aiqbench analysis
This paper provides empirical validation for deploying machine learning inference directly on AWS IoT Greengrass v2 to solve latency and bandwidth bottlenecks in industrial predictive maintenance. By comparing a hybrid edge-cloud architecture against a cloud-only baseline, the study quantifies significant reductions in data transmission costs while maintaining high anomaly detection accuracy during offline operation. The work addresses critical gaps in real-world MLOps feedback loops for edge devices, offering concrete metrics for engineers designing resilient factory floor systems.
Seamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance
arXiv:2610.14815v1 Announce Type: cross Abstract: Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architectures send all raw telemetry to central servers, which costs latency, bandwidth and resilience. This paper presents a hybrid cloud-edge architecture for manufacturing predictive maintenance built on AWS IoT Core and AWS IoT Greengrass v2, with local machine learning inference at the edge and selective cloud synchronization. We deploy two configurations on real AWS infrastructure and compare them: a cloud-only baseline (Configuration A) and the proposed hybrid edge architecture (Configuration B). We measure end-to-end inference latency, bandwidth consumption and inference accuracy. Configuration B cuts cloud-bound bandwidth by 86.8% (63.6 KB to 7.2 KB per 200-reading window) and decision latency by 256x (23.1 ms cloud round trip to 0.09 ms local inference). At the edge, with no cloud involvement, it keeps an anomaly-class F1 score of 0.84 and 91% recall. The evaluation also instruments system uptime and Stream Manager queuing under cloud disconnection; the quantitative disconnection experiment is left as planned work. Our review of the literature points to four gaps that this work addresses: the lack of empirically validated Greengrass v2 deployments for predictive maintenance, unquantified bandwidth savings from selective edge synchronization, unmeasured resilience under cloud disconnection, and the open MLOps feedback loop at the edge.
Abstract:Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architectures send all raw telemetry to central servers, which costs latency, bandwidth and resilience. This paper presents a hybrid cloud-edge architecture for manufacturing predictive maintenance built on AWS IoT Core and AWS IoT Greengrass v2, with local machine learning inference at the edge and selective cloud synchronization. We deploy two configurations on real AWS infrastructure and compare them: a cloud-only baseline (Configuration A) and the proposed hybrid edge architecture (Configuration B). We measure end-to-end inference latency, bandwidth consumption and inference accuracy. Configuration B cuts cloud-bound bandwidth by 86.8% (63.6 KB to 7.2 KB per 200-reading window) and decision latency by 256x (23.1 ms cloud round trip to 0.09 ms local inference). At the edge, with no cloud involvement, it keeps an anomaly-class F1 score of 0.84 and 91% recall. The evaluation also instruments system uptime and Stream Manager queuing under cloud disconnection; the quantitative disconnection experiment is left as planned work. Our review of the literature points to four gaps that this work addresses: the lack of empirically validated Greengrass v2 deployments for predictive maintenance, unquantified bandwidth savings from selective edge synchronization, unmeasured resilience under cloud disconnection, and the open MLOps feedback loop at the edge.
Conference paper draft in IEEE format, with code appendices. Already accepted in AiBThings - IEEE 4th International Conference on Artificial Intelligence, Blockchain and Internet of Things
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI)
arXiv:2610.14815 [cs.DC]
(or arXiv:2610.14815v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2610.14815 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 264 words
Related coverage
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
MLCommons Sets Participation Record with New MLPerf Inference v6.1 Benchmark Results
HPCwire · Sep 17, 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · May 21, 2026
News
Quantum Computing Report · Jul 25, 2026