Online Optimization of DNN Inference Network Utility in Collaborative Edge Computing

TL;DR

This paper introduces an online, learned optimization framework for collaborative edge computing that jointly optimizes workload allocation and routing to maximize network utility, addressing unknown utility functions.

Contribution

It develops a novel nested-loop and single-loop algorithms for joint workload and routing optimization in CEC, with theoretical analysis and improved convergence.

Findings

Algorithms outperform existing methods in simulations.

Proposed methods achieve faster convergence.

Systematic approach handles unknown utility functions.

Abstract

Collaborative Edge Computing (CEC) is an emerging paradigm that collaborates heterogeneous edge devices as a resource pool to compute DNN inference tasks in proximity such as edge video analytics. Nevertheless, as the key knob to improve network utility in CEC, existing works mainly focus on the workload routing strategies among edge devices with the aim of minimizing the routing cost, remaining an open question for joint workload allocation and routing optimization problem from a system perspective. To this end, this paper presents a holistic, learned optimization for CEC towards maximizing the total network utility in an online manner, even though the utility functions of task input rates are unknown a priori. In particular, we characterize the CEC system in a flow model and formulate an online learning problem in a form of cross-layer optimization. We propose a nested-loop algorithm to solve workload allocation and distributed routing iteratively, using the tools of gradient sampling and online mirror descent. To improve the convergence rate over the nested-loop version, we further devise a single-loop algorithm. Rigorous analysis is provided to show its inherent convexity, efficient convergence, as well as algorithmic optimality. Finally, extensive numerical simulations demonstrate the superior performance of our solutions.