Performance Analysis of Priority-Aware DRL-based Call Admission Control for 5G Network

Comprehensive Review of Optimization Techniques for User-Centric Distributed Network Slicing in 5G Networks

A QoE-aware framework for Multi-Access Edge Computing-enabled Open Radio Access Network (O-RAN) architectures, combining a graph attention network (GAT) encoder, distributed multi-agent DRL, and privacy-preserving FL, while transitioning control from Quality of Service (QoS) to QoE metrics is proposed.

Implementation of an Admission Control in SDN Network

SLA-AWare RAN Slicing Via Online Meta-Learning

Real-time inter-slice resource allocation in the Radio Access Network (RAN) is a critical control function in 5G and emerging 6G networks, where the scheduler in the Distributed Unit (DU) dynamically allocates physical resources, namely Physical Resource Blocks (PRBs), to different network slices to meet their diverse Quality of Service (QoS) requirements. To address the need for faster and more flexible radio resource management, and inspired by recent efforts to extend the O-RAN architecture with a real-time controller, we investigate slice-level PRB allocation through the lens of online learning. We formulate inter-slice scheduling as a dynamic decision problem and develop a system model that captures per-slice Service Level Agreement (SLA) requirements and throughput variations over configurable time windows, without assuming future channel knowledge. Our scheduling solution is implemented as a real-time RAN control application, in line with the O-RAN proposition for dApps that are programmable and distributed software components for fine-grained control in O-RAN DUs (O-DUs) and Centralized Units (O-CUs). The proposed approach adapts inter-slice radio resource allocations based on telemetry, with low computational complexity. Experimental results show sublinear dynamic regret, up to 85% fewer SLA violations than static baselines, and submillisecond amortized control overhead. Overall, these findings highlight dynamic-benchmark online control as a practical mechanism for real-time, SLA-aware slicing in O-RAN.

Congestion-Aware Mobility Robustness Optimization: A Multi-Vendor Approach in Live Networks

Mobility Robustness Optimization (MRO) is essential to maintain service continuity, yet its execution often conflicts with Mobility Load Balancing (MLB) functions. While existing literature relies heavily on simulated environments, this paper presents a novel, data-driven, and congestion-aware MRO framework design for live networks. The proposed approach employs multi-vendor capabilities and a five-phase rule-based system to ensure that Handover Control Parameter (HCP) adjustments are grounded in domain-specific knowledge. The framework was deployed in a live network, processing data from over 10,000 cells. Live results show a 19.9% increase in user throughput, a 7.6% decrease in Handover Failures (HOF), and a 36.6% reduction in packet drop rate. Ultimately, this study demonstrates that the proposed framework is highly scalable and adaptive for diverse multi-vendor network environments.

Data-Driven Online Slice Admission Control and Resource Allocation in NextG Mobile Networks

Virtualization in 5G and beyond networks enables the creation of virtual networks (i.e., network slices) tailored to the needs of different applications. To maximize revenue under limited infrastructure resources, InPs must decide in real time whether to admit incoming slice requests (SRs) based on their resource demands and offered values, while accounting for the opportunity cost of consuming scarce resources. To address this challenge, we introduce Online Pricing-based Slice Admission Control and Resource Allocation (OPA) framework. This framework dynamically assigns pseudo-prices to resources that capture long-term scarcity and anticipated inter-temporal opportunity costs. The short-term admission and resource allocation decisions for each SR are then guided by these prices. Additionally, we design an exponential pricing strategy that guarantees bounded worst-case performance. To improve practical performance, we further develop a data-driven exponential pricing approach that learns from historical data. Evaluations on a real-world network topology show that it improves mean revenue by 32.2% and 26.7% over state-of-the-art DRL and optimization-based approaches, respectively, while reducing computational cost by an order of magnitude relative to the latter.

End-to-end delay performance analysis of the 5G-TSN network using network calculus

The emerging Ultra-Reliable and Low-Latency Communication (URLLC) of the Fifth Generation Communication Network (5G) makes the integration of Time-Sensitive Networking (TSN) and 5G communication access possible. Unfortunately, there is a lack of a theoretical study for analyzing the end-to-end (E2E) delay upper bound of different characteristic traffic in the integrated 5G-TSN scenario. Furthermore, current scheduling solutions are not able to meet the scheduling demands of different hybrid traffic in the integrated 5G-TSN network. To address these issues, this article proposes an improved strict-priority Deficit Round-Robin (SP-DRR) scheduling strategy and incorporates it into a unified moment generating function (MGF) analytical framework, referred to as SP-DRR-MGF, for probabilistic E2E delay analysis in 5G–TSN networks. In this framework, the TSN wired segment is characterized through Time-Aware Shaper (TAS)/Credit-Based Shaper (CBS)-related service curves, the 5G wireless segment is modeled using Jake’s fading-based MGF service characterization with Meijer G-functions, and the 5G core segment is represented by the proposed SP-DRR scheduling strategy. These heterogeneous service components are mapped into a common ($\sigma_{s},\rho_{s}$)-bounded form and concatenated within the stochastic network calculus framework to derive the final E2E delay-violation bound. The results demonstrate that the proposed SP-DRR-MGF analysis matches the simulation results well under different operating conditions. Under the considered parameter settings and quasi-stationary fading assumption, the results indicate that the wireless segment becomes the dominant bottleneck once the wired-side service rate exceeds a certain threshold. The wireless resource scheduling strategy is the key to the E2E service guarantee in the 5G-TSN scenarios. Moreover, related parameters such as weight, quantum, and the number of allocated resource blocks (RBs) should be appropriately allocated to improve E2E delay according to a match requirement of delay upper bound and reliability. These observations provide stronger evidence that the proposed theoretical framework can serve not only as an effective approximation tool for realistic 5G-TSN networks, but also as a useful sensitivity-analysis and design-guidance tool for parameter tuning in practical deployments.