Multi-objective Service Function Chain placement in 5G cellular networks based on meta-heuristic approach

• Published in: Simulation modelling practice and theory 2024-05, Vol.133, p.102927, Article 102927
• Main Authors: de Freitas Bezerra, Diego, Santos, Guto Leoni, da Silva Rocha, Élisson, Moreira, André, Sadok, Djamel F.H., Kelner, Judith, Gonçalves, Glauco Estácio, Mehta, Amardeep, Marquezini, Maria Valéria, Endo, Patricia Takako
• Format: Article
• Language: English
• Subjects: Distributed scenarios; NFV; Optimization; Service function chain
• ISSN: 1569-190X; 1878-1462
• DOI: 10.1016/j.simpat.2024.102927

With the emergence of new applications driven by the popularization of mobile devices, the next generation of mobile networks faces challenges to meet different requirements. Virtual Network Functions (VNFs) have been deployed to minimize operational costs and make network management more flexible. In this sense, strategies for VNF placement can impact different metrics of interest. Invoking and visiting VNFs in a specific execution order may be required for different use cases, resulting in a complete network service called Service Function Chain (SFC). The SFC placement problem is to define a feasible path in the physical infrastructure whose nodes and edges meet the computational and bandwidth requirements for the VNFs and virtual links, respectively. It has already been proved that this process is NP-hard and it is difficult to find an optimal solution to this problem. Therefore, in this paper, we propose the use of meta-heuristics to solve the SFC placement problem in cellular networks. We consider a triathlon competition leading to different mobility patterns. We collected real data about the competitors to simulate their movements through the scenario as well as the measured signal quality of the network. We formulate the SFC placement problem as a multi-objective problem where we try to minimize the placement cost and the total SFC delay. To solve the problem, we propose the use of two algorithms, NSGA-II and GDE3, which compare two different greedy approaches that prioritize the different optimization metrics considered in this work. Our results show that the meta-heuristics provide better results for each of the metrics. For all competition stages, GDE3 presented a slightly lower placement costs than NSGA-II, while NSGA-II had a lower delay in some scenarios.