When Backpressure Meets Predictive Scheduling

TL;DR

This paper demonstrates that predictive scheduling, using lookahead window predictions, can significantly improve delay performance in queueing systems and proposes an efficient algorithm, PBP, that leverages prediction for near-optimal utility with reduced delay.

Contribution

It establishes a theoretical equivalence between predictive and non-predictive queueing systems, and introduces PBP, an algorithm that efficiently incorporates prediction to optimize utility and delay.

Findings

Predictive scheduling improves delay performance and can approach zero delay with increased prediction.

PBP achieves near-optimal utility while ensuring better delay distribution.

Predictive scheduling outperforms traditional backpressure, surpassing known utility-delay tradeoffs.

Abstract

Motivated by the increasing popularity of learning and predicting human user behavior in communication and computing systems, in this paper, we investigate the fundamental benefit of predictive scheduling, i.e., predicting and pre-serving arrivals, in controlled queueing systems. Based on a lookahead window prediction model, we first establish a novel equivalence between the predictive queueing system with a \emph{fully-efficient} scheduling scheme and an equivalent queueing system without prediction. This connection allows us to analytically demonstrate that predictive scheduling necessarily improves system delay performance and can drive it to zero with increasing prediction power. We then propose the \textsf{Predictive Backpressure (PBP)} algorithm for achieving optimal utility performance in such predictive systems. \textsf{PBP} efficiently incorporates prediction into stochastic system control and avoids the great complication due to the exponential state space growth in the prediction window size. We show that \textsf{PBP} can achieve a utility performance that is within $O(\epsilon)$ of the optimal, for any $\epsilon>0$, while guaranteeing that the system delay distribution is a \emph{shifted-to-the-left} version of that under the original Backpressure algorithm. Hence, the average packet delay under \textsf{PBP} is strictly better than that under Backpressure, and vanishes with increasing prediction window size. This implies that the resulting utility-delay tradeoff with predictive scheduling beats the known optimal $[O(\epsilon), O(\log(1/\epsilon))]$ tradeoff for systems without prediction.