Sedat Çimen

Disaster events significantly affect communication network performance by causing spatially localized degradations that may not be captured by conventional monitoring approaches. Traditional network assessment relies primarily on average Key Performance Indicators (KPIs), which may obscure localized anomalies and fail to reveal region-specific disruptions. To address this limitation, this study proposes a multi-stage statistical and spatial analysis framework that integrates non-parametric statistical testing with density-based spatial clustering to detect localized performance degradation patterns under disaster conditions. The proposed framework combines statistical significance testing and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to identify abnormal regions and quantify performance variations across network infrastructure. Experimental results demonstrate that the proposed approach effectively detects spatially localized anomalies and provides improved insight into network behavior during abnormal operational conditions. The findings indicate that the proposed framework enables more reliable identification of performance degradation patterns and supports more effective network monitoring and decision-making processes in disaster scenarios.

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.

The vision of 6G requires autonomous, intelligent, and adaptive systems that can manage complex and dynamic communication environments. In this context, artificial intelligence (AI)-based agents are seen as key enablers, combining perception, knowledge, decision, and execution functions to operate across distributed network layers. This study provides a comprehensive overview of agentic systems for 6G, examining their architecture, core capabilities, and enabling AI techniques. We propose a novel framework for agentic intelligence levels which conceptualizes agentic AI systems as a gradual and multidimensional spectrum. Additionally, trust and governance levels, which characterize system deployability independently of agentic competencies, are introduced. We analyze how methods such as reinforcement learning (RL), federated learning, graph neural networks, transfer learning (TL), and meta-learning can be integrated into agents to support tasks including network optimization, predictive traffic management, spectrum allocation, energy-efficient resource control, and security enhancement. The potential of foundation model-based agents in 6G networks is examined, comparing them to classical RL-based agents to highlight their complementarity. Practical 6G use cases—including smart resource orchestration, environmental coordination, industrial applications, reliability and security assurance, and situational awareness—are presented to demonstrate the applicability of agents in real-world scenarios. Their strengths, limitations, and complementary roles within agent-based frameworks are highlighted. The current technological and industrial maturity levels of use cases are mapped to the proposed levels of agentic intelligence and trust/governance. The study bridges theoretical advances and practical 6G implementations by linking AI methods with concrete deployment challenges. Finally, the study identifies challenges related to scalability, interoperability, explainability, and trust, and highlights future directions for building reliable, adaptive, and ethically aligned agent-based systems in 6G.

As 6G networks become increasingly complex and heterogeneous, effective classification of network slicing is essential for optimizing resources and managing quality of service. While recent advances demonstrate high accuracy under controlled laboratory conditions, a critical gap exists between algorithm performance evaluation under idealized conditions and their actual effectiveness in realistic deployment scenarios. This study presents a comprehensive comparative analysis of two distinct preprocessing methodologies for 6G network slicing classification: Pure Raw Data Analysis (PRDA) and Literature-Validated Realistic Transformations (LVRTs). We evaluate the impact of these strategies on algorithm performance, resilience characteristics, and practical deployment feasibility to bridge the laboratory–reality gap in 6G network optimization. Our experimental methodology involved testing eleven machine learning algorithms—including traditional ML, ensemble methods, and deep learning approaches—on a dataset comprising 10,000 network slicing samples (expanded to 21,033 through realistic transformations) across five network slice types. The LVRT methodology incorporates realistic operational impairments including market-driven class imbalance (9:1 ratio), multi-layer interference patterns, and systematic missing data reflecting authentic 6G deployment challenges. The experimental results revealed significant differences in algorithm behavior between the two preprocessing approaches. Under PRDA conditions, deep learning models achieved perfect accuracy (100% for CNN and FNN), while traditional algorithms ranged from 60.9% to 89.0%. However, LVRT results exposed dramatic performance variations, with accuracies spanning from 58.0% to 81.2%. Most significantly, we discovered that algorithms achieving excellent laboratory performance experience substantial degradation under realistic conditions, with CNNs showing an 18.8% accuracy loss (dropping from 100% to 81.2%), FNNs experiencing an 18.9% loss (declining from 100% to 81.1%), and Naive Bayes models suffering a 34.8% loss (falling from 89% to 58%). Conversely, SVM (RBF) and Logistic Regression demonstrated counter-intuitive resilience, improving by 14.1 and 10.3 percentage points, respectively, under operational stress, demonstrating superior adaptability to realistic network conditions. This study establishes a resilience-based classification framework enabling informed algorithm selection for diverse 6G deployment scenarios. Additionally, we introduce a comprehensive explainable artificial intelligence (XAI) framework using SHAP analysis to provide interpretable insights into algorithm decision-making processes. The XAI analysis reveals that Packet Loss Budget emerges as the dominant feature across all algorithms, while Slice Jitter and Slice Latency constitute secondary importance features. Cross-scenario interpretability consistency analysis demonstrates that CNN, LSTM, and Naive Bayes achieve perfect or near-perfect consistency scores (0.998–1.000), while SVM and Logistic Regression maintain high consistency (0.988–0.997), making them suitable for regulatory compliance scenarios. In contrast, XGBoost shows low consistency (0.106) despite high accuracy, requiring intensive monitoring for deployment. This research contributes essential insights for bridging the critical gap between algorithm development and deployment success in next-generation wireless networks, providing evidence-based guidelines for algorithm selection based on accuracy, resilience, and interpretability requirements. Our findings establish quantitative resilience boundaries: algorithms achieving >99% laboratory accuracy exhibit 58–81% performance under realistic conditions, with CNN and FNN maintaining the highest absolute accuracy (81.2% and 81.1%, respectively) despite experiencing significant degradation from laboratory conditions.