A Fast Edge-Based Synchronizer for Tasks in Real-Time Artificial Intelligence Applications

TL;DR

This paper introduces a fast, game-theoretic, edge-based synchronization method for real-time AI tasks that improves timing alignment across devices, enhancing data quality and processing efficiency.

Contribution

It proposes a novel clustering and static synchronization point selection approach using game theory for improved real-time task synchronization in edge AI.

Findings

Outperforms existing synchronization schemes in simulation

Reduces synchronization delay significantly

Maintains high training accuracy with faster convergence

Abstract

Real-time artificial intelligence (AI) applications mapped onto edge computing need to perform data capture, process data, and device actuation within given bounds while using the available devices. Task synchronization across the devices is an important problem that affects the timely progress of an AI application by determining the quality of the captured data, time to process the data, and the quality of actuation. In this paper, we develop a fast edge-based synchronization scheme that can time align the execution of input-output tasks as well compute tasks. The primary idea of the fast synchronizer is to cluster the devices into groups that are highly synchronized in their task executions and statically determine few synchronization points using a game-theoretic solver. The cluster of devices use a late notification protocol to select the best point among the pre-computed synchronization points to reach a time aligned task execution as quickly as possible. We evaluate the performance of our synchronization scheme using trace-driven simulations and we compare the performance with existing distributed synchronization schemes for real-time AI application tasks. We implement our synchronization scheme and compare its training accuracy and training time with other parameter server synchronization frameworks.