VINEVI: A Virtualized Network Vision Architecture for Smart Monitoring of Heterogeneous Applications and Infrastructures

TL;DR

VINEVI tackles the challenge of monitoring heterogeneous infrastructures, including bare-metal, low-cost hardware, and hosted/virtualized services. It proposes an AI-enhanced network vision framework that combines PacketVision CNN-based traffic classification with Prometheus and Victoria Metrics to provide end-to-end, real-time monitoring across hardware, network, and applications. The authors empirically compare SqueezeNet, MobileNetV2, and ResNet-18 for seven-class traffic classification, finding MobileNet delivers the highest accuracy (99.90%) and that per-packet latency depends on architecture and platform (e.g., ResNet on ARM64 vs SqueezeNet on x64) with CPU usage differences; they show that ResNet's lower last-layer complexity can yield lower CPU load on embedded devices. The work demonstrates that VINEVI can adaptively monitor heterogeneous environments with fine-grained traffic class information and offers practical guidance for deploying AI-assisted monitoring across different hardware deployments.

Abstract

Monitoring heterogeneous infrastructures and applications is essential to cope with user requirements properly, but it still lacks enhancements. The well-known state-of-the-art methods and tools do not support seamless monitoring of bare-metal, low-cost infrastructures, neither hosted nor virtualized services with fine-grained details. This work proposes VIrtualized NEtwork VIsion architecture (VINEVI), an intelligent method for seamless monitoring heterogeneous infrastructures and applications. The VINEVI architecture advances state of the art with a node-embedded traffic classification agent placing physical and virtualized infrastructures enabling real-time traffic classification. VINEVI combines this real-time traffic classification with well-known tools such as Prometheus and Victoria Metrics to monitor the entire stack from the hardware to the virtualized applications. Experimental results showcased that VINEVI architecture allowed seamless heterogeneous infrastructure monitoring with a higher level of detail beyond literature. Also, our node-embedded real-time Internet traffic classifier evolved with flexibility the methods with monitoring heterogeneous infrastructures seamlessly.

Figures (7)

• Figure 1: VINEVI Monitoring Schema.
• Figure 2: Intelligent Monitoring Testbed Overview.
• Figure 3: Examples of images for each class.
• Figure 4: Training and Loss values evolution for each CNN model.
• Figure 5: x64: prediction time.