Update to newer PVNet

[jacobbieker]

This PVNet has changes such as 0.1 training data, ECMWF mean and stddev, and 7 hour delay in NWP data, so should be more consistent

Pull Request

Description

This fixes issues with training of PVNet for India v0, matching the training data more closely with the live data, and updating the normalization.

Fixes #

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

• [ ] Yes

If your changes affect data processing, have you plotted any changes? i.e. have you done a quick sanity check?

• [ ] Yes

Checklist:

• [ ] My code follows OCF's coding style guidelines
• [ ] I have performed a self-review of my own code
• [ ] I have made corresponding changes to the documentation
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] I have checked my code and corrected any misspellings

[peterdudfield]

I think it would be good to not merge this until the test is passing