Learning-Augmented Online Packet Scheduling with Deadlines

TL;DR

This paper introduces a learning-augmented online packet scheduling algorithm with deadlines that adapts to prediction accuracy, improving performance when predictions are accurate while maintaining robustness.

Contribution

It presents a novel framework for online packet scheduling with deadlines that leverages predictions to enhance competitive ratios, balancing accuracy and robustness.

Findings

Improves competitive ratio with accurate predictions

Maintains bounded competitive ratio regardless of prediction error

Provides a new algorithmic framework for learning-augmented scheduling

Abstract

The modern network aims to prioritize critical traffic over non-critical traffic and effectively manage traffic flow. This necessitates proper buffer management to prevent the loss of crucial traffic while minimizing the impact on non-critical traffic. Therefore, the algorithm's objective is to control which packets to transmit and which to discard at each step. In this study, we initiate the learning-augmented online packet scheduling with deadlines and provide a novel algorithmic framework to cope with the prediction. We show that when the prediction error is small, our algorithm improves the competitive ratio while still maintaining a bounded competitive ratio, regardless of the prediction error.