openmodelica-microgrid-gym

OpenModelica Microgrid Gym

https://github.com/upb-lea/openmodelica-microgrid-gym/raw/develop/docs/pictures/omg_flow.png

The OpenModelica Microgrid Gym (OMG) package is a software toolbox for the simulation and control optimization of microgrids based on energy conversion by power electronic converters.

The main characteristics of the toolbox are the plug-and-play grid design and simulation in OpenModelica as well as the ready-to-go approach of intuitive reinfrocement learning (RL) approaches through a Python interface.

The OMG toolbox is built upon the OpenAI Gym environment definition framework. Therefore, the toolbox is specifically designed for running reinforcement learning algorithms to train agents controlling power electronic converters in microgrids. Nevertheless, also arbritary classical control approaches can be combined and tested using the OMG interface.

Free software: GNU General Public License v3
Documentation: https://upb-lea.github.io/openmodelica-microgrid-gym

Video Tutorial

Following is a short YouTube video introduction, to get a fist impression how to use OMG.

https://www.youtube.com/watch?v=rwBNFvCi_dY

Installation

Install Python Environment

This is the short installation guide for Windows and Linux. OpenModelica is hardly supported for Mac, they suggest to install in a Linux VM. For this reason, running OMG in a Linux VM is strongly recommended for Mac users!

Since it is not possible to install PyFMI, a package which is necessary for the communication between the python interface and the environment, via pip, we recommend to install this package in advance in a conda environment. As of now, only Windows and Linux are supported officially.

If conda is NOT installed on your PC, install miniconda for python 3.8
Create a new conda environment (e.g. in PyCharm)
Install PyFMI from the conda-forge channel in the terminal:
```
$ conda install -c conda-forge pyfmi
```
Install OpenModelica MicrogridGym from PyPI (recommended):
```
$ pip install openmodelica_microgrid_gym
```

Installation of OpenModelica

OMG was create by using OMEdit v1.16

In case of installation issues you can resort to their pre-built virtual machine.

Getting started

The environment is initialized and run like any other OpenAI Gym

import gym

if __name__ == '__main__':
    env = gym.make('openmodelica_microgrid_gym:ModelicaEnv-v1',
               max_episode_steps=None,
               net='../net/net.yaml',
               model_path='../omg_grid/grid.network.fmu')

    env.reset()
    for _ in range(1000):
        env.render()
        env.step(env.action_space.sample())  # take a random action
    env.close()

OMG uses the FMI standard for the exchange of the model between OpenModelica and Python.

An example network consisting out of two inverters, three filters and an inductive load.

https://github.com/upb-lea/openmodelica-microgrid-gym/raw/master/docs/pictures/omedit.jpg

You can either use one of the provided FMUs (Windows and Linux, 64-bit, both included in the grid.network.fmu) or create your own by running:

openmodelica_microgrid_gym\fmu> omc create_fmu.mos

Windows users might need to open the terminal out of OpenModelica by clicking ‘tools’ => ‘OpenModelica Command Prompt’ to make sure that the command ‘omc’ gets recognized.

Running the staticctrl.py starts a simulation with a manually tuned cascaded PIPI controller

https://github.com/upb-lea/openmodelica-microgrid-gym/raw/master/docs/pictures/control.jpg

A save Bayesian approach of a reinforcement learning agent is provided under examples/berkamkamp.py.

https://github.com/upb-lea/openmodelica-microgrid-gym/raw/master/docs/pictures/kp_kp_J.png

Using pytest

OMG provides a big range of tests to ensure correct working toolbox after changes are done. On some windows machines, the tests can only be started from the terminal via ‘pytest’.

The standard test OS for the development is Linux. In some cases, we have noticed that the test_modelica.py on windows PCs might throw an error. Since on Linux everything works fine, it seems to be a numerical issue connected with the FMUs.

