Lightweight Latency Prediction Scheme for Edge Applications: A Rational Modelling Approach

TL;DR

This paper presents a lightweight, rational modelling-based latency prediction scheme for edge computing that achieves high accuracy without intrusive probing, enabling reliable task offloading.

Contribution

It introduces a novel, efficient latency prediction model using rational functions based on key network features, outperforming traditional methods in accuracy and inference speed.

Findings

MAE = 0.0115, R^2 = 0.9847 in experiments

Eliminates need for intrusive active probing

Offers a good trade-off between accuracy and efficiency

Abstract

Accurately predicting end-to-end network latency is essential for enabling reliable task offloading in real-time edge computing applications. This paper introduces a lightweight latency prediction scheme based on rational modelling that uses features such as frame size, arrival rate, and link utilization, eliminating the need for intrusive active probing. The model achieves state-of-the-art prediction accuracy through extensive experiments and 5-fold cross-validation (MAE = 0.0115, R$^2$ = 0.9847) with competitive inference time, offering a substantial trade-off between precision and efficiency compared to traditional regressors and neural networks.