학술논문

Online Scheduling in Virtualized TSN Networks via Joint Admission Control and VNF Embedding
Document Type
Conference
Source
2024 IEEE/CIC International Conference on Communications in China (ICCC) Communications in China (ICCC), 2024 IEEE/CIC International Conference on. :603-608 Aug, 2024
Subject
Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Measurement
Runtime
Scheduling algorithms
Service function chaining
Heuristic algorithms
Simulation
Admission control
Time-sensitive Networking (TSN)
Admission Control (AC)
VNF embedding (VNE)
Network Function Virtualization (NFV)
Language
Abstract
Introducing virtualization enhances the flexibility of time-sensitive networking (TSN), wherein applications manifest as service function chains comprising a series of virtual network functions (VNFs). However, such virtualized TSN realizes determinacy through global configuration, being too complicated to serve dynamic applications in time. To address this issue, we innovatively propose to achieve TSN scheduling by distributively executing admission control (AC), whereby the scheduling complexity is radically reduced. Specifically, we first build a two-way AC model that captures TSN multi-queue characteristics. Then, we define admissible regions of nodes and links, working as metrics for AC decision-making and enabling feasible TSN scheduling. Built upon this, we propose a joint AC and VNF embedding mechanism, Rapid Admission Control (RapidAC), which consists of two algorithms. The first algorithm responds to dynamic applications rapidly and derives node-mapping solutions by judging nodes’ admissible regions. Based on this, the second algorithm augments the detailed VNF embedding solution according to admissible regions of links. Simulation results show that RapidAC reduces runtime by 90% compared with existing TSN scheduling algorithms.