DeepSlice - 5G Network Slicing

DeepSlice is a project focused on implementing and analyzing 5G network slicing using advanced machine learning techniques. Network slicing is a key feature of 5G networks, enabling the creation of multiple virtual networks on a shared physical infrastructure. This project aims to explore the potential of network slicing to optimize resource allocation and improve network performance.

Dataset

The dataset used in this project can be found here. It contains data relevant to 5G network slicing, including traffic patterns, resource usage, and performance metrics.

Certificate

A certificate related to this project is available here.

Paper

Paper on [DeepSlice: A Deep Learning Approach towards an Efficient and Reliable Network Slicing in 5G Networks] (https://ieeexplore.ieee.org/document/8993066)

Features

• Implementation of machine learning models for network slicing.
• Analysis of 5G network performance metrics.
• Optimization of resource allocation using slicing techniques.

Prerequisites

• Python 3.12
• Jupyter Notebook
• Required Python libraries (see requirements.txt or install directly in the provided environment).

Setup Instructions

1. Clone the repository:

   git clone <repository-url>

2. Navigate to the project directory:

   cd DeepSlice_5G_network_model

3. Activate the virtual environment(on windows):

   .\<your-environment>\Scripts\Activate.ps1

4. Install the required dependencies:

   pip install -r requirements.txt

5. Open the Jupyter Notebook:

   jupyter notebook

6. Run the DeepSlice.ipynb notebook to execute the project.

Project Structure

• DeepSlice.ipynb: Main Jupyter Notebook containing the implementation.
• filtereddata.txt: Preprocessed data used in the project.
• README.md: Project documentation.

Acknowledgments

• Kaggle for providing the dataset.
• Contributors and collaborators for their support.

---

Feel free to contribute to this project by submitting issues or pull requests.