Proactive Service Assurance in 5G and B5G Networks: A Closed-Loop Algorithm for End-to-End Network Slicing

TL;DR

The paper tackles the challenge of proactive, end-to-end service assurance for 5G/B5G network slicing by introducing PCLANSA, a proactive closed-loop algorithm that uses ML-based traffic forecasting (LSTM-FSD) and ILP-based KPI prediction (LP-KPI) to dynamically scale VNFs and link resources across multiple slices. The authors present a formal resource model and a two-stage implementation that operates in parallel across slices, integrating end-to-end orchestration with SDN/NFV and 3GPP-based network architecture. Evaluation in a packet-level Omnet++ environment with four diverse slices demonstrates substantial resource savings (up to ~58%) and reduced KPI violations under varying traffic conditions, while maintaining QoS. The work advances proactive, scalable, end-to-end network slice management with practical implications for reducing over-provisioning and improving SLA compliance in 5G/B5G networks.

Abstract

The customization of services in Fifth-generation (5G) and Beyond 5G (B5G) networks relies heavily on network slicing, which creates multiple virtual networks on a shared physical infrastructure, tailored to meet specific requirements of distinct applications, using Software Defined Networking (SDN) and Network Function Virtualization (NFV). It is imperative to ensure that network services meet the performance and reliability requirements of various applications and users; thus, service assurance is one of the critical components in network slicing. One of the key functionalities of network slicing is the ability to scale Virtualized Network Functions (VNFs) in response to changing resource demand and to meet Customer Service Level agreements (SLAs). In this paper, we introduce a proactive closed-loop algorithm for end-to-end network orchestration, designed to provide service assurance in 5G and B5G networks. We focus on dynamically scaling resources to meet key performance indicators (KPIs) specific to each network slice and operate in parallel across multiple slices, making it scalable and capable of managing completely automatically real-time service assurance. Through our experiments, we demonstrate that the proposed algorithm effectively fulfills service assurance requirements for different network slice types, thereby minimizing network resource utilization and reducing the over-provisioning of spare resources.

Figures (10)

• Figure 1: A reference E2E network slice concept Network-e2e-3gpp
• Figure 2: End-to-end network slice orchestration with closed-loop algorithm
• Figure 3: Proactive closed-loop architecture
• Figure 4: Overview of PCLANSA: a high-level flowchart.
• Figure 5: 5G End-to-End network simulation topology