The SELFNET Approach for Autonomic Management in an NFV/SDN Networking Paradigm

Abstract

To meet the challenging key performance indicators of the fifth generation (5G) system, the network infrastructure becomes more heterogeneous and complex. This will bring a high pressure on the reduction of OPEX and the improvement of the user experience. Hence, shifting today's manual and semi-automatic network management into an autonomic and intelligent framework will play a vital role in the upcoming 5G system. Based on the cutting-edge technologies, such as Software-Defined Networking and Network Function Virtualization, a novel management framework upon the software-defined and Virtualized Network is proposed by EU H2020 SELFNET project. In the paper, the reference architecture of SELFNET, which is

An Approach to Data Analysis in 5G Networks

“…SELFNET enables both autonomic corrective and preventive actions to mitigate existing or potential network problems while providing scalability, extensibility and reduce capital expenditure (capex) and operational expenditure (opex). These capabilities are provided through a layered architecture and a use-case driven approach, as is detailed in [34]. The SELFNET architecture addresses major network management problems including self-protection capabilities against distributed cyber-attacks, self-healing capabilities against network failures, and self-optimization to dynamically improve the performance of the network and the QoE of the users.…”

“…By studying the Analyzer Module as a black box model it is possible to focus more on its inputs/outputs and their relationship with the rest of the SELFNET components [34]. From this perspective, their information sources, nature of the data and behaviour in different circumstances are described.…”

“…Meanwhile, there are reports [1,32] and projects [21,[33][34][35][36][37] that introduce analysis capacities to cover 5G requirements. In this way, METIS Project [28] takes into account SON concept in order to provide a new level of adaptability to 5G infrastructures.…”

Marco para el Análisis e Inferencia de Conocimiento en Redes 5G

“…SELFNET hace uso de los principios de SDN y NFV para gestionar de forma inteligente y autonómica diversas funciones de red con el propósito de dar solución automática a problemas comunes de red, tales como el retardo en la transmisión, la caída de enlaces, etc. Para ello, SELFNET [15] integra un paradigma de autogestión de la red basado en el uso de algoritmos de predicción, reconocimiento de patrones, técnicas de minería de datos, entre otros, para identificar el comportamiento de una red móvil 5G, y determinar las mejores acciones que mitiguen de forma automática los problemas de red detectados. SELFNET se basa en la definición de tres grandes casos de uso: la autoprotección (self-protection), la autosalud (self-healing) y la autooptimización (self-optimization), en los que se distinguen escenarios sobre los que el sistema requiera procesos de toma de decisiones y el despliegue de acciones de respuesta.…”

“…SELFNET [15] SDN, NFV El proyecto provee un marco de gestión autónoma de red, basado en el despliegue inteligente de sensores y actuadores tanto en la infraestructura física como virtual. Las funciones pueden ser basadas en SDN o NFV.…”