Data Collection and Utilization Framework for Edge AI Applications

TL;DR

This paper presents a framework for collecting and utilizing data in edge AI applications, enabling efficient data transfer between edge devices and cloud systems to improve energy efficiency and model performance.

Contribution

It introduces a novel data collection and utilization framework that integrates FPGA-based edge platforms with cloud training for energy-efficient AI applications.

Findings

FPGA-based platform enhances object detection performance

Feasibility demonstrated for data collection and feedback in edge AI

Potential for continuous model improvement at the edge

Abstract

As data being produced by IoT applications continues to explode, there is a growing need to bring computing power closer to the source of the data to meet the response time, power dissipation and cost goals of performance-critical applications in various domains like the Industrial Internet of Things (IIoT), Automated Driving, Medical Imaging or Surveillance among others. This paper proposes a data collection and utilization framework that allows runtime platform and application data to be sent to an edge and cloud system via data collection agents running close to the platform. Agents are connected to a cloud system able to train AI models to improve overall energy efficiency of an AI application executed on an edge platform. In the implementation part, we show the benefits of FPGA-based platform for the task of object detection. Furthermore, we show that it is feasible to collect relevant data from an FPGA platform, transmit the data to a cloud system for processing and receiving feedback actions to execute an edge AI application energy efficiently. As future work, we foresee the possibility to train, deploy and continuously improve a base model able to efficiently adapt the execution of edge applications.