Abstract:

Time Sensitive Networking (TSN) is a process that encompasses a set of standards designed to increase the determinism of packet transmission in converged networks.

The main purpose of this method is to provide mechanisms to ensure low and predictable transmission latency and high availability for demanding applications such as real-time audio/video streaming, automotive and industrial control. To provide the necessary guarantees, engineers came up with a formula called "Periodic Transmission Ethernet". Achieving the required quality of service (QoS) levels requires the appropriate selection and configuration of modeling mechanisms, but this is difficult due to the diverse requirements for coexisting flows in the presence of potential end-system-induced fluctuations.

Thus, a method for transmitting Ethernet messages is described in a real-time distributed system that implements a periodic control algorithm, where many network nodes and at least one switch meet, connected to each other through a communication channel. However, the TTE static segment scheduling problem is considered to be an NP-complete problem due to its constraints, complex topology, and large scale uncertainty (i.e., large volume of packets). To improve the TT traffic scheduling performance, this paper aims to present a method that integrates genetic algorithms (GA) to optimize bandwidth under quality of service (QoS) constraints and minimize total energy consumption.