Hybrid Approach for Cost Efficient Application Placement in Fog-Cloud Computing Environments

Abstract

Fog computing has recently developed as a new paradigm with the aim of addressing time-sensitive applications better than with cloud computing by placing and processing tasks in close proximity to the data sources. However, the majority of the fog nodes in this environment are geographically scattered with resources that are limited in terms of capabilities compared to cloud nodes, thus making the application placement problem more complex than that in cloud computing. An approach for cost-efficient application placement in fog-cloud computing environments that combines the benefits of both fog and cloud computing to optimize the placement of applications and services while minimizing costs. This approach is particularly relevant in scenarios where latency, resource constraints, and cost considerations are crucial factors for the deployment of applications. In this study, we propose a hybrid approach that combines a genetic algorithm (GA) with the Flamingo Search Algorithm (FSA) to place application modules while minimizing cost. We consider four cost-types for application deployment: Computation, communication, energy consumption, and violations. The proposed hybrid approach is called GA-FSA and is designed to place the application modules considering the deadline of the application and deploy them appropriately to fog or cloud nodes to curtail the overall cost of the system. An extensive simulation is conducted to assess the performance of the proposed approach compared to other state-of-the-art approaches. The results demonstrate that GA-FSA approach is superior to the other approaches with respect to task guarantee ratio (TGR) and total cost.