当前位置:
X-MOL 学术
›
IEEE Open J. Intell. Transp. Syst.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ITANS: Incremental Task and Network Scheduling for Time-Sensitive Networks
IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2022-04-28 , DOI: 10.1109/ojits.2022.3171072 Anna Arestova 1 , Wojciech Baron 1 , Kai-Steffen J. Hielscher 1 , Reinhard German 1
IEEE Open Journal of Intelligent Transportation Systems Pub Date : 2022-04-28 , DOI: 10.1109/ojits.2022.3171072 Anna Arestova 1 , Wojciech Baron 1 , Kai-Steffen J. Hielscher 1 , Reinhard German 1
Affiliation
Recent trends such as automated driving in the automotive field and digitization in factory automation confront designers of real-time systems with new challenges. These challenges have arisen due to the increasing amount of data and an intensified interconnection of functions. For distributed safety-critical systems, this progression has the impact that the complexity of scheduling tasks with precedence constraints organized in so-called cause-effect chains increases the more data has to be exchanged between tasks and the more functions are involved. Especially when data has to be transmitted over an Ethernet-based communication network, the coordination between the tasks running on different end-devices and the network flows has to be ensured to meet strict end-to-end deadlines. In this work, we present an incremental heuristic approach that computes schedules for distributed and data-dependent cause-effect chains consisting of multi-rate tasks and network flows in time-sensitive networks. On the one hand, we provide a common task model for tasks and network flows. On the other hand, we introduce the concept of earliest and latest start times to speed up the solution discovery process and to discard infeasible solutions at an early stage. Our algorithm is able to solve large problems for synthetic network topologies with randomized data dependencies in a few seconds on average under strict end-to-end deadlines. We have achieved a high success rate for multi-rate cause-effect chains and an even better result for homogeneous or harmonic chains. Our approach also showed low jitter for homogeonous cause-effect chains.
中文翻译:
ITANS:时间敏感网络的增量任务和网络调度
汽车领域的自动驾驶和工厂自动化的数字化等最新趋势为实时系统的设计人员带来了新的挑战。由于数据量的增加和功能的加强互连,这些挑战已经出现。对于分布式安全关键系统,这种进展会产生影响,即在所谓的因果链中组织具有优先约束的调度任务的复杂性增加,任务之间必须交换的数据越多,涉及的功能越多。特别是当必须通过基于以太网的通信网络传输数据时,必须确保在不同终端设备上运行的任务与网络流之间的协调,以满足严格的端到端期限。在这项工作中,我们提出了一种增量启发式方法,该方法计算分布式和数据相关的因果链的时间表,包括多速率任务和时间敏感网络中的网络流。一方面,我们为任务和网络流提供了一个通用的任务模型。另一方面,我们引入了最早和最晚开始时间的概念,以加快解决方案的发现过程,并在早期阶段丢弃不可行的解决方案。我们的算法能够在严格的端到端期限内平均在几秒钟内解决具有随机数据依赖关系的合成网络拓扑的大问题。我们在多速率因果链上取得了很高的成功率,在同构或谐波链上取得了更好的结果。我们的方法还显示出同质因果链的低抖动。
更新日期:2022-04-28
中文翻译:
ITANS:时间敏感网络的增量任务和网络调度
汽车领域的自动驾驶和工厂自动化的数字化等最新趋势为实时系统的设计人员带来了新的挑战。由于数据量的增加和功能的加强互连,这些挑战已经出现。对于分布式安全关键系统,这种进展会产生影响,即在所谓的因果链中组织具有优先约束的调度任务的复杂性增加,任务之间必须交换的数据越多,涉及的功能越多。特别是当必须通过基于以太网的通信网络传输数据时,必须确保在不同终端设备上运行的任务与网络流之间的协调,以满足严格的端到端期限。在这项工作中,我们提出了一种增量启发式方法,该方法计算分布式和数据相关的因果链的时间表,包括多速率任务和时间敏感网络中的网络流。一方面,我们为任务和网络流提供了一个通用的任务模型。另一方面,我们引入了最早和最晚开始时间的概念,以加快解决方案的发现过程,并在早期阶段丢弃不可行的解决方案。我们的算法能够在严格的端到端期限内平均在几秒钟内解决具有随机数据依赖关系的合成网络拓扑的大问题。我们在多速率因果链上取得了很高的成功率,在同构或谐波链上取得了更好的结果。我们的方法还显示出同质因果链的低抖动。