Abstract

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.

Highlights

  • Wireless networks are characterized by complex features, such as signal properties, channel quality, and frequency bands [1]

  • Recent years have witnessed the application of several deep learning models in this area, we focus our attention on generative adversarial networks (GANs)-based models, and we refer the reader to the existing literature [3, 29] for a survey of deep learning models in mobile and Wi-Fi networks

  • The Wasserstein GAN (WGAN) was chosen as the final model because it seemed slightly better in the descriptive analysis, at least in the interpretation of the domain experts

Read more

Summary

Introduction

Wireless networks are characterized by complex features, such as signal properties, channel quality, and frequency bands [1]. Communication performance depends on several factors, including resource allocation, queue management, and congestion control. To handle this complex scenario, machine learning techniques have been widely used in the area of wireless networks [2]. Generative adversarial networks for Wi-Fi signal quality many CPEs are dual-band and give the user the possibility of choosing between the two frequency bands: 2.4 GHz or 5 GHz. The main difference between these two frequency bands is the range and bandwidth that they provide. A band of 2.4 GHz has a bigger Wi-Fi coverage, whereas a 5 GHz band has a faster speed

Objectives
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call