Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models

Recently, transformer-based learning models have shown promising results in network traffic prediction across various contexts. However, their potential in Mobile Edge Computing (MEC) environments remains largely unexplored, despite the unique requirements of MEC such as low latency and high-bandwid...

Full description

Saved in:
Bibliographic Details
Main Authors: Ravi Shankar Shukla, Abdulrahman M. Alatawi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11002480/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132079500591104
author Ravi Shankar Shukla
Abdulrahman M. Alatawi
author_facet Ravi Shankar Shukla
Abdulrahman M. Alatawi
author_sort Ravi Shankar Shukla
collection DOAJ
description Recently, transformer-based learning models have shown promising results in network traffic prediction across various contexts. However, their potential in Mobile Edge Computing (MEC) environments remains largely unexplored, despite the unique requirements of MEC such as low latency and high-bandwidth communication between end-users and edge servers. This study evaluates the performance of four transformer-based learning models for Internet traffic prediction in MEC environments, comparing them against state-of-the-art models using a real-world dataset from publicly available mobile operator networks. Performance is assessed using mean squared error (MSE) and mean absolute error (MAE) as evaluation metrics. Our experiments demonstrate that the proposed GAN-based transformer model, referred to as 5GT-GAN-Trans, achieves an MSE of 0.428 and an MAE of 0.441, considerably outperforming baseline models such as FED-Former-F (MSE: 0.791, MAE: 0.606), FED-Former-W (MSE: 0.622, MAE: 0.508), Informer (MSE: 0.814, MAE: 0.649), and a standard Transformer model (MSE: 0.803, MAE: 0.640). These numerical improvements underscore the efficacy of transformer-based models for precise Internet traffic forecasting in MEC environments, offering valuable insights for improved network management and enhanced user experience.
format Article
id doaj-art-321ce570dd7c4f91a9e063a1ce502e01
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-321ce570dd7c4f91a9e063a1ce502e012025-08-20T02:32:16ZengIEEEIEEE Access2169-35362025-01-0113836078361810.1109/ACCESS.2025.356938911002480Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based ModelsRavi Shankar Shukla0https://orcid.org/0009-0007-5607-0680Abdulrahman M. Alatawi1Department of Computer Science, College of Computing and Informatics, Saudi Electronic University, Riyadh, Saudi ArabiaDepartment of Computer Science, Saudi Electronic University, Riyadh, Saudi ArabiaRecently, transformer-based learning models have shown promising results in network traffic prediction across various contexts. However, their potential in Mobile Edge Computing (MEC) environments remains largely unexplored, despite the unique requirements of MEC such as low latency and high-bandwidth communication between end-users and edge servers. This study evaluates the performance of four transformer-based learning models for Internet traffic prediction in MEC environments, comparing them against state-of-the-art models using a real-world dataset from publicly available mobile operator networks. Performance is assessed using mean squared error (MSE) and mean absolute error (MAE) as evaluation metrics. Our experiments demonstrate that the proposed GAN-based transformer model, referred to as 5GT-GAN-Trans, achieves an MSE of 0.428 and an MAE of 0.441, considerably outperforming baseline models such as FED-Former-F (MSE: 0.791, MAE: 0.606), FED-Former-W (MSE: 0.622, MAE: 0.508), Informer (MSE: 0.814, MAE: 0.649), and a standard Transformer model (MSE: 0.803, MAE: 0.640). These numerical improvements underscore the efficacy of transformer-based models for precise Internet traffic forecasting in MEC environments, offering valuable insights for improved network management and enhanced user experience.https://ieeexplore.ieee.org/document/11002480/Internet traffic predictiongenerative adversarial network5Gmobile edge computing
spellingShingle Ravi Shankar Shukla
Abdulrahman M. Alatawi
Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
IEEE Access
Internet traffic prediction
generative adversarial network
5G
mobile edge computing
title Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
title_full Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
title_fullStr Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
title_full_unstemmed Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
title_short Enhancing Internet Traffic Forecasting in MEC Environments With 5GT-Trans: Leveraging Synthetic Data and Transformer-Based Models
title_sort enhancing internet traffic forecasting in mec environments with 5gt trans leveraging synthetic data and transformer based models
topic Internet traffic prediction
generative adversarial network
5G
mobile edge computing
url https://ieeexplore.ieee.org/document/11002480/
work_keys_str_mv AT ravishankarshukla enhancinginternettrafficforecastinginmecenvironmentswith5gttransleveragingsyntheticdataandtransformerbasedmodels
AT abdulrahmanmalatawi enhancinginternettrafficforecastinginmecenvironmentswith5gttransleveragingsyntheticdataandtransformerbasedmodels