Back to Search Start Over

Collaborative Inference in DNN-based Satellite Systems with Dynamic Task Streams

Authors :
Guan, Jinglong
Zhang, Qiyang
Murturi, Ilir
Donta, Praveen Kumar
Dustdar, Schahram
Wang, Shangguang
Publication Year :
2023

Abstract

As a driving force in the advancement of intelligent in-orbit applications, DNN models have been gradually integrated into satellites, producing daily latency-constraint and computation-intensive tasks. However, the substantial computation capability of DNN models, coupled with the instability of the satellite-ground link, pose significant challenges, hindering timely completion of tasks. It becomes necessary to adapt to task stream changes when dealing with tasks requiring latency guarantees, such as dynamic observation tasks on the satellites. To this end, we consider a system model for a collaborative inference system with latency constraints, leveraging the multi-exit and model partition technology. To address this, we propose an algorithm, which is tailored to effectively address the trade-off between task completion and maintaining satisfactory task accuracy by dynamically choosing early-exit and partition points. Simulation evaluations show that our proposed algorithm significantly outperforms baseline algorithms across the task stream with strict latency constraints.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2311.06073
Document Type :
Working Paper