Automated Design System of Automotive Ethernet Utilizing Simulation-Based Machine Learning

In recent years, Ethernet is attracting attention as a technology for constructing in-vehicle networks. However, there is a concern that bottlenecks may occur due to concentration of a large amount of data on specific parts of the network, resulting in the situation that critical data related to vehicle control does not reach the ECU in real-time. Therefore, in this study, we propose a new automated design system of in-vehicle Ethernet utilizing a machine learning technology for deriving appropriate QoS control parameter.