Mímir: Building and Deploying an ML Framework for Industrial IoT
Abstract
In this paper we describe Mímir, a production grade cloud and edge spanning ML framework for Industrial IoT applications. We first describe our infrastructure for optimized capture, streaming and multi-resolution storage of manufacturing data and its context. We then describe our workflow for scalable ML model training, validation, and deployment that leverages a manufacturing taxonomy and parameterized ML pipelines to determine the best metrics, hyper-parameters and models to use for a given task. We also discuss our design decisions on model deployment for real-time and batch data in the cloud and at the edge. Finally, we describe the use of the framework in building and deploying an application for Predictive Quality monitoring during a Plastics Extrusion manufacturing process.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
When a model is operational, the whole application stack is constantly monitored for performance metrics such as latency, throughput, and disk utilization.
“When a model is operational, the whole application stack is constantly monitored for performance metrics such as latency, throughput, disk utilization, etc. [39,45].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Model accuracy should be used to determine when a new model is needed.
“Model accuracy should be used to determine when a new model is needed [39].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
In a pull-pattern deployment, the target environment periodically polls for model updates and downloads when available.
“In a pull-pattern deployment, the target environment (host application running on, e.g., server or edge device) periodically polls for model updates and downloads when available [28,39,40].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Another reported method of integration is to serialize the model and load it at runtime, possibly with an ML framework optimized for production.
“Another reported method of integration is to serialize the model (e.g., into ONNXfoot_2 , HDF5, Joblib 4 ) and load it at runtime, possibly with an ML framework that is optimized for production [9,21,39,40].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Reviewed studies reporting deployment of ML models to IoT devices tended to construct custom deployment systems to deploy to edge devices.
“Our reviewed studies reporting deployment of ML models to Internet of Things (IoT) devices tended to construct custom deployment systems in order to deploy to edge devices [39].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Edge deployments are often reported as being more challenging than cloud deployments because of hardware resource heterogeneity, the typically distributed nature of edge devices, and possibly varying network connection quality.
“Edge deployments are often reported as being more challenging than cloud deployments because of hardware resource heterogeneity, the typically distributed nature of edge devices, and possibly varying network connection quality [7,10,20,22,39,53].”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Containerization is a commonly reported method of packaging ML models.
“Containerization is a commonly reported method of packaging ML models [39,42,45]”
From Operationalizing machine learning models: a systematic literature review (2022) · cites this paper as [39]
Cites
Low, Y., Bickson, D., Gonzalez, J. E., Guestrin, C., Kyrola, A., & Hellerstein, J. M. (2012) · Proceedings of the VLDB Endowment · doi:10.14778/2212351.2212354 · Cited by 1,656 · see citing works
Applied Machine Learning at Facebook: A Datacenter Infrastructure Perspective
Hazelwood, K., Bird, S., Brooks, D., Chintala, S., Diril, U., Dzhulgakov, D., Fawzy, M., Jia, B., Jia, Y., Kalro, A., et al. (2018) · 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2018.00059 · Cited by 590 · see citing works
Meidan, Y., Bohadana, M., Shabtai, A., Guarnizo, J., Ochoa, M., Tippenhauer, N. O., & Elovici, Y. (2017) · ACM Symposium on Applied Computing · doi:10.1145/3019612.3019878 · Cited by 424 · see citing works
A brief survey of machine learning methods and their sensor and IoT applications
Shanthamallu, U. S., Spanias, A., Tepedelenlioğlu, C., & Stanley, M. (2017) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa.2017.8316459 · Cited by 273 · see citing works
A survey of IoT platforms: Create Your Own Internet of Things
Singh, K. J., & Kapoor, D. S. (2017) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2016.2640718 · Cited by 212 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Operationalizing machine learning models: a systematic literature review
Kolltveit, A. B., & Li, J. (2022) · Proceedings of the 1st Workshop on Software Engineering for Responsible AI · doi:10.1145/3526073.3527584 · Cited by 34 · see citing works
- Authors
- Peticolas, D., Kirmayer, R., & Turaga, D.
- Venue
- 2019 International Conference on Data Mining Workshops (ICDMW)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 399-406
- ISSN
- 2375-9259 (ISSN-L)
- OpenAlex
- W2999338903
- Cited by
- 2
- References
- 5
- Citations by year
- 2024: 1 · 2022: 1
- FWCI
- 0.36
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE ... International Conference on Data Mining workshops (publishedVersion)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Digital Transformation in Industry
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Social Sciences › Decision Sciences › Management Science and Operations Research › Impact of AI and Big Data on Business and Society
- Keywords
- Industrial Internet of Things, machine learning framework, edge-cloud computing, stream processing, hyperparameter optimization, plastic extrusion
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
