A Tailored Genetic Algorithm Approach for SLA-Based Service Provisioning in Vehicular Cloud Networks
Farhoud Jafari Kaleibar, Marc St‐Hilaire, Masoud Barati · 2025
Service provisioning in Vehicular Cloud Networks (VCNs) presents challenges such as ensuring Quality of Service (QoS), availability, and fair pricing, necessitating an optimized approach. A previous study [15] introduced a heuristic algorithm leveraging fuzzy logic and mathematical modeling to enhance service provisioning in VCNs. While effective, the approach faced scalability challenges in large-scale instances and did not ensure consistently high-quality solutions. In this paper, we propose a tailored genetic algorithm to enhance service provisioning optimization in VCNs. Although genetic algorithms are heuristic in nature and do not ensure global optimality, our approach improves solution quality by leveraging a novel fitness function that efficiently balances multiple factors of the Service Level Agreement (SLA), including mobility, delay, cost, and availability. Additionally, it incorporates a customized initial generation method to further enhance optimization. Extensive simulation results demonstrate the superior performance of the proposed method compared to other approaches, particularly in handling large-scale scenarios with dynamic conditions.