Overage and Staleness Metrics for Status Update Systems

TL;DR

This paper introduces three new metrics—overage probability, stale update probability, and average overage—to evaluate the freshness and staleness of status updates in queuing systems, providing insights beyond traditional AoI metrics.

Contribution

It proposes novel metrics for assessing status update systems' performance in meeting freshness thresholds, and analyzes these metrics across different queuing models.

Findings

Lower bound for stale update probability with limited buffer size.

Overage probability decreases as update arrival rate increases.

Stale update probability increases with higher arrival rates.

Abstract

Status update systems consist of sensors that take measurements of a physical parameter and transmit them to a remote receiver. Age of Information (AoI) has been studied extensively as a metric for the freshness of information in such systems with and without an enforced hard or soft deadline. In this paper, we propose three metrics for status update systems to measure the ability of different queuing systems to meet a threshold requirement for the AoI. The {\em overage probability} is defined as the probability that the age of the most recent update packet held by the receiver is larger than the threshold. The {\em stale update probability} is the probability that an update is stale, i.e., its age has exceeded the deadline, when it is delivered to the receiver. Finally, the {\em average overage} is defined as the time average of the overage (i.e., age beyond the threshold), and is a measure of the average ``staleness'' of the update packets held by the receiver. We investigate these metrics in three typical status update queuing systems -- M/G/1/1, M/G/1/$2^*$, and M/M/1. Numerical results show the performances for these metrics under different parameter settings and different service distributions. The differences between the average overage and average AoI are also shown. Our results demonstrate that a lower bound exists for the stale update probability when the buffer size is limited. Further, we observe that the overage probability decreases and the stale update probability increases as the update arrival rate increases.