Edge Computing Architectures for IoT Data Aggregation in Industrial Manufacturing

Abstract

This paper discusses edge computing platform to be used in aggregating IoT data in a production scenario. As IoT sensors generate huge quantities of data, edge computing is a feasible solution to work with such data and aggregate them near where they originate, thus reducing the amount of latency and saving on bandwidth. The research paper has a design that uses edge and fog computing to support distributed data processing in the network edge to facilitate real-time analytics. Running sensor data on the platform eliminates the requirement to have high bandwidth communication to centralized cloud servers and enhances responsiveness of the system and network traffic jams are minimized. In addition, edge analytics plays a critical role when it comes to making quick decisions, as it creates real-time information about manufacturing processes. The framework facilitates predictive maintenance where sensor data is used to detect any signs of failure in equipment early before it goes out of business, thereby minimizing the time spent on downtime and enhancing operational efficiency. The document outlines some key architectural frameworks of applying edge computing to the industrial IoT environment, which places emphasis on local data processing, machine learning algorithms, and cloud-based services. The proposed system lay out will simplify the manufacturing systems with scalable, low-latency, bandwidth efficient systems, which enable operational intelligence and predictive maintenance.