Architectural ML Framework for IoT Services Delivery Based on Microservices

Tatiana Atanasova, Kristina Dineva
The Internet of Things (IoT) is the interconnection of devices and services that allows free data flow. Managing and analyzing this data is the actual added value that IoT is beneficial for. Machine learning plays an increasingly important role in performing data analysis in IoT solutions. This paper presents an architectural framework with machine learning solutions implemented as a service in the microservice group. This architectural framework for IoT services delivery is designed following the Agile methodology. The requirements for the software architecture and expected functionalities of the system are defined. The microservices collection is explained by providing a separate description for every service. Machine learning (ML) analytics on IoT (as the processing paradigm for intelligently handling the IoT data) is represented as a part of the microservice platform. Several strategic advantages of the proposed microservice-based IoT architecture over others are discussed together with implementation issues.