Elastic Queueing Engine for Time Sensitive Networking

Abstract

In this work we introduce the concept of Elastic Queueing Engine (EQE) for Time Sensitive Networking (TSN) which is a new networking-optimized queueing strategy designed to maximize Quality of Service (QoS) and usability of resources in time sensitive networks. The proposed dynamic run-time adaptation of queues to network status exploits usability of resources by introducing three new degrees of elasticity in Hardware (HW), i.e., the system is able to dynamically adapt to events in incoming traffic by optimizing the usage of available resources. The three new degrees of elasticity introduced by EQE are: dynamic queues size, dynamic Internal Priority Value (IPV) management and dynamic Gate Control List (GCL). Apart from inventing the queueing closed-loop control algorithms, EQE synthesizes these three functionalities in HW as co-processors attached to the system CPU to guarantee a real-time response to ingress frames, aimed at contributing towards fail-safe and fail-operational In-Vehicle Network (IVN) solutions. Our results show that as long as there is available memory in the system, EQE for TSN can completely avoid frame drops in scenarios where static queues systems would be compromised, while other network KPIs (maximum latency, cost) remain similar to implementations without the proposed new features.