Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing

TL;DR

This paper introduces Edgent, a framework that enhances real-time DNN inference on mobile devices by adaptively partitioning computation between device and edge, and employing early exiting strategies to reduce latency in varying network conditions.

Contribution

The paper proposes a novel edge computing framework with adaptive DNN partitioning and right-sizing, addressing latency issues in mobile AI inference under static and dynamic network environments.

Findings

Edgent achieves significant latency reduction in DNN inference.

The framework effectively adapts to network fluctuations with high accuracy.

Experimental results validate Edgent's practicality on Raspberry Pi and PC.

Abstract

As a key technology of enabling Artificial Intelligence (AI) applications in 5G era, Deep Neural Networks (DNNs) have quickly attracted widespread attention. However, it is challenging to run computation-intensive DNN-based tasks on mobile devices due to the limited computation resources. What's worse, traditional cloud-assisted DNN inference is heavily hindered by the significant wide-area network latency, leading to poor real-time performance as well as low quality of user experience. To address these challenges, in this paper, we propose Edgent, a framework that leverages edge computing for DNN collaborative inference through device-edge synergy. Edgent exploits two design knobs: (1) DNN partitioning that adaptively partitions computation between device and edge for purpose of coordinating the powerful cloud resource and the proximal edge resource for real-time DNN inference; (2) DNN right-sizing that further reduces computing latency via early exiting inference at an appropriate intermediate DNN layer. In addition, considering the potential network fluctuation in real-world deployment, Edgentis properly design to specialize for both static and dynamic network environment. Specifically, in a static environment where the bandwidth changes slowly, Edgent derives the best configurations with the assist of regression-based prediction models, while in a dynamic environment where the bandwidth varies dramatically, Edgent generates the best execution plan through the online change point detection algorithm that maps the current bandwidth state to the optimal configuration. We implement Edgent prototype based on the Raspberry Pi and the desktop PC and the extensive experimental evaluations demonstrate Edgent's effectiveness in enabling on-demand low-latency edge intelligence.