Network Digital Twin-Generated Dataset for Machine Learning-based Intelligent Zero-Touch SLA Preservation

Overview

This record contains a set of synthetic datasets designed for the automatic (zero-touch) preservation of Service Level Agreements (SLA) in virtualized networks. Unlike the previous case, this dataset includes metrics such as latency, jitter, and packet loss measured end-to-end, providing a comprehensive view of overall network performance under different traffic conditions. This approach allows the training and evaluation of machine learning models aimed at intelligently ensuring SLA compliance.

To obtain this information without impacting the performance of the scenario, specific probes were deployed within the Network Digital Twin (NDT), capable of collecting metrics in a non-intrusive manner. In addition, data flows emulating congestion or degradation conditions were generated on the scenario, enriching the dataset and providing greater realism to the modeled situations.

To address this challenge, a Network Digital Twin (NDT) approach was employed to emulate realistic network conditions and traffic patterns, enabling the automated generation of labeled data for monitoring, preserving, and intelligently optimizing end-to-end SLA compliance.

Feature Set:

📌 General Information

Timestamp: time marker of the measurement

Link: monitored network link

📌 Network Performance Metrics

Packet_loss: percentage of lost packets

Jitter: variation in packet delay

RTT (Round-Trip Time): measured round-trip latency

TTL (Time to Live): hop-related metric

📌 Traffic Flow Metrics

Outflow_Router_eth4: outgoing traffic via router interface eth4

Outflow_Router_eth5: outgoing traffic via router interface eth5

Inflow_Router_eth3: incoming traffic via router interface eth3

Inflow_Router_eth4: incoming traffic via router interface eth4

Total_outflow: aggregate outgoing traffic across monitored interfaces

Total_inflow: aggregate incoming traffic across monitored interfaces

Diff_Mbps: difference between total inflow and outflow in Mbps

📌 Service Metrics

Resolve: DNS resolution success/failure indicator

Availability: service availability status

📌 Probe Metrics

Probe_duration: duration of the active probe/measurement

📌 Derived Status Flags

Status: indicates whether total_outflow is greater than or less than total_inflow

Duplicated_flow_flag: set if diff_Mbps > 2 and packet_loss < 0.5%

📌 Dataset Label

Label: 0/1/2

Dataset Variations:

To accommodate diverse research needs and scenarios, the dataset is provided in the following variations. Traffic bandwidth ranges emulated are as follows:

Range 0: 1–10 Mbps

Range 1: 11–40 Mbps

Range 2: 41–70 Mbps

Range 3: 71–90 Mbps

Range 4: Greater than 91 Mbps

dataset_01_TC34_09072025_with_loss_diff_labeled.csv

Execution of multi-flow UDP/TCP with an approximately homogeneous range distribution, around 20% for each generated range (ranges 0, 1, 2, 3, and 4), without applying packet loss or latency through "Traffic Control (TC)".

dataset_02_TC34_12072025_with_loss_diff_labeled.csv

Execution of multi-flow UDP/TCP with an approximately homogeneous range distribution, around 20% for each generated range (ranges 0, 1, 2, 3, and 4), applying packet loss or latency through "Traffic Control (TC)" on the ingress routers of the NDT network.

dataset_03_TC34_16072025_with_loss_diff_labeled.csv

Execution of multi-flow UDP/TCP with an approximately homogeneous range distribution, around 20% for each generated range (ranges 0, 1, 2, 3, and 4), applying packet loss or latency through "Traffic Control (TC)" on the egress routers of the NDT network.