ORION: Multiobjective Optimization-Based Task Scheduling for Vehicular Clouds

• Matheus R. Esteves UNIFESP http://orcid.org/0009-0003-1464-7489
• Bruno Kimura UNIFESP http://orcid.org/0000-0002-2174-2762
• Maycon Peixoto UFBA http://orcid.org/0000-0002-4851-5228
• Geraldo Rocha UESB http://orcid.org/0000-0001-6795-2768
• Leandro Villas UNICAMP http://orcid.org/0000-0002-3372-3366
• Allan M. de Souza UNICAMP http://orcid.org/0000-0002-5518-8392
• Joahannes B. D. da Costa UNIFESP http://orcid.org/0000-0001-9973-2479

DOI: https://doi.org/10.5753/sbrc.2026.19311

Abstract

Vehicular Edge Computing (VEC) has emerged as a promising paradigm to address the growing demand for low-latency computation in vehicular applications, driven by the rapid increase of connected vehicles and the massive generation of data. However, the dynamic and resource-constrained nature of this environment poses significant challenges for efficient computational task scheduling. This work proposes ORION, a multi-objective optimization-based scheduler that leverages the NSGA-II algorithm to balance conflicting objectives: maximizing the number of tasks completed within deadlines, minimizing monetary cost, and reducing system latency. Results show that ORION outperforms existing task scheduling solutions in VEC, particularly under high resource-demand scenarios, maintaining high scheduling rates, lowering costs, and achieving acceptable latency.

References

Bai, L., Cao, J., Zhang, M., and Li, B. (2025). Collaborative Edge Intelligence for Autonomous Vehicles: Opportunities and Challenges. IEEE Network.

Baumann, D., Sommer, M., Dettinger, F., Rösch, T., Weyrich, M., and Sax, E. (2024). Connected Vehicle: Ontology, Taxonomy and Use Cases. In 2024 IEEE International Systems Conference (SysCon), pages 1–6. IEEE.

Caiano, S. R., Marfort, L., and Tang, J. (2025). Otimização Multiobjetivo Eficiente de Sistemas AEB: Um Estudo Comparativo entre Sweeping e NSGA-II. Blucher Engineering Proceedings, 12(1):489–493.

da Costa, J. B., de Souza, A. M., Meneguette, R. I., Cerqueira, E., Rosário, D., Sommer, C., and Villas, L. (2023). Mobility and Deadline-Aware Task Scheduling Mechanism for Vehicular Edge Computing. IEEE Transactions on Intelligent Transportation Systems, 24(10):11345–11359.

da Costa, J. B., de Souza, A. M., Rosário, D., and Villas, L. (2024). TEMIS: Provisionamento de Justiça na Utilização de Recursos Computacionais em Nuvens Veiculares. In Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos (SBRC), pages 15–28. SBC.

Felix, A. A., da Costa, J. B., and Oliveira, H. M. d. S. (2025). Assessing vehicle collision prevention based on machine learning and v2x communication. In 2025 IEEE 102nd Vehicular Technology Conference (VTC2025-Fall), pages 1–5. IEEE.

Hattab, G., Ucar, S., Higuchi, T., Altintas, O., Dressler, F., and Cabric, D. (2019). Optimized Assignment of Computational Tasks in Vehicular Micro Clouds. In Proceedings of the 2nd International Workshop on Edge Systems, Analytics and Networking, pages 1–6.

Lieira, D. D., Quessada, M. S., De Grande, R. E., and Meneguette, R. I. (2025). LOPRIVE: LOA-Based Priority-Driven Task Allocation in the Vehicular Edge. In 2025 IEEE Symposium on Computers and Communications (ISCC), pages 1–6. IEEE.

Pereira, R., Boukerche, A., da Silva, M. A., Nakamura, L. H., Freitas, H., Rocha Filho, G. P., and Meneguette, R. I. (2021). FORESAM-FOG Paradigm-Based Resource Allocation Mechanism for Vehicular Clouds. Sensors, 21(15):5028.

Surayya, A., Hussain, M. M., Reddy, V. D., Abdul, A., and Gazi, F. (2025). Evolutionary Algorithms for Edge Server Placement in Vehicular Edge Computing. IEEE Access.

Weissberger, A. (2023). Juniper research: 5g connectivity opportunity for the connected car market. Acessado em 13 jan. 2026.

Yang, J., Yang, K., Dai, X., Xiao, Z., Jiang, H., Zeng, F., and Li, B. (2024). Service-aware computation offloading for parallel tasks in vec networks. IEEE Internet of Things Journal.