David

> Is that ConvergenceWarning significant? It could be just one training iteration that did not converge, also we are doing a grid search to find the best parameters, so it...

I'll close this as complete. We can discuss the ongoing tests on the discord or in the discussion section.

Closing this specific issue. Feel free to open another one if needed.

> Continuing to be an issue, p_nom is 115200, but with an end_timestep constraint it allocates forecast power levels above p_nom. So you see this problem when using the `end_timestep`...

Hi, thanks for working on this. Two quick comments. The name of the new control variable is `load_sensor_kw` but it applies to both the load power and the PV power....

> The name of the new control variable is `load_sensor_kw` but it applies to both the load power and the PV power. That is confusing and not generalized, for example...

Unit tests are failing. This doesn't seem ready yet?

> Hello David, apologies I am not used to working with GitHub or pull request etiquette. Should I undo the pull request until it is clean and ready to go?...

Closing for now with the proposed delay solution. Re-open if needed

Hi, this is complete. You may find the `sensor.total_cost_fun_value` published after a data publish call.