Orchestrating Networked Machine Learning Applications Using Autosteer

doi:10.1109/MIC.2022.3180907

Orchestrating Networked Machine Learning Applications Using Autosteer

2022-11-01

0

OA

AI

DOI：10.1109/MIC.2022.3180907

Original

Original request for help

Save

Abstract

En 中文

A platform for orchestrating networked machine learning (ML) applications over distributed environments is described. ML applications are transformed into automated pipelines that manage the whole application lifecycle and production-grade implementations are automatically constructed. We present AUTOSTEER, a software platform that can deploy ML applications on various hardware resources-interconnected using heterogeneous network resources-across cloud and edge devices. Device placement optimization and model adaptation are used as control actions to support application requirements and maximize the performance of ML model execution over heterogeneous computing resources. The performance of deployed applications is continually monitored at runtime to overcome performance degradation due to incorrect application parameter settings or model decay. Three real-world applications are used to demonstrate how AUTOSTEER can support application deployment and runtime performance guarantees.

Keywords:

Performance evaluation

Degradation

Training data

Adaptation models

Cloud computing

Runtime

Computational modeling

Orchestrating Networked Machine Learning Applications Using Autosteer

Abstract

Journal

Organization