🤖 AI Summary
To address the challenges of dynamic VNF scaling and delayed SLA assurance in 5G/B5G network slicing, this paper proposes an end-to-end proactive, multi-slice parallel closed-loop orchestration framework. Built upon integrated SDN/NFV architecture, the framework incorporates real-time KPI monitoring, predictive resource scheduling, and closed-loop feedback control—enabling fully automated, low-latency service assurance without manual intervention for the first time. Experimental evaluation under coexisting eMBB and uRLLC slicing scenarios demonstrates a 99.2% SLA compliance rate, a 23% reduction in resource redundancy, and a 37% improvement in resource utilization. The core innovation lies in the proactive multi-slice collaborative closed-loop mechanism, which overcomes the latency and accuracy limitations inherent in conventional reactive orchestration paradigms.
📝 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.