Citation & white paper

Please find a white paper on the OMG toolbox including an exemplary usage scenario here:

https://arxiv.org/abs/2005.04869

Please use the following BibTeX entry for citing us:

@article{OMG-code2020,
    title = {OMG: A Scalable and Flexible Simulation and Testing Environment Toolbox for Intelligent Microgrid Control},
    author = {Stefan Heid and Daniel Weber and Henrik Bode and Eyke Hüllermeier and Oliver Wallscheid},
    year = {2020},
    doi = {10.21105/joss.02435},
    url = {https://doi.org/10.21105/joss.02435},
    publisher = {The Open Journal},
    volume = {5},
    number = {54},
    pages = {2435},
    journal = {Journal of Open Source Software}
}

@article{OMG-whitepaper2020,
    title={Towards a Scalable and Flexible Simulation and
           Testing Environment Toolbox for Intelligent Microgrid Control},
    author={Henrik Bode and Stefan Heid and Daniel Weber and Eyke Hüllermeier and Oliver Wallscheid},
    year={2020},
    eprint={http://arxiv.org/abs/2005.04869},
    archivePrefix={arXiv},
    primaryClass={eess.SY}
}

Contributing

Please refer to the contribution guide.

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.

History

0.4.0 (2021-04-07)

Changes

ModelicaEnv:
- Introduced action clipping
- model_params: None values are not passed to the OpenModelica env to allow initialization
- model_params: negative time values are introduced for initialization (fix)
- Introduced abort reward in env if episode is terminated
- Introduced obs_output to define a subset of history given as observation to the agent

Fix

omg.net.MasterInverter:
- default values used to overwrite passed values

Add

Random Process wrapper
ObsTempl test
reset test for initialized env

0.3.0 (2020-12-18)

API

ModelicaEnv:
- Uses Network
- __init__: - removed: timestep, model_output, model_input - added: network
- Delay buffer
Network and Components:
- Specify class structure using config file corresponding to fmu (see net-folder)
- added noise
SafeoptAgent:
- __init__: Performance parameters and calculation
aux_ctl.Contoller:
- __init__: timestep and undersampling changed
- added output clipping
Plotmanager

Examples

updated to changed API

Experiments

model validation:
- experiment files
- experiment environment managing testbench connection via SSH

Dependencies

Decreased Language Level to Python 3.7

0.2.0 (2020-05-27)

API

ModelicaEnv:
- reward function parameter
- vis_cols now also supports Plotting templates
EmptyHistory and descendant: update(), append()
Agent: added properties
StaticControlAgent and descendant: small changes in constructor params, specifically obs_template, added properties
SafeOptAgent: added properties
Runner: plotting can be disabled

Examples

added example for plotting

Performance

6.6× speedup

Dependencies

Increased Language Level to Python 3.8

0.1.3 (2020-05-13)

best parameter set output after termination of SafeOpt agent (#7)
proper action and observation space (#14)
resolved problem related to environment model_params (#21)

documentation improvements (more examples, installation)

0.1.2 (2020-05-04)

corrected pip install requirements

0.1.1 (2020-04-22)

First release on PyPI.

Release files for openmodelica-microgrid-gym 0.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for openmodelica-microgrid-gym 0.4.0
File	Size	Uploaded
openmodelica_microgrid_gym-0.4.0.tar.gz	1.7 MB	Feb 2, 2022	Details

Built distribution (wheel)

Table of built distributions (wheels) for openmodelica-microgrid-gym 0.4.0
File	Interpreter	ABI	Platform	Reset
openmodelica_microgrid_gym-0.4.0-py2.py3-none-any.whl 65.7 kB Feb 2, 2022	Python 2, Python 3	none	any	Details

Total release size: 1.8 MB

Release files / openmodelica_microgrid_gym-0.4.0.tar.gz

Download URL	openmodelica_microgrid_gym-0.4.0.tar.gz
Size	1.7 MB
Tags	Source
SHA-256 checksum How to use checksums	`53d4c00893ed2a70443e8e37c24b56d698f07433ca40f2b3ec5ab8f26264cb97`
BLAKE2b-256 checksum How to use checksums	`4f860cdce14188f96920116893f75ca436985cecf831db1824224370fdd52dd7`
Upload date	Feb 2, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.0.1 pkginfo/1.4.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.57.0 CPython/3.9.7`

Release files / openmodelica_microgrid_gym-0.4.0-py2.py3-none-any.whl

Download URL	openmodelica_microgrid_gym-0.4.0-py2.py3-none-any.whl
Size	65.7 kB
Tags	Python 2 Python 3
SHA-256 checksum How to use checksums	`c46f6594b0f2e39a701b62cfc40d13f1b4c33e58574fa504231b000d2035242d`
BLAKE2b-256 checksum How to use checksums	`6a1ff83093f4b52a79933664867f0fd1471ed44b9f8afec4b9f7642f4c9e64f9`
Upload date	Feb 2, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.0.1 pkginfo/1.4.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.57.0 CPython/3.9.7`