Performance analysis of local exit for distributed deep neural networks over cloud and edge computing

Abstract

In edge computing, most procedures, including data collection, data processing, and service provision, are handled at edge nodes and not in the central cloud. This decreases the processing burden on the central cloud, enabling fast responses to enddevice service requests in addition to reducing bandwidth consumption. However, edge nodes have restricted computing, storage, and energy resources to support computation-intensive tasks such as processing deep neural network (DNN) inference. In this study, we analyze the effect of models with single and multiple local exits on DNN inference in an edge-computing environment. Our test results show that a single-exit model performs better with respect to the number of local exited samples, inference accuracy, and inference latency than a multi-exit model at all exit points. These results signify that higher accuracy can be achieved with less computation when a single-exit model is adopted. In edge computing infrastructure, it is therefore more efficient to adopt a DNN model with only one or a few exit points to provide a fast and reliable inference service.

Research on Digital Economy and Human Resources Based on Fuzzy Clustering and Edge Computing

“…erefore, based on the combination of the existing research results of the same kind at home and abroad, this article firstly defines the connotation of the digital economy and its development characteristics and builds a digital economy development evaluation index system on this basis and then conducts a review of the development status of China's digital economy. e statistical evaluation also reveals the main problems in the development, provides data support for the correct judgment of the current situation of my country's digital economy development, and plays a role in inducing subsequent similar quantitative research [16,17]. A schematic diagram of the digital economy research process is shown in Figure 1.…”

Finite Element Structure Analysis of Automobile Suspension Control Arm Based on Neural Network Control

“…e simulation results are considered an extremely important theoretical basis for structure design and optimization of the spot-welding robot [13].…”

“…e strain matrix B for any point in the element is the element strain matrix. Secondly, by using constitutive equation, the relationship between node displacement and element stress is derived from formula (13).…”

Research on Mining of Applied Mathematics Educational Resources Based on Edge Computing and Data Stream Classification

“…As the main front of mathematics education, ecological research in mathematics classrooms has received more and more attention [20,21].…”