Internet Traffic Classification: A Survey

Srivastava, Gargi; Singh, M. P.; Kumar, Parvinder; Singh, Jaswinder Pal

doi:10.1142/9789814704830_0058

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traffic analysis is critical for evaluating and analyzing the performance of the networks, depending on the usage of the resources. The fundamental reason for analyzing the traffic of network is to assess the quality of service, troubleshoot the problems, and maintaining the overall security of the network [25]. Network classification is vital for service providers for managing the overall performance of the network, including certain aspects like Intrusion Detection Systems (IDS) etc.…”

Section: Review Of Internet Traffic Classification Approaches 1) Omentioning

confidence: 99%

Towards Optimizing WLANs Power Saving: Novel Context-Aware Network Traffic Classification Based on a Machine Learning Approach

Saeed

Kolberg

2019

IEEE Access

View full text Add to dashboard Cite

Energy is a vital resource in wireless computing systems. Despite the increasing popularity of wireless local area networks (WLANs), one of the most important outstanding issues remains the power consumption caused by wireless network interface controller. To save this energy and reduce the overall power consumption of wireless devices, most approaches proposed to-date are focused on static and adaptive power saving modes. Existing literature has highlighted several issues and limitations in regards to their power consumption and performance degradation, warranting the need for further enhancements. In this paper, we propose a novel context-aware network traffic classification approach based on machine learning (ML) classifiers for optimizing WLAN power saving. The levels of traffic interaction in the background are contextually exploited for application of ML classifiers. Finally, the classified output traffic is used to optimize our proposed context-aware listen interval power saving modes. A real-world dataset is recorded, based on nine smartphone applications' network traffic, reflecting different types of network behavior and interaction. This is used to evaluate the performance of eight ML classifiers in this initial study. The comparative results show that more than 99% of accuracy can be achieved. This paper indicates that ML classifiers are suited for classifying smartphone applications' network traffic based on the levels of interaction in the background. INDEX TERMS 802.11, energy consumption, machine learning (ML), power save mode (PSM), traffic classification, WLAN.

show abstract

Section: Review Of Internet Traffic Classification Approaches 1) Omentioning

confidence: 99%

Towards Optimizing WLANs Power Saving: Novel Context-Aware Network Traffic Classification Based on a Machine Learning Approach

Saeed

Kolberg

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Para melhorar a qualidade dos resultados, essas aplicações estão exigindo cada vez mais poder computacional, sendo executadas em sistemas de computacionais dedicados, demorando muitas horas para completar suas execuções e movimentando grandes volumes de dados, fazendo com que a rede se torne um gargalo. Então, entender as demandas de comunicação e classificar os aplicativos nos data centers é um desafio relevante[Srivastava et al, 2016]. A identificação correta de quais aplicativos estão usando os recursos do data center é essencial em várias atividades de gerenciamento, como planejamento de expansão, engenharia de tráfego, detecção de anomalias, monitoramento, e economia de energia[Trois et al, 2018].13 Na biblioteca Scikit-learn, as classes reais são as linhas e as preditas são as colunas…”

unclassified

Introdução à Ciência de Dados: Uma Visão Pragmática utilizando Python, Aplicações e Oportunidades em Redes de Computadores

Comarela¹,

Franco²,

Trois

et al. 2019

Minicursos Do XXXVII Simpósio Brasileiro De Redes De Computadores E Sistemas Distribuídos

View full text Add to dashboard Cite

Internet of Things, smart cities, crowdsourcing, and other neotechnologies are making the world and people more and more connected, causing colossal amounts of information to be transmitted through the network. In order to extract new knowledge and relevant information from these data, Data Science, which covers several disciplines, such as statistics, data mining, machine learning, and artificial intelligence, is becoming popular and gaining space in the most diverse areas of knowledge. In this context, this course presents, in a pragmatic way, through the Python language and specific libraries, the methods most used by data scientists to manipulate and analyze information, applying them in the resolution of relevant problems in the area of computer networks. ResumoInternet das Coisas, cidades inteligentes, crowdsourcing e outros neotecnologismos estão tornando o mundo e as pessoas cada vez mais conectados, fazendo que quantidades colossais de informação sejam transmitidas pela rede. No intuito de extrair novos conhecimentos e informações relevantes desses dados, a Ciência de Dados, que abrange várias disciplinas, tais como estatística, mineração de dados, aprendizado de máquina e inteligência artificial, está se popularizando e ganhando espaço nas mais diversas áreas de conhecimento. Nesse contexto, esse minicurso apresenta, de forma pragmática, através da linguagem Python e bibliotecas específicas, os métodos mais usados para manipular e analisar dados e extrair informações, aplicando-os na resolução de problemas relevantes da área de redes de computadores.

show abstract