Optimized Dynamic Service Placement for Enhanced Scheduling in Fog-Edge Computing Environments

Abstract

The traditional cloud computing model struggles to efficiently handle the vast number of Internet of Things (IoT) services due to its centralized nature and physical distance from end-users. In contrast, edge and fog computing have emerged as promising solutions for supporting latency-sensitive IoT applications by distributing computational resources closer to the data source. However, these technologies are limited by their size and computational capacities, making optimal service placement a critical challenge. This paper addresses this challenge by introducing a dynamic and distributed service placement policy tailored for edge and fog environments. By leveraging the inherent advantages of proximity in fog and edge nodes, the proposed policy seeks to enhance service delivery efficiency, reduce latency, and improve resource utilization. The proposed method focuses on optimizing the placement of high-demand services closer to the data generation sources to enhance scheduling efficiency in fog computing environments. Our method is divided into three interconnected modules. The first module is the service type estimator, which is responsible for distributing services to appropriate nodes. Here, we use the Political Optimizer (PO) as a new metaheuristic algorithm for deploying IoT services. The second module is service dependency estimator, which manages service dependencies. Here, we load dependent services near the data using a path matrix based on the Warshall algorithm. Finally, the third module is resource demand scheduling, which estimates resource demand to facilitate optimal scheduling. Here, we use a popularity-based policy to manage resource demand and service execution scheduling. Implementation results demonstrate significant improvements over existing state-of-the-art policies, highlighting the efficacy of the proposed policy in enhancing service delivery within fog-edge computing frameworks.