Towards IoT Analytics. A vf-OS Approach

New challenges faced by the current Industrial Internet of Things (IIoT) are stringent latency, capacity constraints, uninterrupted devices with intermittent connectivity cannot be solved with centralized cloud computing architecture [1]. Sending all the data to the cloud will require prohibitively high network bandwith [2]. vf-OS - Virtual Factory Open Operating System - is a project funded by the H2020 Framework Programme of the European Commission under Grant Agreement 723710, with the purpose to provide an Open Operating System for Virtual Factories composed of a kernel, application programming interface, and middleware specifically designed for the factory of the future. This paper presents the Virtual Open Operating System (vf-OS) approach to IoT Analytics, and how vf-OS IO (Input/Output) components and vf-OS analytics can be used to capture data from sensors and Program Logic Controllers (PLCs) to generate and run machine learning models to do analytics in the cloud and in the edge. The main contribution of the paper is the proposal of new architectural solutions and providing alternative scenarios for developers developing applications for the manufacturing sector