tu-delft-ai-energy-lab / deep-statistical-solver-for-distribution-system-state-estimation Goto Github PK

Dear TU Delft AI Energy Lab researchers,

Thank you for your amazing paper and helpful open-source codes. That is so useful in reproducing the project. I encountered one issue on the input variables of the trained model.

For the trained model (such as the trained mode in the folder saved_model>> cigre_meas1_dss), the input variables are (a_flat,b_flat,U_flat,A0, training=False) (see line 1086 in the case_study.py), where the labeled variable, i.e., U_flat, is included as input when I use the trained model to perform DSSE. However, when I use the procedure to train a new model, the input variables of the trained model are (a_flat, b_flat, A0, training=False) (see line 901 in the fun_dss.py), where the labeled variable, i.e., U_flat, is NOT included as input when I test the trained model.

It is well known that when using a trained model for inference (making predictions on new data), we only need to provide the input features that the model was trained on. Including the labeled variables as inputs to the trained model would be unnecessary and redundant for making predictions. Hence, I am confused with the input of the trained model (provided by the authors). Why the labeled variables (i.e., U_flat) are included when using it for predicting.

Thank you for your response in advance.

Sincerely,
Gang

Dear TU Delft AI Energy Lab researchers,

Thanks very much for the amazing paper and code!

I have a question about the parameter to tweak load and generation in data_gen.py line 65, I don't know how to select the parameters to scale the load and gen profiles, and what's the usage of this parameter. Could you please briefly explain about it?

I met another problem with the load sampling section in data_gen.py, after executing the loop of generating the load and gen of 24 h profile, I noticed that the data for the 9-th gen (wind turbine) was a fixed value over the 24 hours.

I think the issue comes from line 314, the code makes all values of the raw 8 to be the same. After change it to load_sgen[i][8] = net.sgen['p_mw'][8] * profile_day_wind[i] *sgen_inc , the gen profile would vary over 24 h.

I'm looking forward to your reply, this means a lot to me, thanks again for the amazing work!