Efficient Information Updates in Compute-First Networking via Reinforcement Learning with Joint AoI and VoI

TL;DR

This paper introduces a joint Age-and-Value-Aware metric and a reinforcement learning policy for efficient service information updates in compute-first networking, significantly reducing communication without sacrificing task accuracy.

Contribution

It proposes a novel AVA metric that combines timeliness and relevance, and a reinforcement learning approach to optimize update decisions in compute-first networking systems.

Findings

AVA reduces update frequency by over 90% on average.

The RL policy maintains task accuracy despite fewer updates.

Significant communication savings without performance loss.

Abstract

Timely and efficient dissemination of service information is critical in compute-first networking systems, where user requests arrive dynamically and computing resources are constrained. In such systems, the access point (AP) plays a key role in forwarding user requests to a server based on its latest received service information. This paper considers a single-source, single-destination system and introduces an Age-and-Value-Aware (AVA) metric that jointly captures both the timeliness and the task relevance of service information. Unlike traditional freshness-based metrics, AVA explicitly incorporates variations in server-side service capacity and AP forwarding decisions, allowing more context-aware update evaluation. Building upon AVA, we propose a reinforcement learning-based update policy that learns to selectively transmit service information updates to the AP. It aims to maximize overall task success while minimizing unnecessary communications. Extensive simulations under diverse user request patterns and varying service capacities demonstrate that AVA reduces the update frequency by over 90% on average compared to baselines, with reductions reaching 98% in certain configurations. Crucially, this reduction is achieved without compromising the accuracy of task execution or the quality of decision making.