Elapsed-Service-Time-Aware Preemption for Age of Information Minimization
Abstract
We study the age of information and peak age of information in status update systems with an arbitrary number of independent sources sharing a single server with generally distributed service times. We consider a general age-dependent self-preemptive policy in which an in-service update from source c is preempted by a new same-source arrival with a probability pc(x) that depends on the elapsed service time x. This formulation subsumes the non-preemptive, fully self-preemptive, and probabilistically preemptive policies as special cases, and also accommodates threshold-based preemption. We develop a unified analytical framework based on non-homogeneous absorbing continuous-time Markov chains and semi-Markov chains to derive explicit expressions for the average age of information and peak age of information of each source under general per-source service-time distributions and age-dependent preemption rules. The framework applies to both single-source and multi-source systems and enables joint tuning of per-source preemption parameters. Numerical results for fifteen service-time distributions in the single-source setting reveal that the benefits of preemption depend strongly on the service-time hazard-rate structure, with threshold-based preemption providing its most notable additional gains over age-independent policies for distributions with unimodal hazard rates. For a dual-source system with lognormal service times, jointly tuned threshold-based preemption achieves lower sum average age of information and peak age of information than the considered age-independent policies, highlighting the importance of cross-source interactions in preemption decisions.
Related
- Worse Routes, Fresher Information: Preemption Redefines Which Route is Best
- Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics
- Physics-Aware Power Optimization for Rydberg Quantum Arrays via Barankin Bound Minimization
- Explaining f-Divergence-Based Regularization via Local Curvature and Sharpness-Aware Minimization
- Curvature-Scaled Sharpness-Aware Minimization: Convergence Beyond Smoothness
BibTeX
@misc{moltafet2026elapsedservicetimeaware,
title = {{Elapsed-Service-Time-Aware Preemption for Age of Information Minimization}},
author = {Mohammad Moltafet and Nail Akar and Sennur Ulukus and Marian Codreanu and Roy D. Yates},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07151},
eprint = {2611.07151},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07151},
}
RIS
TY - UNPB
TI - Elapsed-Service-Time-Aware Preemption for Age of Information Minimization
AU - Mohammad Moltafet
AU - Nail Akar
AU - Sennur Ulukus
AU - Marian Codreanu
AU - Roy D. Yates
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.07151
UR - https://arxiv.org/abs/2611.07151
AB - We study the age of information and peak age of information in status update systems with an arbitrary number of independent sources sharing a single server with generally distributed service times. We consider a general age-dependent self-preemptive policy in which an in-service update from source c is preempted by a new same-source arrival with a probability p_c(x) that depends on the elapsed service time x. This formulation subsumes the non-preemptive, fully self-preemptive, and probabilistically preemptive policies as special cases, and also accommodates threshold-based preemption. We develop a unified analytical framework based on non-homogeneous absorbing continuous-time Markov chains and semi-Markov chains to derive explicit expressions for the average age of information and peak age of information of each source under general per-source service-time distributions and age-dependent preemption rules. The framework applies to both single-source and multi-source systems and enables joint tuning of per-source preemption parameters. Numerical results for fifteen service-time distributions in the single-source setting reveal that the benefits of preemption depend strongly on the service-time hazard-rate structure, with threshold-based preemption providing its most notable additional gains over age-independent policies for distributions with unimodal hazard rates. For a dual-source system with lognormal service times, jointly tuned threshold-based preemption achieves lower sum average age of information and peak age of information than the considered age-independent policies, highlighting the importance of cross-source interactions in preemption decisions.
ER -