format

Running tests

make test

⚠️ Note: one test for the AD model is skipped locally unless the HF token is set, this HF token can be found in AWS Secret Manager under {environment}/huggingface/token and then can be set via export HUGGINGFACE_TOKEN={token_value} in the repo to run the additional test. In CI tests this secret is set so the test will run there.

Running the app locally

Replace {DB_URL} with a postgres DB connection string (see below for setting up a ephemeral local DB)

If testing on a local DB, you may use the following script to seed the the DB with a dummy user, site and site_group.

DB_URL={DB_URL} poetry run seeder

⚠️ Note this is a destructive script and will drop all tables before recreating them to ensure a clean slate. DO NOT RUN IN PRODUCTION ENVIRONMENTS

This example runs the application and writes the results to stdout

DB_URL={DB_URL} NWP_ZARR_PATH={NWP_ZARR_PATH} poetry run app

To save batches, you need to set the SAVE_BATCHES_DIR environment variable to directory.

### Starting a local database using docker

```bash
    docker run \
        -it --rm \
        -e POSTGRES_USER=postgres \
        -e POSTGRES_PASSWORD=postgres \
        -p 54545:5432 postgres:14-alpine \
        postgres

The corresponding DB_URL will be

postgresql://postgres:postgres@localhost:54545/postgres

Building and running in Docker

Build the Docker image

make docker.build

Create a container from the image. This example runs the application and writes the results to stdout.
Replace {DB_URL} with a postgres DB connection string.
N.B if the database host is localhost on the host machine, replace localhost with host.docker.internal so that docker can access the database from within the container

docker run -it --rm -e DB_URL={DB_URL} -e NWP_ZARR_PATH={NWP_ZARR_PATH} ocf/india-forecast-app

Notes

This repo makes use of PyTorch (torch and torchvision packages) CPU-only version. In order to support installing PyTorch via poetry for various environments, we specify the exact wheels for each environment in the pyproject.toml file. Some background reading on why this is required can be found here: https://santiagovelez.substack.com/p/how-to-install-torch-cpu-in-poetry?utm_campaign=post&utm_medium=web&triedRedirect=true

Troubleshooting

Docker Database Connection Issues

Problem: Container can't connect to local database with "connection refused" error Solution: If using localhost in your DB_URL, replace it with host.docker.internal when running in Docker

Problem: Database authentication failures Solution: Verify your DB_URL format is correct: postgresql://username:password@hostname:port/database

Model Loading Issues

Problem: Out of memory errors when loading models Solution: Ensure your system has sufficient RAM, or consider using a smaller model variant.