A Machine Learning Framework for the Internet of Things
Project Summary (NSF Award 1553340)
The Internet of Things describes a network of devices, from RFID tags, to smart thermostats, to light bulbs, that can sense and communicate information. It is predicted that by 2020, there will be 25 to 50 billion devices in the Internet of Things. This massive network and the data it generates will enable new applications in a wide range of critical domains including environmental management, smart infrastructure, and healthcare. To achieve this vision, it is crucial to be able to quickly analyze and learn from the massive amount of generated data. Current approaches for big data analytics require full data transfer to a platform with large computational power, such as the cloud. Given the projected explosion in the number of devices and the resulting data generation rate, this is not feasible.
The proposed research integrates tools and theory from machine learning, distributed computing, and networked systems in three main thrusts that include; a computational framework that provides an abstraction for algorithm design and implementation that is flexible enough to support a wide collection of machine learning methods, a framework implementation that provides a stable platform for algorithm developers by masking device heterogeneity, devices failures, and the network dynamics of the Internet of Things, and development and implementation of techniques to adapt the network and computation to support algorithm execution with performance guarantees.
People
- Stacy Patterson (PI)
- Erika Mackin - PhD Student
- Anirban Das - PhD Student
- Brian Park - Undergraduate Researcher 2018
- Shigeru Imai - Postdoc 2018
- Connor Foody - MS 2018
- William Kronmiller - MS 2017
- Perry Adams - Undergraduate Reseracher 2016
- Yuhao Yi - Visiting Scholar 2016-2017
Software and Benchmarks
- EdgeBench: An open-source benchmark suite for serverless edge computing platforms
- Spindle: An extension of Spark Streaming for Edge Devices
Related Publications
- Imai, I., C. Varela, and S. Patterson, "A Performance Study of Geo-Distributed IoT Data Aggregation for Fog Computing", Procedings of the 1st Workshop on Managed Fog-to-Cloud, 2018.
- Das, A., S. Patterson, and M. Wittie, "EdgeBench: Benchmarking Edge Computing Platforms", Proceedings of the 4th International Workshop on Serverless Computing, 2018.
- Mackin, E. and S. Patterson, "Submodular Optimization
for Consensus Networks with Noise-Corrupted Leaders", IEEE Transctions on Automatic Control, 2018 (accepted).
- Yi, Y., Z. Zhang, and S. Patterson, "Scale-free Loopy Structure is Resistant to Noise in Consensus Dynamics in Complex Networks", IEEE Transactions on Cybernetics, 2018 (accepted).
- Das, A., Y. Yi, S. Patterson, B. Bamieh, and Z. Zhang, "Convergence Rate of Consensus in a Network of Networks", Proceedings of the 57th IEE Conference on Decision and Control, 2018.
-
Mackin, E., and S. Patterson, "Second Order Consensus with Absolute Information", Proceedings of the 57th IEEE Conference on Decision and Control, 2018.
- Imai, S., S. Patterson, and C. Varela,
"Uncertainty-Aware Elastic Virtual Machine Scheduling for Stream Processing Systems", Proceedings of the 18th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), 2018.
- Patterson, S., Y. Yi, and Z. Zhang,
"A Resistance Distance-Based Approach for Optimal Leader Selection in Noisy Consensus Networks" IEEE Transactions on Control of Network Systems, 2018 (pre-print).
- Patterson, S., N. McGlohon, and K. Dyagilev,
"Optimal k-Leader Selection for Coherence and Convergence Rate in One-Dimensional Networks",
IEEE Transactions on Control of Network Systems, 2017.
- Hollis, B., S. Patterson, and J.Trinkle,
"Adaptive Basis Selection for Compressed Sensing in Robotic Tactile Skins",
IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2017.
- Mackin, E., and S. Patterson,
"Optimizing the Coherence of Composite Networks
",
Proceedings of the American Control Conference, 2017.
- S. Patterson,
"Optimizing coherence in 1-D noisy consensus networks with noise-free leaders
",
Proceedings of the American Control Conference, 2017.
- Imai, S., S. Patterson, and C. Varlea,
Maximum Sustainable throughput Prediction for Data Stream Processing over Public Clouds,
Proceedings of the 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), 2017.
- Chen, Q., B. Bellows, M. P. Wittie, S. Patterson, and Q. Yang,
"MOVESET: MOdular VEhicle SEnsor Technology",
IEEE Vehicular Networking Conference, 2016.
- Imai, S., S. Patterson, and C. Varela,
"Cost-Efficient Elastic Stream Processing Using Application-Agnostic Performance Prediction",
Proceedings of the16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing: Doctoral Symposium , 2016.
- McGlohon, N., and S. Patterson,
"Distributed Semi-Stochastic Optimization with Quantization Refinement",
Proceedings of the American Control Conference , 2016.
- Imai, S., S. Patterson, and C. Varela,
"Elastic Virtual Machine Scheduling for Continuous Air Traffic Optimization",
Proceedings of the16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, 2016.
News Articles