Adaptive Edge Offloading for Image Classification Under Rate Limit

TL;DR

This paper introduces a deep reinforcement learning-based offloading policy for embedded image classification devices, optimizing accuracy under network rate constraints regulated by a token bucket, and demonstrates its effectiveness on a testbed with ImageNet data.

Contribution

It proposes a novel DQN-based online offloading policy that manages image transmission under rate limits, handling complex input patterns and deployment on embedded devices.

Findings

The policy improves classification accuracy under rate constraints.

It effectively manages correlated image arrivals and accuracy variations.

Deployment on embedded devices is feasible and practical.

Abstract

This paper considers a setting where embedded devices are used to acquire and classify images. Because of limited computing capacity, embedded devices rely on a parsimonious classification model with uneven accuracy. When local classification is deemed inaccurate, devices can decide to offload the image to an edge server with a more accurate but resource-intensive model. Resource constraints, e.g., network bandwidth, however, require regulating such transmissions to avoid congestion and high latency. The paper investigates this offloading problem when transmissions regulation is through a token bucket, a mechanism commonly used for such purposes. The goal is to devise a lightweight, online offloading policy that optimizes an application-specific metric (e.g., classification accuracy) under the constraints of the token bucket. The paper develops a policy based on a Deep Q-Network (DQN), and demonstrates both its efficacy and the feasibility of its deployment on embedded devices. Of note is the fact that the policy can handle complex input patterns, including correlation in image arrivals and classification accuracy. The evaluation is carried out by performing image classification over a local testbed using synthetic traces generated from the ImageNet image classification benchmark. Implementation of this work is available at https://github.com/qiujiaming315/edgeml-dqn.