View in EDS

Campus internet traffic characterization with policing and shaping on Grafana virtualization dashboard.

Saved in:
Bibliographic Details
Title: Campus internet traffic characterization with policing and shaping on Grafana virtualization dashboard.
Authors: Abdullah, Nor Paezah, Kassim, Murizah
Source: AIP Conference Proceedings; 2025, Vol. 3322 Issue 1, p1-11, 11p
Subject Terms: QUALITY of service, TRAFFIC congestion, BANDWIDTH allocation, COMPUTER networks, FLOW control (Data transmission systems), TRAFFIC flow measurement, COMPUTER network monitoring, TRAFFIC monitoring
Abstract: This paper introduces traffic characterization, traffic policing, and traffic shaping as approaches to managing network congestion and delay issues. Increased internet usage on campus can cause some difficulties, including traffic bursts, which can have an impact on the quality of service (QoS) that users get. The solution entails traffic characterization and policing on the Metro-E 50Mbps campus network via a virtual dashboard. The analysis will determine the distribution model, as well as the policing and shaping of the network of real-time internet traffic data, which will include burst traffic at 50Mbps/6.5MB. The best-fitted model is the log-normal distribution model, which has the highest MLE score of -2726. Policing and shaping on inbound bytes before and after a threshold of 50Mbps/6.5MB was performed, resulting in a total of 3422404.81MB buckets being created, with a total of 219273.88MB buckets after policing and a reduced percentage of 99.36%. Comparing the three different distribution models Lognormal, Gumbel and Exponential, policing on Gumbel has a drastic fall in bucket capacity from 38,425,134,909,099.88 bytes to 2,395,507,816.73 bytes (99.99% reduction) has a substantial impact on the network's ability to handle traffic bursts and maintain the QoS. Meanwhile, the total bucket capacity for Exponential remained unchanged at 16,3130.51 bytes, with a 0.00% reduction and the network's ability to handle traffic bursts while maintaining the QoS. This research has implications for Wan Metro-E Network's future QoS bandwidth management control techniques and network traffic performance improvement. [ABSTRACT FROM AUTHOR]
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:This paper introduces traffic characterization, traffic policing, and traffic shaping as approaches to managing network congestion and delay issues. Increased internet usage on campus can cause some difficulties, including traffic bursts, which can have an impact on the quality of service (QoS) that users get. The solution entails traffic characterization and policing on the Metro-E 50Mbps campus network via a virtual dashboard. The analysis will determine the distribution model, as well as the policing and shaping of the network of real-time internet traffic data, which will include burst traffic at 50Mbps/6.5MB. The best-fitted model is the log-normal distribution model, which has the highest MLE score of -2726. Policing and shaping on inbound bytes before and after a threshold of 50Mbps/6.5MB was performed, resulting in a total of 3422404.81MB buckets being created, with a total of 219273.88MB buckets after policing and a reduced percentage of 99.36%. Comparing the three different distribution models Lognormal, Gumbel and Exponential, policing on Gumbel has a drastic fall in bucket capacity from 38,425,134,909,099.88 bytes to 2,395,507,816.73 bytes (99.99% reduction) has a substantial impact on the network's ability to handle traffic bursts and maintain the QoS. Meanwhile, the total bucket capacity for Exponential remained unchanged at 16,3130.51 bytes, with a 0.00% reduction and the network's ability to handle traffic bursts while maintaining the QoS. This research has implications for Wan Metro-E Network's future QoS bandwidth management control techniques and network traffic performance improvement. [ABSTRACT FROM AUTHOR]
ISSN:0094243X
DOI:10.1063/5.0290597