2021
DOI: 10.1007/978-3-030-80126-7_27
|View full text |Cite
|
Sign up to set email alerts
|

Unsupervised Machine Learning-Based Elephant and Mice Flow Identification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 17 publications
0
3
0
Order By: Relevance
“…In [108], the management of network flows in SDN was proposed, particularly for data center networks (DCNs). The goal is to identify and distinguish between different types of network flows (elephant and mouse flows) and route them efficiently based on their characteristics.…”
Section: ) Unsupervised Learning Techniquesmentioning
confidence: 99%
“…In [108], the management of network flows in SDN was proposed, particularly for data center networks (DCNs). The goal is to identify and distinguish between different types of network flows (elephant and mouse flows) and route them efficiently based on their characteristics.…”
Section: ) Unsupervised Learning Techniquesmentioning
confidence: 99%
“…Due to the need to identify the different requirements of the services provided in the networks to have an accurate knowledge of the network behavior, machine learning (ML) has been used to extract knowledge from the data through methods to classify the network traffic [12].…”
Section: A Backgroundmentioning
confidence: 99%
“…It has been proven in studies such as [79,80,81] that the presence of heterogeneous traffic on shared infrastructures generates a high degradation of performance in terms of utilization, latency, end-to-end throughput, and fairness index. Large flows can fill the router queues at bottlenecks, starving short flows, causing high queuing delay and packet loss and thus degradation in the quality of service [82]. On the other hand, with only a small percentage of packet loss, the performance of long flows is compromised because congestion detection and control have high convergence times due to the RTT [83].…”
Section: Issues Of Large Data Transfers Over Non-dedicated Networkmentioning
confidence: 99%