LEM: a Tool for Large-Scale Workflow Control in Edge-Based Industry 5.0 Applications

Edge computing is poised to greatly boost Industry 5.0 by providing a computing substrate that can run highly specialized applications with minimal latency, reducing the requirements on computational resources at the end-user and allowing the sharing of resources between multiple end-users. The intended services and workflows need to be designed, configured and deployed at target edge devices, and during operation their status needs to be monitored. There are several industrial frameworks that provide such functionalities, but often there is little support to execute them simultaneously over many target devices. In this paper we present the LEM tool, a tool that enables the management (monitor, configure, deploy) of workflows in a large number of edge devices. The tool connects to existing industrial frameworks to provide these functionalities, abstracting the low level configuration aspects of each framework and enabling simultaneous configuration of multiple devices, a feature that many frameworks do not support. The tool offers a web-based GUI that allows the infrastructure manager to conveniently check the status of all devices and flows running in each device, deploy new flows on selected devices, and start and stop flows. Experimental measurements show residual response time overhead as the number of devices increases.