Data Collection and Utilization Framework for Edge AI Applications
This addresses energy efficiency problems for edge AI applications in domains like IIoT and automated driving, but it is incremental as it builds on existing data collection and cloud-edge integration methods.
The paper tackles the challenge of managing data from IoT applications by proposing a framework that collects runtime data via agents at the edge and uses cloud-based AI training to improve energy efficiency for edge AI applications, demonstrating feasibility with an FPGA-based object detection implementation.
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.