LENS: Layer Distribution Enabled Neural Architecture Search in Edge-Cloud Hierarchies

TL;DR

LENS introduces a multi-objective neural architecture search method tailored for edge-cloud systems, optimizing workload distribution by incorporating wireless communication parameters into the design process.

Contribution

The paper presents LENS, a novel NAS approach that considers wireless conditions during architecture design for two-tiered edge-cloud systems.

Findings

LENS improves energy efficiency by 76.47%.

LENS reduces latency by 75%.

Demonstrates effective workload distribution considering wireless parameters.

Abstract

Edge-Cloud hierarchical systems employing intelligence through Deep Neural Networks (DNNs) endure the dilemma of workload distribution within them. Previous solutions proposed to distribute workloads at runtime according to the state of the surroundings, like the wireless conditions. However, such conditions are usually overlooked at design time. This paper addresses this issue for DNN architectural design by presenting a novel methodology, LENS, which administers multi-objective Neural Architecture Search (NAS) for two-tiered systems, where the performance objectives are refashioned to consider the wireless communication parameters. From our experimental search space, we demonstrate that LENS improves upon the traditional solution's Pareto set by 76.47% and 75% with respect to the energy and latency metrics, respectively.