Network traffic prediction based on PSO-LightGBM-TM

Network traffic prediction is critical in wireless network management by allowing a good estimate of the traffic trend, which is also an important approach for detecting traffic anomalies in order to enhance network security. Deep-learning-based method has been widely adopted to predict network traf...

Full description

Saved in:
Bibliographic Details
Main Authors: Li, Feng, Nie, Wei, Lam, Kwok-Yan, Wang, Li
Other Authors: College of Computing and Data Science
Format: Article
Language:English
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10356/180314
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-180314
record_format dspace
spelling sg-ntu-dr.10356-1803142024-10-11T02:44:29Z Network traffic prediction based on PSO-LightGBM-TM Li, Feng Nie, Wei Lam, Kwok-Yan Wang, Li College of Computing and Data Science School of Computer Science and Engineering Strategic Centre for Research in Privacy-Preserving Technologies & Systems (SCRIPTS) Computer and Information Science Network traffic prediction Machine learning Network traffic prediction is critical in wireless network management by allowing a good estimate of the traffic trend, which is also an important approach for detecting traffic anomalies in order to enhance network security. Deep-learning-based method has been widely adopted to predict network traffic matrix (TM) though with the main drawbacks in high complexity and low efficiency. In this paper, we propose a traffic prediction model based on Particle Swarm Optimization (PSO) and LightGBM (PSO-LightGBM-TM), which optimizes the LightGBM parameters for each network flow by PSO so that LightGBM can adapt to each of the network traffic flow. Compared with existing commonly used deep learning models, our model has a more straightforward structure and yet outperforms existing deep learning models. Sufficient comparison tests on three real network traffic datasets, Abilene, GÉANT, and CERNET have been conducted, and the results show that our model provides more accurate results and higher prediction efficiency. Info-communications Media Development Authority (IMDA) National Research Foundation (NRF) This research is supported by the National Research Foundation, Singapore under its Strategic Capability Research Centres Funding Initiative and Infocomm Media Development Authority under its Future Communications Research & Development Programme. 2024-10-11T02:44:29Z 2024-10-11T02:44:29Z 2024 Journal Article Li, F., Nie, W., Lam, K. & Wang, L. (2024). Network traffic prediction based on PSO-LightGBM-TM. Computer Networks, 254, 110810-. https://dx.doi.org/10.1016/j.comnet.2024.110810 1389-1286 https://hdl.handle.net/10356/180314 10.1016/j.comnet.2024.110810 2-s2.0-85204357326 254 110810 en Computer Networks © 2024 Elsevier B.V. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Network traffic prediction
Machine learning
spellingShingle Computer and Information Science
Network traffic prediction
Machine learning
Li, Feng
Nie, Wei
Lam, Kwok-Yan
Wang, Li
Network traffic prediction based on PSO-LightGBM-TM
description Network traffic prediction is critical in wireless network management by allowing a good estimate of the traffic trend, which is also an important approach for detecting traffic anomalies in order to enhance network security. Deep-learning-based method has been widely adopted to predict network traffic matrix (TM) though with the main drawbacks in high complexity and low efficiency. In this paper, we propose a traffic prediction model based on Particle Swarm Optimization (PSO) and LightGBM (PSO-LightGBM-TM), which optimizes the LightGBM parameters for each network flow by PSO so that LightGBM can adapt to each of the network traffic flow. Compared with existing commonly used deep learning models, our model has a more straightforward structure and yet outperforms existing deep learning models. Sufficient comparison tests on three real network traffic datasets, Abilene, GÉANT, and CERNET have been conducted, and the results show that our model provides more accurate results and higher prediction efficiency.
author2 College of Computing and Data Science
author_facet College of Computing and Data Science
Li, Feng
Nie, Wei
Lam, Kwok-Yan
Wang, Li
format Article
author Li, Feng
Nie, Wei
Lam, Kwok-Yan
Wang, Li
author_sort Li, Feng
title Network traffic prediction based on PSO-LightGBM-TM
title_short Network traffic prediction based on PSO-LightGBM-TM
title_full Network traffic prediction based on PSO-LightGBM-TM
title_fullStr Network traffic prediction based on PSO-LightGBM-TM
title_full_unstemmed Network traffic prediction based on PSO-LightGBM-TM
title_sort network traffic prediction based on pso-lightgbm-tm
publishDate 2024
url https://hdl.handle.net/10356/180314
_version_ 1814047296452558848