Getting Started

  1. Setup Configuration

Customize the dc_config_dc<N>.json file (where N=1,2,.. represent the data center identifier) to specify the environment settings for each of the data centers. To learn more about the DC parameters you can customize, check Data Center Configuration File

  1. Environment Configuration

The main environment for wrapping the environments is hierarchical_env.py, which reads configurations from the EnvConfig class and manages the external data sources for each of the data centers using managers for weather, carbon intensity, and workload. For instructions how to customize the enviroment configuration, check Main Configuration Files

  1. Train Example:

To run a basic experiment, use the following command:

python train_truly_hierarchical.py

This will start a simulation with the default configuration. The results will be saved in results/ output directory.

  1. Running in background mode

If you want to run the Green-DCC framework in background mode use:

nohup python PYTHON_SCRIPT > OUTPUT_FILE.txt  &

where PYTHON_SCRIPT is the script you want to run (e.g., train_truly_hierarchical.py) and OUTPUT_FILE is the name of the file that will contain the output (e.g. latest_experiment_output)

  1. Monitor the results

To visualize the experiments while they are running, you can launch TensorBoard. Open a new terminal, navigate to the “code”results/ directory, and run the following command:

Example:

tensorboard --logdir ./test

This will start a TensorBoard server, and you can view the experiment visualizations by opening a web browser and navigating to http://localhost:6006