Timing and schedulability analysis for distributed automotive control applications

Abstract

High-end cars today consist of more than 100 electronic control units (ECUs) that are connected to a set of sensors and actuators and run multiple distributed control applications. The design flow of such architectures consists of specifying control applications as Simulink/Stateflow models, followed by generating code from them and finally mapping such code onto multiple ECUs. In addition, the scheduling policies and parameters on both the ECUs and the communication buses over which they communicate also need to be specified. These policies and parameters are computed from high-level timing and control performance constraints. The proposed tutorial will cover different aspects of this design flow, with a focus on timing and schedulability problems. After reviewing the basic concepts of worst-case execution time analysis and schedulability analysis, we will discuss the differences between meeting timing constraints (as in classical real-time systems) and meeting control performance constraints (e.g., stability, steady and transient state performance). We will then describe various control performance related schedulability analysis techniques and how they may be tied to model-based software development. Finally, we will discuss various schedule synthesis techniques, both for ECUs as well as for communication protocols like FlexRay, so that control performance constraints specified at the model-level may be satisfied. Throughout the tutorial different commercial as well as academic tools will be discussed and demonstrated. Copyright is held by the author/owner(s). EMSOFT'11, October 9-14, 2011, Taipei, Taiwan. ACM 978-1-4503-0714-7/11/10. Categories and Subject Descriptors Control Applications• control requirements (stability, settling time) • timing requirements (end-to-end latencies, WCETs)Automotive ArchitecturesFigure 1: Illustration of a concurrent design of distributed automotive control systems. OUTLINEIn the following, different aspects of a design flow for timing and schedulability analysis of distributed automotive control application are discussed. These aspects break down to state-of-the-art automotive architectures, control applications, and a design methodology that considers a concurrent co-design. An overview is illustrated in Figure 1. Automotive ArchitecturesModern cars consist of a large number of electronic components that carry out highly diverse applications with the goal to increase the safety and comfort of the driver. Recent innovations in the automotive domain like adaptive cruise control or lane, parking, and, traffic assistant systems are put into practice by integrated hardware/software solutions. As a result, modern high-end cars consist of more than 100 electronic control units (ECUs) that are connected to a set of sensors and actuators, running a multitude of distributed control applications. These automotive architectures are highly heterogeneous, consisting of many different computational and communication components. This growing complexity issues enormous challenges to...

Control Performance Optimization for Application Integration on Automotive Architectures

“…As per Constraint (10), we might schedule an occurrence of an activity beyond the hyperperiod H. However, note that if we schedule an activity at time t then it repeats at time t + H. And therefore, we cannot schedule another activity at…”

“…As inputs, it takes (i) the element i to be scheduled; (ii) ši and ŝi , the earliest and the latest possible start times of this element based on the precedence relation and the end-to-end latency constraint, computed according to Equations ( 14) and ( 18), respectively. We compute ŝi in Equation ( 18) as the maximum of three values: 1) its lower bound LB j i defined by Equation (10), i.e., start of the corresponding period; 2) completion time of the previous element occurrence if it is a message and j > 1; and 3) start time of the earliest activity in the application plus the end-to-end latency bound Lw minus processing time of the element e i to satisfy end-to-end latency constraints.…”

“…Therefore, car manufacturers face the problem of integrating subsystems from different suppliers comprising one or multiple applications, such that their control and timing requirements are guaranteed [22], [24], [39]. The control performance of an application depends strongly on the timing behavior of its implementation on the shared platform [9], [10]. The relationship between control performance and the timing behavior the control application experiences heavily depends on the application [12].…”

Performance optimization of task intensive real‐time applications on multicore ECUs—A hybrid scheduler

“…© 2021 The Authors. The Journal of Engineering published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology instructs strict partitioning and mapping of the tasks to definite cores [3]. Tasks are scheduled for the intended cores based on static priority scheme.…”

Performance optimization of task intensive real time applications on multicore ECUs - a hybrid scheduler

“…Parallelized application tasks need to be efficiently scheduled and allocated to multiple computing cores to accomplish the functions within the specified deadlines to ensure the system is fail safe. The state of the art task scheduling algorithm for multicore ECUs instructs strict partitioning and mapping of the tasks to definite cores [3]. Tasks are scheduled for the intended cores based on static priority scheme.…”