Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices

TL;DR

This paper introduces a low-latency, dynamic licensing architecture for deploying deep neural networks on edge devices, enabling efficient model updates and version control through cloud synergy and access permissions.

Contribution

It presents a novel architecture that facilitates dynamic model licensing and low-latency updates for neural networks on edge devices using cloud integration and access control.

Findings

Enables low-latency model updates on edge devices.

Supports multiple model versions with a single deployment.

Facilitates secure, permission-based model access.

Abstract

Along with the rapid development in the field of artificial intelligence, especially deep learning, deep neural network applications are becoming more and more popular in reality. To be able to withstand the heavy load from mainstream users, deployment techniques are essential in bringing neural network models from research to production. Among the two popular computing topologies for deploying neural network models in production are cloud-computing and edge-computing. Recent advances in communication technologies, along with the great increase in the number of mobile devices, has made edge-computing gradually become an inevitable trend. In this paper, we propose an architecture to solve deploying and processing deep neural networks on edge-devices by leveraging their synergy with the cloud and the access-control mechanisms of the database. Adopting this architecture allows low-latency DNN model updates on devices. At the same time, with only one model deployed, we can easily make different versions of it by setting access permissions on the model weights. This method allows for dynamic model licensing, which benefits commercial applications.