GVNF-P: An Energy-Aware Genetic Algorithm for VNF Placement in B5G Networks

This paper presents GVNF-P, a genetic-algorithm framework that minimises energy consumption while placing Virtual Network Functions (VNFs) for service function chains in beyond-5G (B5G) cloud networks. The algorithm encodes SFC order within chromosomes, leverages a server-centred power model that separates static and dynamic costs, and employs problem-aware crossover and mutation operators to guide the search through feasible solutions. Experiments on heterogeneous B5G topologies show that GVNF-P achieves energy savings within 3% of an integer linear programming optimum while reducing computation time by more than an order of magnitude-dropping from 4.5 minutes to just 0.12 minutes-and keeping memory usage low under realistic traffic and resource load conditions.