loading page

Assessing Deep Generative Models on Time-Series Network Data
  • +2
  • Muhammad Haris Naveed ,
  • Umair Hashmi ,
  • Nayab Tajved ,
  • Neha Sultan ,
  • Ali Imran
Muhammad Haris Naveed
Author Profile
Umair Hashmi
School of Electrical Engineering and Computer Science, School of Electrical Engineering and Computer Science

Corresponding Author:[email protected]

Author Profile
Nayab Tajved
Author Profile
Neha Sultan
Author Profile
Ali Imran
Author Profile


This paper explores whether Generative Adversarial Networks (GANs) can produce realistic network load data that can be utilized to train machine learning models in lieu of real data. In this regard, we evaluate the performance of three recent GAN architectures on the Telecom Italia data set across a set of qualitative and quantitative metrics. Our results show that GAN generated synthetic data is indeed similar to real data and forecasting models trained on this data achieve similar performance to those trained on real data.
2022Published in IEEE Access volume 10 on pages 64601-64617. 10.1109/ACCESS.2022.3177906