Accelerating network softwarization in the cognitive age

Abstract

This special issue contains extended versions of three best papers from the IEEE International Conference on Network Softwarization (NetSoft 2021, https://netsoft2021.ieee-netsoft.org/). The theme of NetSoft 2021 was “Accelerating Network Softwarization in the Cognitive Age.” The General Co-Chairs were Kohei Shiomoto, Tokyo City University, Japan and Young-Tak Kim, Yeungnam University, Korea. The TPC-Co-Chairs were Christian Esteve Rothenberg, University of Campinas, Brazil; Barbara Martini, CNIT, Italy; and Eiji Oki, Kyoto University, Japan.

The first paper, titled “RNN-EdgeQL: An Auto-Scaling and Placement Approach for SFC,” proposes an innovative prediction-based scaling and placement algorithm for service function chains (SFCs) that improves service level agreements (SLAs) and reduces operational costs. The authors use a variant of recurrent neural networks (RNNs) called gated recurrent unit (GRU) for resource demand prediction and an algorithm that applies Q-Learning on Edge computing environment (EdgeQL) to place scaled-out virtual network functions (VNFs) in appropriate locations. The proposed algorithm is tested on realistic temporal dynamic load models and achieves the lowest overall latency, lowest SLA violations, and lowest VNFs requirement compared with existing algorithms.

The second paper, titled “SRv6-based Time-Sensitive Networks (TSN) with Low Overhead Rerouting,” proposes a software-defined network (SDN)-based approach for low-overhead TSN network updates using segment routing over IPv6 (SRv6) for path control. The authors introduce the concept of TSN subgraphs to quickly reschedule flows traversing problematic areas and propose a TSN-aware routing heuristic to minimize convergence time. The proposed approach yields faster recovery and significantly reduces the number of required reconfigurations upon failures, at the expense of a small SRv6 encoding/decoding overhead.

The third paper, titled “Analysis of Network Function Sharing in Content Delivery Network-as-a-Service Slicing Scenarios,” investigates the potential efficiencies that can be achieved when sharing a virtual cache function among Internet service providers (ISPs) that are sharing a common physical infrastructure. The authors simulate the sharing of virtualized cache functions and analyze the implications of limiting the storage capacity of the caches at the edge. The paper provides insights into the potential cost savings that can be achieved by sharing network infrastructures and virtualized cache functions among ISPs.

We believe that these three papers make significant contributions and offer valuable insights into the challenges and opportunities of managing softwarized networks. We hope that this special issue will inspire further research in this area and lead to the development of more efficient and effective network management solutions.

We would like to thank the authors for their excellent contributions and the reviewers for their insightful comments and suggestions. We would also like to acknowledge the editorial team for their hard work in putting together this special issue.

We hope that readers find these papers informative and thought-provoking, and we look forward to further advancements in the field of network management.

Sincerely,