# KISS methodologies for network management and anomaly detection

## TL;DR

This paper presents scalable, resource-efficient methodologies for network management and anomaly detection, tested in real industrial environments, addressing challenges of data collection and centralization in growing networks.

## Contribution

It introduces and evaluates novel methodologies for network monitoring and anomaly detection that reduce reliance on centralized data collection in large-scale networks.

## Key findings

- Effective in real industrial environments
- Reduce data centralization requirements
- Improve scalability of network management

## Abstract

Current networks are increasingly growing in size and complexity and so is the amount of monitoring data that they produce. As a result, network monitoring systems have to scale accordingly. As a possible approach, horizontal scalability can be achieved by large data centralization systems based on clusters, which are expensive and difficult to deploy in a real production scenario. In this paper we propose and evaluate a series of methodologies, deployed in real industrial production environments, for network monitoring and management, from the architecture design to the visualization system as well as for the anomaly detection methodologies, that intend to squeeze the vertical resources and overcome the difficulties of data collection and centralization.