Skip to main content
editor@theusajournals.com | Oscar Publishing Services Journal Home
Login

International Journal Of Management And Economics Fundamental

Peer Reviewed | Open Access | E-ISSN: 2771-2257
Published Article

Deterministic Virtualization and Resource Management in Safety-Critical Automotive and Aerospace Systems: A Comprehensive Study of Scheduling, Memory Arbitration, And Architectural Convergence

Deterministic Virtualization and Resource Management in Safety-Critical Automotive and Aerospace Systems: A Comprehensive Study of Scheduling, Memory Arbitration, And Architectural Convergence

Authors

  • Bennita Alvarez
    Department of Computer Engineering, University of Barcelona, Spain

Keywords:

Deterministic Virtualization Real-Time Scheduling Memory Arbitration Safety-Critical Systems

Abstract

The increasing complexity of safety-critical systems in automotive and aerospace domains has necessitated the convergence of high-performance computing, virtualization, and deterministic real-time behavior. As modern embedded platforms evolve toward centralized and software-defined architectures, ensuring predictability, safety certification, and efficient resource utilization has become a fundamental challenge. This paper presents a comprehensive analytical study of deterministic virtualization and resource management techniques, focusing on scheduling policies, memory arbitration mechanisms, and architectural frameworks for safety-critical systems. Drawing upon a diverse body of literature, including standards such as DO-178B/C, real-time Linux scheduling, and advanced hypervisor-based partitioning, this study explores how deterministic execution can be maintained in multicore environments with shared resources. The analysis investigates memory bandwidth regulation, cache management, and slack-based arbitration techniques as key enablers of temporal isolation. Furthermore, it examines the role of virtualization platforms such as Xen and lightweight hypervisors in supporting mixed-criticality workloads while meeting stringent certification requirements. The integration of these techniques within modern automotive E/E architectures, including AUTOSAR platforms and centralized computing paradigms, is critically evaluated. The findings highlight the trade-offs between flexibility, performance, and predictability, and identify key challenges related to scalability, certification, and dynamic workload management. The paper concludes by proposing future research directions aimed at developing unified frameworks that integrate deterministic scheduling, secure virtualization, and adaptive resource management for next-generation safety-critical systems.

References

Ampatzoglou, A., et al. Identifying, categorizing and mitigating threats to validity in software engineering secondary studies. Information and Software Technology, 106, 201–230, 2019.

Askaripoor, H., et al. E/e architecture synthesis: Challenges and technologies. Electronics, 11(4), 518, 2022.

AUTOSAR. Autosar adaptive platform, 2024.

AUTOSAR. Autosar classic platform, 2024.

Avci, C., et al. Software architectures for big data: a systematic literature review. Big Data Analytics, 5(1), 5, 2020.

Bandur, V., et al. Making the case for centralized automotive e/e architectures. IEEE Transactions on Vehicular Technology, 70(2), 1230–1245, 2021.

Banijamali, A., et al. Software architectures of the convergence of cloud computing and the internet of things: A systematic literature review. Information and Software Technology, 122, 106271, 2020.

Bauer, T., et al. Reference architectures for automotive software. Springer, 2022.

Bordoloi, U., et al. Autonomy-driven emerging directions in software-defined vehicles. IEEE DATE, 2023.

Bucaioni, A., et al. Modelling centralised automotive e/e software architectures. Advanced Engineering Informatics, 59, 102289, 2024.

Abdul Salam Abdul Karim. (2023). Fault-Tolerant Dual-Core Lockstep Architecture for Automotive Zonal Controllers Using NXP S32G Processors. International Journal of Intelligent Systems and Applications in Engineering, 11(11s), 877–885. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/7749

Kostrzewa, A., Saidi, S., Ernst, R. Slack-based resource arbitration for real-time networks-on-chip. DATE Conference, 1012–1017, 2016.

Lelli, J., Scordino, C., Abeni, L., et al. Deadline scheduling in the Linux kernel. Software: Practice and Experience, 46(6), 821–839, 2016.

Li, Y., Akesson, K., Goossens, K. Architecture and analysis of a dynamically-scheduled real-time memory controller. Real-Time Systems, 52(5), 675–772, 2016.

Mancuso, R., Dudko, R., Betti, E., et al. Real-time cache management framework for multi-core architectures. IEEE RTAS, 2013.

Mancuso, R., Pellizzoni, R., Tokcan, N., et al. WCET derivation under single core equivalence with explicit memory budget assignment. ECRTS, 2017.

Martins, J., Tavares, A., Solieri, M., et al. Bao: A lightweight static partitioning hypervisor for modern multi-core embedded systems. NG-RES, 2020.

Microsemi. PolarFire SoC - Lowest Power, Multi-Core RISC-V SoC FPGA. 2020.

RTCA. DO-178B Software Considerations in Airborne Systems and Equipment Certification, 1992.

RTCA. DO-178C Software Considerations in Airborne Systems and Equipment Certification, 2011.

Sabogal, D., George, A. D. Towards resilient spaceflight systems with virtualization. IEEE Aerospace Conference, 2018.

Schulz, B., Annighöfer, B. Evaluation of adaptive partitioning and real-time capability for virtualization with xen hypervisor. IEEE Transactions on Aerospace and Electronic Systems, 58(1), 206–217, 2022.

SELENE. Self-monitored Dependable platform for High-Performance Safety-Critical Systems, 2019.