An Efficient Energy-Saving Scheme Using Genetic Algorithm for 5G Heterogeneous Networks

Abstract

Energy-saving (ES) is becoming one of the most challenging tasks that fifth-generation (5G) tends to tackle. The problem of identifying the optimal set cells to be turned <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">off</small> is nondeterministic polynomial time-hard. In this research article, we use heuristic algorithms to save energy in 5G heterogeneous networks (HetNet). Our approach is based on turning <sc xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">off</small> underutilized components of base stations to reduce energy consumption, while satisfying users’ requests. Basically, we elaborate a new mechanism providing ES for 5G networks. The proposed mechanism is based on genetic algorithm (GA) and is called ES based on GA in 5G (ESGA-5G). Bio-inspired GA and particle swarm optimization (PSO) algorithms stand for AI solutions that intelligently manage the operation of ES self-organized network mechanisms in 5G HetNet. The performance analysis of the proposed ESGA-5G approach illustrates its efficiency in terms of reducing the energy consumption. In particular, ESGA achieves a higher percentage of ESs compared to PSO algorithm, with a gap to optimality amounting to 28% for GA and 54% for PSO.