Adaptive Edge Offloading for Image Classification Under Rate Limit
Adaptive Edge Offloading for Image Classification Under Rate Limit
复制标题
DOI：
10.1109/tcad.2022.3197533
复制
发表时间：
2022-07
影响因子：
2.9
通讯作者：
Jiaming Qiu-;Ruiqi Wang;Ayan Chakrabarti;R. Guérin;Chenyang Lu
中科院分区：
文献类型：
--
作者：
Jiaming Qiu-;Ruiqi Wang;Ayan Chakrabarti;R. Guérin;Chenyang Lu
本文考虑一种使用嵌入式设备来获取和分类图像的设置。由于计算能力有限，嵌入式设备依赖于简约的分类模型，但精度参差不齐。当本地分类被认为不准确时，设备可以决定将图像卸载到具有更准确但资源密集型模型的边缘服务器。然而，资源约束，例如网络带宽，需要调节这样的传输以避免拥塞和高等待时间。本文研究通过令牌桶进行传输管理时的卸载问题，令牌桶是一种通常用于此类目的的机制。我们的目标是设计一种轻量级的在线卸载策略，在令牌桶的约束下优化特定于应用的指标(例如，分类准确性)。本文提出了一种基于深度$Q$-网络(DQN)的策略，并论证了该策略的有效性及其在嵌入式设备上部署的可行性。值得注意的是，该策略可以处理复杂的输入模式，包括图像到达的相关性和分类精度。该评估是通过使用从ImageNet图像分类基准生成的合成痕迹在本地试验床上执行图像分类来执行的。有关这项工作的实施情况，请访问https://github.com/qiujiaming315/edgeml-dqn.
This article 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. This article 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. This article 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.