Closed-Form and Boundary Expressions for Task-Success Probability in Status-Driven Systems

TL;DR

This paper develops a unified analytical framework to accurately model and bound the task-success probability in status-driven systems, accounting for stochastic arrivals, delays, and limited server capacity, validated through extensive simulations.

Contribution

It introduces a closed-form expression and bounds for task success probability using Laplace transforms, adaptable to various policies and delay distributions.

Findings

The bounds closely match empirical success rates within 0.01 and 0.016.

The framework effectively captures effects of delays, staleness, and server capacity.

Simulations validate the accuracy and adaptability of the analytical model.

Abstract

Timely and efficient dissemination of server status is critical in compute-first networking systems, where user tasks arrive dynamically and computing resources are limited and stochastic. In such systems, the access point plays a key role in forwarding tasks to a server based on its latest received server status. However, modeling the task-success probability suffering the factors of stochastic arrivals, limited server capacity, and bidirectional link delays. Therefore, we introduce a unified analytical framework that abstracts the AP forwarding rule as a single probability and models all network and waiting delays via their Laplace transforms. This approach yields a closed form expression for the end to end task success probability, together with upper and lower bounds that capture Erlang loss blocking, information staleness, and random uplink/downlink delays. We validate our results through simulations across a wide range of parameters, showing that theoretical predictions and bounds consistently enclose observed success rates. Our framework requires only two interchangeable inputs (the forwarding probability and the delay transforms), making it readily adaptable to alternative forwarding policies and delay distributions. Experiments demonstrate that our bounds are able to achieve accuracy within 0.01 (upper bound) and 0.016 (lower bound) of the empirical task success probability.