rus
DOI: 10.22184/2070-8963.2025.132.8.54.57
Modern network infrastructures generate enormous amounts of data on network activity, which traditional analysis methods are becoming inefficient at handling. This paper proposes the use of Big Data technologies to analyze network activity aimed at improving security, performance, and reliability of network services. A comprehensive approach to collecting, processing, and analyzing large volumes of network activity data is suggested, including the use of Node Exporter, Prometheus, Apache Airflow, machine learning, and visualization techniques. The results demonstrate the potential for identifying complex anomalies and security threats, as well as optimizing the use of network resources.
Tags: apache airflow big data technologies machine learning monitoring tools network activity network monitoring инструменты мониторинга машинное обучение мониторинг сети сетевая активность технологии big data
Subscribe to the journal Last Mile to read the full article.
Modern network infrastructures generate enormous amounts of data on network activity, which traditional analysis methods are becoming inefficient at handling. This paper proposes the use of Big Data technologies to analyze network activity aimed at improving security, performance, and reliability of network services. A comprehensive approach to collecting, processing, and analyzing large volumes of network activity data is suggested, including the use of Node Exporter, Prometheus, Apache Airflow, machine learning, and visualization techniques. The results demonstrate the potential for identifying complex anomalies and security threats, as well as optimizing the use of network resources.
Tags: apache airflow big data technologies machine learning monitoring tools network activity network monitoring инструменты мониторинга машинное обучение мониторинг сети сетевая активность технологии big data
Subscribe to the journal Last Mile to read the full article.
Readers feedback
