AI-GeneSI: Exploiting generative AI for autonomous generation of the southbound interface in the IoT

Virtual objects, which are representations in the digital world of physical entities, uses the data collected by one or several sensor nodes to operate. To overcome the diversity and heterogeneity of protocols implemented by different sensor nodes and the way in which sensor data is represented, it is convenient to exploit appropriate components referred to as “southbound interfaces” in this paper. The objective of the southbound interface is to convert the communication protocols implemented by sensor nodes and virtual objects and to harmonize data representations. The implementation of the southbound interfaces is not a complex task, however it is extremely specific of the current setting, which turns in low reusability of the code, and is time-consuming. In this paper, a methodology named AI-GeneSI is proposed to exploit Large Language Models (LLM)s to generate the code to communicate with the southbound interface. Such code is utilized to create and deploy a microservice which implements the southbound interface functions. A prototype of the proposed methodology has been implemented to demonstrate the feasibility of the proposed approach.