Changing schedule based on Artificial Neural Network using values from energy plus

edit

Hi @mechyai,

thank you so much for replying. I spend last two weeks trying to understand EMS python API and it is still super hard to understand it.

I found that using plugin method 'EnergyPlusPlugin' might be easier for a beginner like me. Is it possible to do all the process like sensing, reading ANN models and actuating using the python plugin mode?

thanks..

@prp92 I am not sure as I have only used used EnergyPlus as a "library" with the Python EMS API, not Python as a plugin in EnergyPlus. I made this workflow decision a while ago so I don't remember all my motivations, but I think I remember choosing running E+ as a library in Python because of the ability to keep my namespace (for instance NN model params) in Python for the longevity of the simulation and Python script. If I remember correctly, Python plugin's namespace only persist within the individual call, you would have to read/write your NN model params at each call.

@prp92, also I believe if using Python as a plugin you have to bottle your ENTIRE Python workflow into the single plugin script. When using EnergyPlus as a library in Python, I can have a normal programming workflow, say with a bunch of PyTorch NN stuff, in Python, then only pass EnergyPlus specific things via a callback function at specific calling points. If I take an OOP approach in Python, I can pass a whole slew of variables and objects (.ie NN models, etc.) into EnergyPlus, preserving namespace inside and outside E+ for the entire simulation run period.

@prp92 using E+ as a library in Python with the EMS Python API should make sense once you understand how to pass callback functions and calling points. The callback function is the single piece of Python code that gets passed to E+ at runtime, the calling point is specifically when this happens.

@prp92 see @jmarrec great notebook at "Run EnergyPlus in API mode" to see examples of how to use E+ as a library/API

@mechyai The above link is great. Thank you so much for helping me out..

@mechyai I can now import values from zone temperature and outdoor temperature and pass it into my ANN model. I can also get the output from my model. Now, I want to input my value into the actuator. I can see that first I have to define actuator handle and then pass this handle to the get_actuator_value() function. But the problem is, I cannot see where I can enter the results from my ANN model. Is it possible to give ANN output to the actuator? Thanks..

@prp92 Great. You need to use set_actuator_value function to change values for a given timestep / calling point. You input your actuator handle and value

@mechyai I used set_actuator_value and tried to run it. It is giving me following error.

* Severe * Data Exchange API: index error in setActuatorValue; received handle: -1

This means that there is something wrong with my actuator handle. Since my objective is to control Window open/close values using Eplus natural ventilation, I tried to use following syntax.

sch_handle = api.exchange.get_actuator_handle(state, "Zone Ventilation Wind And Stack Open Area", "Opening Area Fraction Schedule Name", "LIV1XWIN_SCH")

I am confused about how to solve this actuator handle issue.

@mechyai

I am particularly confused with actuator_key part of the handle. I set actuator_key as already existing dummy schedule named 'LIV1XWIN_SCH'. Actuator should replace this with the value from ANN model.

Thank you so much for helping me out..

@prp92 here is a link to a similar question I asked on this topic. First you need to see if what you are trying to actuate is an available actuator, look in the .edd file in the output for list of available actuators

@mechyai I tried to see the actuator details using the link you posted earlier. I found the following.

EnergyManagementSystem:Actuator Available,LIV1XWIN_SCH,Schedule:Compact,Schedule Value,[ ]

But this does not have the information about the actuator_key part.