Odin: Effective End-to-End SLA Decomposition for 5G/6G Network Slicing via Online Learning

2025-09-16

AI Summary

Addressing the challenge of cross-domain Service-Level Agreement (SLA) decomposition in 5G/6G end-to-end network slicing—stemming from domain heterogeneity, dynamic network conditions, and the SLA orchestrator’s lack of intra-domain resource optimization insights—this paper proposes the first Bayesian optimization-based online dynamic SLA decomposition framework. The framework integrates end-to-end SLA modeling, cross-domain collaborative feedback, and a noise-robust online learning mechanism to enable adaptive, coordinated optimization of domain-specific objectives across access, transport, and core networks. It provides theoretical guarantees on convergence and resource allocation efficiency. Experimental evaluation under multiple dynamic scenarios demonstrates up to a 45% improvement in SLA compliance rate, alongside reduced overall resource consumption, significantly outperforming existing static and heuristic approaches.

Technology Category

• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Network slicing plays a crucial role in realizing 5G/6G advances, enabling diverse Service Level Agreement (SLA) requirements related to latency, throughput, and reliability. Since network slices are deployed end-to-end (E2E), across multiple domains including access, transport, and core networks, it is essential to efficiently decompose an E2E SLA into domain-level targets, so that each domain can provision adequate resources for the slice. However, decomposing SLAs is highly challenging due to the heterogeneity of domains, dynamic network conditions, and the fact that the SLA orchestrator is oblivious to the domain's resource optimization. In this work, we propose Odin, a Bayesian Optimization-based solution that leverages each domain's online feedback for provably-efficient SLA decomposition. Through theoretical analyses and rigorous evaluations, we demonstrate that Odin's E2E orchestrator can achieve up to 45% performance improvement in SLA satisfaction when compared with baseline solutions whilst reducing overall resource costs even in the presence of noisy feedback from the individual domains.

Problem

• Decomposing end-to-end SLA into domain-level targets
• Addressing domain heterogeneity and dynamic network conditions
• Optimizing resource allocation for network slicing

Innovation

• Bayesian Optimization-based online learning solution
• Leverages domain feedback for SLA decomposition
• Achieves higher SLA satisfaction with lower costs