A Trust-Aware Multi-Objective Optimization Framework (TAMOOF) for Secure and Optimized Workflow Execution in Vehicular Edge Computing

Authors

  • Uma Shankari Srinivasan Author
  • S Babu Author
  • Sakthivelu U Author
  • S. Gangadharan Author
  • Adlin Sheeba Author
  • Dahlia Sam Author
  • R. Nareshkumar Author

Keywords:

Vehicular Edge Computing; Trust Management; Multi-Objective Optimization; Workflow Scheduling; Edge Resource Allocation; Security; Internet of Vehicles.

Abstract

The rapid evolution of Vehicular Edge Computing (VEC) has enabled intelligent vehicular applications by providing low latency computation and communication services closer to vehicles. However, the highly dynamic network topology, heterogeneous edge resources, security vulnerabilities, and increasing workflow complexity pose great challenges for reliable and efficient workflow execution. To address these issues, this paper proposes a Trust-Aware Multi-Objective Optimization Framework (TAMOOF) for secure and optimized workflow execution in VEC environments. The proposed framework combines distributed trust evaluation and multi-objective optimization to simultaneously optimize the workflow execution latency, the computational resource usage, the energy consumption, the communication overhead and the security reliability. The optimization mechanism dynamically selects appropriate edge resources and workflow execution paths based on the varying vehicular conditions, and integrates trust values into the decision process. We perform an extensive Monte Carlo simulation study against three baseline scheduling strategies: a trust-blind multi-objective optimizer (MOO-NT), a greedy least-latency scheduler, and a round-robin scheduler, under different vehicle densities, workload intensities, network conditions, and adversarial (malicious-node) ratios. Performance is measured by workflow completion time, end-to-end latency, throughput, utilization of resources, energy consumption, task success rate, communication overhead, trust reliability and malicious-node selection rate.The simulation results show that TAMOOF reduces malicious-edge-node selection to effectively zero under moderate adversarial pressure (0% at 10–25% malicious-node ratio vs. 4–22% for trust-blind baselines) while remaining competitive  though not always optimal  on raw latency and throughput, reflecting the expected security/performance trade-off of enforcing a trust constraint. TAMOOF achieves the most stable task success rate under network congestion and rising adversarial ratios among the compared methods. The proposed framework offers an adaptive foundation for secure, scalable, multi-objective workflow optimization in next generation vehicular edge computing environments.

Downloads

Download data is not yet available.

Downloads

Published

2026-09-22

How to Cite

A Trust-Aware Multi-Objective Optimization Framework (TAMOOF) for Secure and Optimized Workflow Execution in Vehicular Edge Computing . (2026). Minimax Theory and Its Applications, 11(2s), 560-573. https://journalmta.com/index.php/jmta/article/view/436