A semantic data lake framework for autonomous fault management in SDN environments

Abstract

Fault Management is a vital issue for any network operator since the beginning of the telecommunications era. As networks have become more and more complex, their management systems are crucial for any operator company. In this ecosystem, the Software‐Defined Networking (SDN) approach has appeared as a possible solution for different networking issues. The flexibility provided by SDN to the network management enables a great dynamism in the configuration of network devices. However, this feature introduces the cost of a potential increase in failures because every modification introduced on the control plane is a new possibility for failures to appear and cause a decrement of the quality for offered services. Because of the growing pace of the networks, the classical approach is not feasible to cope that dynamism. Increasing the number of human operators in charge of the fault management process would increase the operation cost dramatically. Thus, this paper presents an approach to apply machine learning over a big data framework for an autonomous fault management process in SDN networks. In this paper, we present a Semantic Data Lake framework for a self‐diagnosis service, which is deployed on top of an SDN management platform. Moreover, we have developed a prototype of the proposed service with different diagnosis models for SDN networks. Models and algorithms have been evaluated showing good results.

Using the RFC 7575 and Models at Runtime for Enabling Autonomic Networking in SDN

“…Focusing on QoE, [Volpato et al 2017] defined an ANM architecture (i.e., the Autonomic QoE Management Architecture) to offer QoE-aware services. The work of [Benayas et al 2019] describes a semantic data lake architecture for fault management based on Bayesian Reasoning for SDN Environments. In [Bega et al 2019], the authors propose an architecture based on deep learning for enabling autonomic behavior.…”

Software-Defined Multi-domain Tactical Networks: Foundations and Future Directions

“…Based on the concept of semantic ontology, an autonomous fault management agent for SDN is developed in [63]. It compares network status with semantic models using Bayesian reasoning as inference method for determining the category of a fault.…”

SmartX Multi‐View Visibility Framework for unified monitoring of SDN‐enabled multisite clouds

“…Considering visibility storage requirements, inside the vis center, we setup Visibility DataLake (DataLake 35 ) to deliver large-scale storage repository for storing any type of data with varying characteristics. The general temptation is to retain all cleaned data into a DataLake, irrespective of data complexity whether structured or unstructured.…”

“…Towards interactive visualization of multilayer visibility, comprehensive visualization infrastructure is arranged for enabling a panoramic view of playground resources and quickly responding to the operational glitches. 35 Furthermore, to overcome the troubleshooting complexity of the playground, fine-grained physical-virtual topological visualization is developed. This visualization has a user-friendly web interface and a state-of-the-art dashboard.…”