Comyx is a Python library for simulating wireless communication systems. It uses NumPy and SciPy for numerical computation, and Numba for just-in-time (JIT) compilation. It provides a number of features for simulating wireless communication systems:

• B5G Features: Supports a variety of B5G specific features, such as STAR-RIS, and NOMA.
• Channel Models: Provides the AWGN, Rayleigh, and Rician fading models.
• Signal Modulation: Supports a variety of modulation schemes, such as BPSK, QPSK, and QAM.
• Performance Metrics: Can calculate a variety of performance metrics, such as the sum rate, and outage probability.

To-Do

• Update documentation
• Add network optimization support
• Add Reinforcement Learning (RL) support

Installation

You can install the latest version of the package using pip:

pip install comyx

Note: It is recommended to create a new virtual environment so that updates/downgrades of packages do not break other projects.

Or you can clone the repository along with research code and perform an editable installation:

git clone https://github.com/muhd-umer/comyx.git
pip install -e .

Reinforcement Learning (RL) Support

For RL support, you will need to install the following dependencies:

• Install PyTorch (Stable)

  pip install torch torchvision torchaudio

• Install Ray RLlib

  pip install -U ray[default]  # core, dashboard, cluster launcher
  pip install -U ray[rllib]  # tune, rllib