Comparing Admission Control Architectures for Real-Time Ethernet

Abstract

Industry 4.0 and Autonomous Driving are emerging resource-intensive distributed application domains that deal with open and evolving environments. These systems are subject to stringent resource, timing, and other non-functional constraints, as well as frequent reconfiguration. Thus, real-time behavior must not preclude operational flexibility. This combination is motivating ongoing efforts within the Time Sensitive Networking (TSN) standardization committee to define admission control mechanisms for Ethernet. Existing mechanisms in TSN, like those of AVB, its predecessor, follow a distributed architecture that favors scalability. Conversely, the new mechanisms envisaged for TSN (IEEE 802.1Qcc) follow a (partially) centralized architecture, favoring short reconfiguration latency. This paper shows the first quantitative comparison between distributed and centralized admission control architectures concerning reconfiguration latency. Here, we compare AVB against a dynamic real-time reconfigurable Ethernet technology with centralized management, namely HaRTES. Our experiments show a significantly lower latency using the centralized architecture. We also observe the dependence of the distributed architecture in the end nodes' performance and the benefit of having a protected channel for the admission control transactions. INDEX TERMS Ethernet, TSN, AVB, HaRTES, real-time communication, dynamic reconfiguration, admission control protocol.

Distributed Authentication Model for Secure Network Connectivity in Network Separation Technology

“…The conventional method of [40] and the proposed DAM4SNC were implemented in the same simulation environment. By disabling the differentiated functions such as aggregation and trust level of the DAM4SNC in this simulation environment, we confirmed the baseline of the environmental conditions for comparing DAM4SNC and conventional performance.…”

“…The performance of the proposed DAM4SNC method and the conventional method were compared and analyzed in the same simulation environment implemented with Python 3. In the simulation model, the core function of the typical centralized method [40] was implemented for the conventional method. The simulator for these two methods was implemented in a PC environment with a 3.80 GHz Intel ® Core ™ i7-10700K CPU and 32 GB of RAM.…”

“…For simplicity in effectively comparing the proposed ideas with conventional methods, we implemented only key functions related to authentication. Latency and authentication level were measured in the same way as conventional research methodologies [40] in the simulation model. When the simulation is performed, a network is configured with randomly distributed nodes, and the conventional method is a model in which one central node authenticates and connects other nodes, and the proposed method is a model distributedly authenticated and connected by the DAM4SNC mechanism.…”

“…transfer data n OUTPUT: Latency Algorithms 1-3 show the pseudo codes for the simulation of the proposed DAM4SNC and conventional centralized authentication methods, respectively. The CON stands for a conventional centralized network model [40]. The conventional centralized authentication methods do not employ frame aggregation and trust node for data communications.…”

Delay-Guaranteeing Admission Control for Time-Sensitive Networking Using the Credit-Based Shaper

“…A main advantage of TSN is the possibility to include mixed traffic types on the same medium. Traffic criticality can be classified as hard real-time (HRT), soft real-time (SRT), and non-real-time (NRT) traffic [5], [6]. To reserve HRT traffic in TSN, previous works propose the use of time-triggered (TT) gates which allow for explicit time-slot reservations of flows using a globally synchronized clock [7].…”