Joint Batching and Scheduling for High-Throughput Multiuser Edge AI with Asynchronous Task Arrivals

TL;DR

This paper proposes a joint batching and scheduling framework for multiuser edge AI that maximizes throughput by optimizing batch sizes, start times, and task associations, considering heterogeneous arrivals and deadlines.

Contribution

It introduces a convex optimization-based approach with an alternating algorithm for joint batching and scheduling, and leverages spectrum holes for further throughput enhancement.

Findings

Significant throughput improvement over benchmark schemes

Effective handling of heterogeneous task arrivals and deadlines

Efficient algorithm for near-optimal joint batching and scheduling

Abstract

In this paper, we study joint batching and (task) scheduling to maximise the throughput (i.e., the number of completed tasks) under the practical assumptions of heterogeneous task arrivals and deadlines. The design aims to optimise the number of batches, their starting time instants, and the task-batch association that determines batch sizes. The joint optimisation problem is complex due to multiple coupled variables as mentioned and numerous constraints including heterogeneous tasks arrivals and deadlines, the causality requirements on multi-task execution, and limited radio resources. Underpinning the problem is a basic tradeoff between the size of batch and waiting time for tasks in the batch to be uploaded and executed. Our approach of solving the formulated mixed-integer problem is to transform it into a convex problem via integer relaxation method and $\ell_0$-norm approximation. This results in an efficient alternating optimization algorithm for finding a close-to-optimal solution. In addition, we also design the optimal algorithm from leveraging spectrum holes, which are caused by fixed bandwidth allocation to devices and their asynchronized multi-batch task execution, to admit unscheduled tasks so as to further enhance throughput. Simulation results demonstrate that the proposed framework of joint batching and resource allocation can substantially enhance the throughput of multiuser edge-AI as opposed to a number of simpler benchmarking schemes, e.g., equal-bandwidth allocation, greedy batching and single-batch execution.