English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Anomaly detection is increasingly important to handle the amount of sensordata in Edge and Fog environments, Smart Cities, as well as in Industry 4.0. Toensure good results, the utilized ML models need to be updated periodically toadapt to seasonal changes and concept drifts in the sensor data. Although theincreasing resource availability at the edge can allow for in-situ execution ofmodel training directly on the devices, it is still often offloaded to fogdevices or the cloud.  In this paper, we propose Local-Optimistic Scheduling (LOS), a method forexecuting periodic ML model training jobs in close proximity to the datasources, without overloading lightweight edge devices. Training jobs areoffloaded to nearby neighbor nodes as necessary and the resource consumption isoptimized to meet the training period while still ensuring enough resources forfurther training executions. This scheduling is accomplished in adecentralized, collaborative and opportunistic manner, without full knowledgeof the infrastructure and workload. We evaluated our method in an edgecomputing testbed on real-world datasets. The experimental results show thatLOS places the training executions close to the input sensor streams, decreasesthe deviation between training time and training period by up to 40% andincreases the amount of successfully scheduled training jobs compared to anin-situ execution.

LOS: Local-Optimistic Scheduling of Periodic Model Training For Anomaly Detection on Sensor Data Streams in Meshed Edge Networks