Summary
Asia-Pacific Network Operations and Management Symposium
2022
Session Number:PS1
Session:
Number:PS1-14
SFC Path Selection based on Combination of Topo-logical Analysis and Demand Prediction
Takahiro Hirayama, Masahiro Jibiki,
pp.-
Publication Date:2022/09/28
Online ISSN:2188-5079
PDF download
Summary:
The 5th generation (5G) or beyond 5G (B5G) mobile net-works offer a range of services over the existing infrastruc-ture. Service function chaining (SFC) provides a platform for flexible resource management by dynamically allocat-ing and adjusting resources to virtual network functions (VNFs). To satisfy the quality of service (QoS) require-ments, the system requires the migration of VNFs from the current server to other servers that have sufficient re-sources. Previously, we discussed an artificial intelligence (AI)based VNF migration scheduling mechanism for multiple service function (SF) chains. However, our previ-ous approach focused only on SFC management in small-scale networks. To manage large-scale networks, we must consider SFC path selection against interference among multiple SFC management AIs. To avoid interference, in this study, we propose a supervisory mechanism to estab-lish an SFC management system consisting of multiple AIs. The supervisor determines the path recommendation ratio for each chain group governed by the management AIs. The recommendation ratio is determined by the topo-logical features and predicted resource demands of the chains. By using the recommendation ratio, SFC manage-ment may reduce the load of VNF-providing servers by approximately 20% compared with the case where no su-pervisor is used