Modelling multi-criticality vehicular software systems: evolution of an industrial component model
- PDF / 3,522,532 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 176 Views
SPECIAL SECTION PAPER
Modelling multi-criticality vehicular software systems: evolution of an industrial component model Alessio Bucaioni1,2 · Saad Mubeen1,2 · Federico Ciccozzi1 · Antonio Cicchetti1 · Mikael Sjödin1 Received: 31 January 2019 / Accepted: 31 March 2020 © The Author(s) 2020
Abstract Software in modern vehicles consists of multi-criticality functions, where a function can be safety-critical with stringent realtime requirements, less critical from the vehicle operation perspective, but still with real-time requirements, or not critical at all. Next-generation autonomous vehicles will require higher computational power to run multi-criticality functions and such a power can only be provided by parallel computing platforms such as multi-core architectures. However, current model-based software development solutions and related modelling languages have not been designed to effectively deal with challenges specific of multi-core, such as core-interdependency and controlled allocation of software to hardware. In this paper, we report on the evolution of the Rubus Component Model for the modelling, analysis, and development of vehicular software systems with multi-criticality for deployment on multi-core platforms. Our goal is to provide a lightweight and technology-preserving transition from model-based software development for single-core to multi-core. This is achieved by evolving the Rubus Component Model to capture explicit concepts for multi-core and parallel hardware and for expressing variable criticality of software functions. The paper illustrates these contributions through an industrial application in the vehicular domain. Keywords Model-based engineering · Metamodelling · Single-core · Multi-core · Multi-criticality · Vehicular embedded systems · Real-time systems
1 Introduction Software has become the heart of modern systems across most domains and is enhancing, sometimes even replacing, an ever larger number of mechanical and electrical parts. Communicated by A. Pierantonio, A. Anjorin, S. Trujillo, and H. Espinoza.
B
Alessio Bucaioni [email protected]; [email protected] Saad Mubeen [email protected]; [email protected] Federico Ciccozzi [email protected] Antonio Cicchetti [email protected] Mikael Sjödin [email protected]
1
School of Innovation, Design and Engineering, Mälardalen University, Västerås, Sweden
2
Arcticus Systems AB, Järfälla, Sweden
The automotive industry, for instance, has experienced a dramatic increment of software in vehicles. A modern car is a software-intensive system, while historically vehicles have been considered to be mechanics-intensive [1]. The same is happening in other domains, such as, for example, aerospace, automation, and robotics. In our research, we target vehicular applications, where multiple networks, consisting of electronic control units (ECUs), sensors, and actuators whose most value-added functionalities are realised by software. An example is the throttle control system, implemented
Data Loading...
