Randomization of Data Generation Times Improves Performance of Predictive IoT Networks

A challenge of IoT networks is to offer Quality of Service (QoS) and meet deadline requirements when packets from numerous IoT devices must be forwarded. Thus this paper introduces the Randomization of flow Generation Times (RGT) that smooths incoming IoT traffic so that QoS improves and packet loss is avoided. When the “Earliest Deadline First” (EDF) or “Priority based on Average Load” (PAL) scheduling algorithms are used, simulation results show that RGT provides significantly better performance, for a small additional computational cost at each device, providing a useful performance improvement for IoT networks.