Optimizing resource scheduling based on extended particle swarm optimization in fog computing environments

摘要

Cloud computing (CC) allows on-demand networks to access central computer resources, such as servers, databases, storage, and network services. While clouds can handle enormous amounts of data, they still encounter problems due to insufficient cloud resources. Therefore, another computing model, called fog computing, was introduced. However, the inefficient scheduling of user tasks in fog computing can cause more delays than that in CC. To address the issues of resource utilization, response time, and latency, optimal and efficient techniques are required for the scheduling strategies. In this study, we developed an extended particle swarm optimization (EPSO) algorithm with an extra gradient method to optimize the task scheduling problem in cloud-fog environments. Our primary aim is to improve the efficiency of resources and minimize the time taken to complete tasks. We conducted extensive experiments on the iFogSim simulator in terms of makespan and total cost. We compared the performance of the proposed EPSO method with that of other traditional techniques, such as ideal PSO and modified PSO; the results demonstrated that EPSO achieved a makespan of 342.53 s. Thus, it can be concluded that the performance of the proposed method is comparable to that of other approaches.