Location
Hilton Hawaiian Village, Honolulu, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
3-1-2024 12:00 AM
End Date
6-1-2024 12:00 AM
Description
The aim of the current paper is to present a dynamic model of managing nodes of the Fog layer in Edge-Fog-Cloud systems of the Internet of Things in scientific partnerships. The article is a response to the problem of managing Fog nodes in IoT systems, where classic management mechanisms, based on schedules, become insufficient. It also addresses the problem of delays in data processing in the Cloud layer, which is significant and affects decision-making processes. Therefore, the authors propose a Business Intelligence model based on association rules that predict the number of agents of Fog layer nodes. This prediction allows for the design of nodes in which the requirements of the scientific partner (number of processor cores, RAM size, classifier type, number of processed records, classifier working time) are the basis for selecting the appropriate number of Fog node agents. The model was validated by using association rules to select the appropriate number of Fog node agents for the domain of air quality data processed in three scientific partnerships using different types of data classifiers.
Recommended Citation
Behrens, Grit; Karatzas, Kostas; and Orlowski, Cezary, "Business Intelligence Fog IoT node development model for Big Data processing of air quality in scientific partnerships" (2024). Hawaii International Conference on System Sciences 2024 (HICSS-57). 3.
https://aisel.aisnet.org/hicss-57/cl/bi_for_organizations/3
Business Intelligence Fog IoT node development model for Big Data processing of air quality in scientific partnerships
Hilton Hawaiian Village, Honolulu, Hawaii
The aim of the current paper is to present a dynamic model of managing nodes of the Fog layer in Edge-Fog-Cloud systems of the Internet of Things in scientific partnerships. The article is a response to the problem of managing Fog nodes in IoT systems, where classic management mechanisms, based on schedules, become insufficient. It also addresses the problem of delays in data processing in the Cloud layer, which is significant and affects decision-making processes. Therefore, the authors propose a Business Intelligence model based on association rules that predict the number of agents of Fog layer nodes. This prediction allows for the design of nodes in which the requirements of the scientific partner (number of processor cores, RAM size, classifier type, number of processed records, classifier working time) are the basis for selecting the appropriate number of Fog node agents. The model was validated by using association rules to select the appropriate number of Fog node agents for the domain of air quality data processed in three scientific partnerships using different types of data classifiers.
https://aisel.aisnet.org/hicss-57/cl/bi_for_organizations/3