A Survey for Real-Time Network Performance Measurement via Machine Learning

TL;DR

This survey reviews how Machine Learning and Network Calculus are integrated to enhance real-time network performance measurement, enabling dynamic scheduling and latency guarantees for time-critical applications.

Contribution

It comprehensively summarizes existing approaches combining ML and NC for real-time network measurement, highlighting their results, dependencies, and application scenarios.

Findings

ML and NC integration improves measurement efficiency

Various approaches have been applied in different scenarios

The survey identifies key challenges and future directions

Abstract

Real-Time Networks (RTNs) provide latency guarantees for time-critical applications and it aims to support different traffic categories via various scheduling mechanisms. Those scheduling mechanisms rely on a precise network performance measurement to dynamically adjust the scheduling strategies. Machine Learning (ML) offers an iterative procedure to measure network performance. Network Calculus (NC) can calculate the bounds for the main performance indexes such as latencies and throughputs in an RTN for ML. Thus, the ML and NC integration improve overall calculation efficiency. This paper will provide a survey for different approaches of Real-Time Network performance measurement via NC as well as ML and present their results, dependencies, and application scenarios.