Subscriber aware dynamic service function chaining

Ozdem M., ALKAN M.

COMPUTER NETWORKS, cilt.194, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 194
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1016/j.comnet.2021.108138
  • Dergi Adı: COMPUTER NETWORKS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, PASCAL, ABI/INFORM, Aerospace Database, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Library and Information Science Abstracts, Library, Information Science & Technology Abstracts (LISTA), Metadex, zbMATH, Civil Engineering Abstracts
  • Anahtar Kelimeler: NFV, SDN, Service function chaining, Real-Time Testbed, SGi-LAN, CHALLENGES
  • Gazi Üniversitesi Adresli: Evet

Özet

In this study, a novel subscriber aware dynamic service function chaining (SFC) framework is developed by using open source software-defined networking (SDN) and network function virtualization (NFV) solutions, where the aim is to provide service chaining per user traffic and to transform SGi-LAN services into virtual network functions. With this SFC framework, customer based dynamically applicable value added services can be provided without the need for manual operation that would require vast effort. In order to show the performance and scalability of the proposed framework, the solution is tested in a live telecom lab with varying number of subscribers and thread counts. The test results show that the proposed solution can successfully manage subscribers dynamically without packet loss for 2 million simultaneous subscribers' traffic flows when the system is overloaded, regardless of hardware or vendor. In addition, it has been observed that the service chain rules can be applied in a very short period such as 2.9 s for 10,000 simultaneous subscriber SFC requests even in the loaded traffic flows, while the CPU consumption of virtual machines remained between 23.5% and 28.5%. These results have proved that the proposed solution can be used in large-scale telecom networks.