ACSOS 2021
Mon 27 September - Fri 1 October 2021 Washington, DC, United States

Anomaly detection is increasingly important to handle the amount of sensor data in Edge and Fog environments, Smart Cities, as well as in Industry 4.0. To ensure good results, the utilized ML models need to be updated periodically to adapt to seasonal changes and concept drifts in the sensor data. Although the increasing resource availability at the edge can allow for in-situ execution of model training directly on the devices, it is still often offloaded to fog devices or the cloud.

In this paper, we propose Local-Optimistic Scheduling (LOS), a method for executing periodic ML model training jobs in close proximity to the data sources, without overloading lightweight edge devices. Training jobs are offloaded to nearby neighbor nodes as necessary and the resource consumption is optimized to meet the training period while still ensuring enough resources for further training executions. This scheduling is accomplished in a decentralized, collaborative and opportunistic manner, without full knowledge of the infrastructure and workload.

We evaluated our method in an edge computing testbed on real-world datasets. The experimental results show that LOS places the training executions close to the input sensor streams, decreases the deviation between training time and training period by up to 40% and increases the amount of successfully scheduled training jobs compared to an in-situ execution.

Wed 29 Sep

Displayed time zone: Eastern Time (US & Canada) change

13:00 - 14:30
Software and Systems Engineering for Autonomic and Self-Organizing SystemsMain Track at AUDITORIUM 1
Chair(s): Aniruddha Gokhale Vanderbilt University
LOS: Local-Optimistic Scheduling of Periodic Model Training For Anomaly Detection on Sensor Data Streams in Meshed Edge Networks
Main Track
Sören Becker TU Berlin, Florian Schmidt TU Berlin, Lauritz Thamsen TU Berlin, Ana Juan Ferrer Universitat Oberta de Catalunya, Odej  Kao Technische Universität Berlin
On Adapting SNMP as Communication Protocol in Distributed Control Loops for Self-adaptive Systems
Main Track
Ilja Shmelkin Technische Universität Dresden, Germany, Thomas Springer Technical University of Dresden
Towards Highly Automated Machine-Learning-Empowered Monitoring of Motor Test Stands
Main Track
Diego Botache University of Kassel, Florian Bethke University of Kassel, Martin Hardieck University of Kassel, Maarten Bieshaar University of Kassel, Ludwig Brabetz University of Kassel, Mohamed Ayeb University of Kassel, Peter Zipf University of Kassel, Bernhard Sick University of Kassel
Engineering Adaptive Authentication
Main Track
Alzubair Hassan University College Dublin, Bashar Nuseibeh The Open University (UK) & Lero (Ireland), Liliana Pasquale University College Dublin & Lero