Adaptive Industrial Iot/Cps Messaging Strategies For Improved Edge Compute Utility

Messaging strategies for data transport play a central role in large scale IIoT/CPS systems. Research to date in these domains has focused on comparative studies of different messaging protocols and various congestion control techniques. This paper presents an experimental evaluation of the latency and throughput for different message payload strategies using the same protocol combined with a novel congestion control algorithm. The results provide key insights based on experiments carried out in a real-world IOT wireless sensor network deployment. The approach presented dynamically varies the message schema and sizes in response to the utilization of edge nodes. The goal is to achieve the highest possible data throughput that fits within the available edge based compute capacity without requiring auto-scaling of back end cloud resources.