A Conditional Generative Adversarial Network Based Approach for Network Slicing in Heterogeneous Vehicular Networks

Farnoush Falahatraftar,Steven Chamberland,Samuel Pierre

doi:10.3390/telecom2010009

Farnoush Falahatraftar, Steven Chamberland + Show 1 more

Open Access

https://doi.org/10.3390/telecom2010009

Copy DOI

Journal: Telecom	Publication Date: Mar 18, 2021
Citations: 2	License type: CC BY 4.0

Affiliation: Polytechnique Montréal

Abstract

Heterogeneous Vehicular Network (HetVNET) is a highly dynamic type of network that changes very quickly. Regarding this feature of HetVNETs and the emerging notion of network slicing in 5G technology, we propose a hybrid intelligent Software-Defined Network (SDN) and Network Functions Virtualization (NFV) based architecture. In this paper, we apply Conditional Generative Adversarial Network (CGAN) to augment the information of successful network scenarios that are related to network congestion and dynamicity. The results show that the proposed CGAN can be trained in order to generate valuable data. The generated data are similar to the real data and they can be used in blueprints of HetVNET slices.

Highlights

The vision of having a central, robust, and intelligent network management can be achieved by taking advantages of learning algorithms in the control layer of SoftwareDefined Network (SDN)
On the basis of the research question and the direct relation between the congestion problem and the resource allocation problem, we propose a novel method that is based on Deep Learning and network slicing technique with the aim of avoiding congestion in Heterogeneous Vehicular Network (HetVNET)
We proposed an intelligent hybrid Conditional Generative Adversarial Network (CGAN)-SDN architecture for network slicing, while considering the network congestion problem in HetVNET

Summary

Introduction

The vision of having a central, robust, and intelligent network management can be achieved by taking advantages of learning algorithms in the control layer of SoftwareDefined Network (SDN). If we have a very dynamic network, like HetVNET, it may be a novel idea to propose a method that can provide network resources and requirements quickly and dynamically based on network templates These templates can be used to dynamically create the HetVNET slices. To the best of our knowledge, in the current scientific works that are related to vehicular networks, there is a lack of an intelligent SDN-NFV based architecture that could provide network templates in HetVNET environment using computing power of fog objects. We will show how the proposed CGAN helps us to intelligently and reliably generate valuable information in order to create network slices with the aim of avoiding congestion in HetVNET. It is the first time that CGAN has been applied in this context to the best of our knowledge

Related Work

Generating Dataset Using Simulation Scenarios

Proposing CGAN Model for HetVNET

A Hybrid CGAN-SDN Architecture

The Proposed CGAN Model Performance Evaluation

Findings

Conclusions