Scheduling is an NP-hard problem, and metaheuristic algorithms are often used to find approximate solutions within a feasible time frame. Existing metaheuristic algorithms, such as ACO, PSO, and BOA address this problem either in cloud or fog environments. However, when these environments are combined into a hybrid cloud-fog environment, these algorithms become inefficient due to inadequate handling of local and global search strategies. This inefficiency leads to suboptimal scheduling across the cloud-fog environment because the algorithms fail to adapt effectively to the combined challenges of both environments. In our proposed Improved Butterfly Optimization Algorithm (IBOA), we enhance adaptability by dynamically updating the computation cost, communication cost, and total cost, effectively balancing both local and global search strategies. This dynamic adaptation allows the algorithm to select the best resources for executing tasks in both cloud and fog environments. We implemented our proposed approach in the CloudSim simulator and compared it with traditional algorithms such as ACO, PSO, and BOA. The results demonstrate that IBOA offers significant reductions in total cost, communication cost, and computation cost by 19.65%, 18.28%, and 25.41%, respectively, making it a promising solution for real-world cloud-fog computing (CFC) applications.

Cloud-fog computing frameworks are innovative frameworks that have been designed to improve the present Internet of Things (IoT) infrastructures. The major limitation for IoT applications is the availability of ongoing energy sources for fog computing servers because transmitting the enormous amount of data generated by IoT devices will increase network bandwidth overhead and slow down the responsive time. Therefore, in this paper, the Butterfly Spotted Hyena Optimization algorithm (BSHOA) is proposed to find an alternative energy-aware task scheduling technique for IoT requests in a cloud-fog environment. In this hybrid BSHOA algorithm, the Butterfly optimization algorithm (BOA) is combined with Spotted Hyena Optimization (SHO) to enhance the global and local search behavior of BOA in the process of finding the optimal solution for the problem under consideration. To show the applicability and efficiency of the presented BSHOA approach, experiments will be done on real workloads taken from the Parallel Workload Archive comprising NASA Ames iPSC/860 and HP2CN (High-Performance Computing Center North) workloads. The investigation findings indicate that BSHOA has a strong capacity for dealing with the task scheduling issue and outperforms other approaches in terms of performance parameters including throughput, energy usage, and makespan time.