Service Placement Optimization Based on Evolutionary Algorithm in Fog Computing

Abstract

As an emerging distributed computing paradigm, fog computing provides low-latency and real-time interactive services to end-user or Internet of Things(IoT) devices at the edge of the network. One of the main challenges of fog computing is to select the right fog node to deploy and run IoT application services, which is commonly referred to as the fog service placement problem (FSPP). However most schemes model FSPP as a single objective optimization problem. These single- objective optimization schemes usually cannot meet the needs of increasingly complex engineering practice. In this study, we model the fog service placement problem as a constrained multi-objective optimization problem, which aims to improve the resource utilization of the system and reduce network latency and service placement costs. Secondly, the elitist nondominated sorting genetic algorithm II (NSGA-II) is used to optimize the constrained multi-objective service placement problem. Experimental results show that the proposed scheme is superior to the existing schemes in terms of overall performance.