DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels

TL;DR

DFTS2 is a simulation framework that models deep feature transmission over unreliable channels in edge-cloud AI systems, aiding in understanding and improving system robustness against packet loss.

Contribution

This paper introduces DFTS2, a novel TensorFlow-based simulation tool for analyzing CI system performance under packet loss and evaluates various concealment methods for image classification.

Findings

DFTS2 accurately simulates CI system behavior under different channel conditions.

Packet loss concealment methods significantly improve classification accuracy.

The framework facilitates development of error control strategies for edge-cloud AI.

Abstract

In edge-cloud collaborative intelligence (CI), an unreliable transmission channel exists in the information path of the AI model performing the inference. It is important to be able to simulate the performance of the CI system across an imperfect channel in order to understand system behavior and develop appropriate error control strategies. In this paper we present a simulation framework called DFTS2, which enables researchers to define the components of the CI system in TensorFlow~2, select a packet-based channel model with various parameters, and simulate system behavior under various channel conditions and error/loss control strategies. Using DFTS2, we also present the most comprehensive study to date of the packet loss concealment methods for collaborative image classification models.