AI-Driven Network Slicing for F5G-A Networks: A Framework With Unsupervised Discovery, Temporal Dynamics, and Explainable AI

New generation fixed networks such as Fifth Generation Fixed Network (F5G), F5G Advanced (F5G-A), and Sixth Generation Fixed Network (F6G) networks must support diverse services with strict quality requirements under highly dynamic traffic conditions. Although these networks rely on stable infrastructures, rapid demand fluctuations make static and reactive network slicing approaches insufficient. While machine learning (ML) has been increasingly adopted to automate resource management, many existing solutions remain reactive, depend on predefined slice models, and lack transparency due to their black-box nature. This paper presents an Artificial Intelligence (AI)-driven network slicing framework for fixed networks that jointly addresses data-driven slice discovery , proactive management, and explainability. The proposed framework performs unsupervised slice discovery from real operational data using a MiniBatchKMeans-based approach aligned with F5G-A service characteristics, and predicts slice-level changes 5 to 60 minutes in advance through Granger causality analysis. To enhance transparency and operational trust, a multi-level explainability layer is integrated, combining permutation importance, SHAP, LIME, and partial dependence analysis. Experimental results demonstrate that the proposed framework achieves an accuracy of 99.58% under temporal train/test split while reducing bandwidth usage by 20.8% with slice-dependent QoS trade-offs (+2pp violations for stable slices, severe latency impact for volatile IoT). Comprehensive validation demonstrates that discovered slices capture traffic behavior (87.6% feature importance) beyond subscription tiers (12.4%), though limited temporal coverage (48 hours) and modest Granger predictive accuracy (AUC=0.58) indicate areas for future work. These results establish a proof-of-concept framework that advances network slicing through integrated discovery, proactive management, and explainable intelligence.