Slack-based Traffic Shaping for Real-time Ethernet Networks

Ethernet has been identified as the most promising technology to be used as the backbone for the communication infrastructure in future automotive networks. Several traffic shapers have been proposed to meet the requirements of low latency and high throughput in automotive applications. Safety-critical traffic typically has strict timing requirements, however, meeting those requirements well ahead of time often brings no benefits. These spare capacities, called slack, could be exploited for the benefit of less critical but still time-sensitive traffic. Existing traffic shaping policies do not offer efficient possibilities to reduce and/or exploit this slack. In this paper, we propose a novel, scalable approach for slack-based traffic shaping, which can significantly improve the performance of time-sensitive traffic, at the expense of the slack of safety-critical traffic, which still fulfils all timing requirements. The promising results of the experimental evaluation suggest that the proposed approach represents an efficient means for meeting multi-dimensional and versatile requirements of current- and next-generation automotive applications.