Computation and Communication Co-scheduling for Multi-Task Remote Inference

TL;DR

This paper introduces a novel co-scheduling method for multi-task remote inference systems that optimizes feature generation and transmission to minimize inference errors under resource constraints.

Contribution

It formulates the co-scheduling as a weakly-coupled Markov decision process and develops an asymptotically optimal reoptimized maximum gain first policy.

Findings

Reoptimized MGF policy significantly outperforms baseline policies.

The approach effectively manages resource constraints in multi-task remote inference.

Asymptotic optimality holds as resources and tasks increase proportionally.

Abstract

In multi-task remote inference systems, an intelligent receiver (e.g., command center) performs multiple inference tasks (e.g., target detection) using data features received from several remote sources (e.g., edge devices). Key challenges to facilitating timely inference in these systems arise from (i) limited computational power of the sources to produce features from their inputs, and (ii) limited communication resources of the channels to carry simultaneous feature transmissions to the receiver. We develop a novel computation and communication co-scheduling methodology which determines feature generation and transmission scheduling to minimize inference errors subject to these resource constraints. Specifically, we formulate the co-scheduling problem as a weakly-coupled Markov decision process with Age of Information (AoI)-based timeliness gauging the inference errors. To overcome its PSPACE-hard complexity, we analyze a Lagrangian relaxation of the problem, which yields gain indices assessing the improvement in inference error for each potential feature generation-transmission scheduling action. Based on this, we develop a reoptimized maximum gain first (MGF) policy. We show that this policy is asymptotically optimal for the original problem as the number of inference tasks and the available communication and computation resources increase, provided the ratio among them remains fixed. Experiments demonstrate that reoptimized MGF obtains significant improvements over baseline policies for varying numbers of tasks, channels, and sources.