Cost-Efficient Resource Allocation in Hybrid Cloud Environments Using Grey Wolf Optimizer and Ant Colony Algorithms

Hybrid cloud infrastructures present considerable difficulties in the dynamic and economical allocation of resources due to fluctuating workloads, pricing structures, and quality of service limitations. Current methodologies frequently fail to achieve an equilibrium among execution costs, energy usage, and SLA consistency. This research presents a hybrid metaheuristic framework that integrates the Grey Wolf Optimiser (GWO) with Ant Colony Optimisation (ACO) to tackle these difficulties. The GWO component conducts global exploration to determine ideal search areas, while the ACO algorithm guarantees accurate local allocation using pheromone-based task mapping. Experiments performed on a synthesised dataset of 1000 tasks and 50 diverse virtual machines illustrate the advantages of the suggested strategy. In comparison to FCFS, Round Robin, standalone GWO, and ACO approaches, the hybrid GWO-ACO model attains a make span of 92.5 units, a SLA violation rate of 1.2%, an execution cost of $874.4, and energy usage of 164.0 kWh. The results demonstrate the model's resilience, scalability, and efficiency in handling extensive cloud workloads. The suggested approach provides substantial advantages for cloud service providers aiming to reduce operational costs while upholding SLA commitments. Further improvements may include the integration of dynamic pricing, adaptive feedback learning, and multi-objective optimisation to manage progressively complicated resource scheduling situations in real-time cloud environments.