Get started
Work

Explainable AI-Based Decision Framework for Transparent Network Slice Resource Management

Year: 2026
Type: article
Abstract: Network slicing has become a foundational paradigm for fifth-generation and beyond mobile networks, enabling multiple logical networks to coexist on a shared physical infrastructure. Efficient resource management across slices is essential to meet diverse quality-of-service requirements, yet the growing adoption of artificial intelligence in orchestration decisions introduces opacity that can undermine trust, accountability, and regulatory compliance. This paper presents a system-level explainable AI-based decision framework for transparent network slice resource management that reconciles high-performance automation with human-intelligible governance. The framework integrates interpretable machine learning models, post-hoc explanation modules, and a dedicated governance layer to translate local feature attributions into auditable resource allocation actions. We examine the structural trade-offs between predictive accuracy and explainability, describe how the architecture can embed within existing ETSI management and orchestration platforms, and analyze the implications for fairness, operational robustness, and energy sustainability. Through cross-domain comparisons and deployment scenarios, the discussion illuminates how transparency mechanisms can enable stakeholder confidence, facilitate fault diagnosis, and support regulatory oversight without compromising real-time performance. The paper positions explainable AI as a governance instrument that aligns algorithmic decision-making with organizational accountability and long-term infrastructure evolution, arguing that transparent slice resource management is not merely a technical desideratum but a socio-technical necessity for trustworthy network automation.
Language: English
Open Access status: diamond
OpenAlex ID: W7220216611
FWCI:
Cites:
Cited by:
Related to: 10