Performance Evaluation of Control Plane Signaling in 5G: A Novel Adaptive Software-Edge Architecture

Toward End-to-End Intent-Based Networking for 6G: Architectures, Challenges, Recent Advances, and Future Directions

Intent-Based Networking (IBN) has emerged as a promising paradigm for simplifying network management by allowing operators and applications to specify high-level service objectives rather than low-level device configurations. Early IBN research was mainly developed in Software-Defined Networking (SDN), Network Function Virtualization (NFV), transport networks, core networks, and data-center environments, where programmability, virtualization, and relatively stable infrastructure models enabled intent translation, orchestration, and assurance. However, realizing IBN in end-to-end mobile networks is more challenging because the Radio Access Network (RAN) is highly dynamic, wireless-channeldependent, mobility-sensitive, and governed by multiple control timescales. The emergence of Open RAN (O-RAN) changes this landscape by making the RAN programmable, disaggregated, data-driven, and control-lable through non-real-time and near-real-time intelligent control loops. This survey reviews the evolution of IBN from SDN/NFV-enabled automation toward O-RAN-driven end-to-end intent-based networking for 5G-Advanced and 6G. We discuss architectural mechanisms, key challenges, recent advances in AI-driven and agentic IBN, and future research directions including Large Language Model (LLM)-based intent translation, contractbased O-RAN slicing, digital twin-assisted validation, and trustworthy closed-loop orchestration.

Implementation of an Admission Control in SDN Network

Design of a Scalable Control Plane for Large-Scale SDNs

Software-Defined Networking (SDN) has become a major facilitator to flexible and programmable network operation; nevertheless, the extension of the control plane to handle big networks with heterogeneous networks has remained a core issue. The proposal presented in this paper is a design of a scalable control plane in a large SDN that can overcome the constraints of the centralized and fixed multi-controller designs. The suggested architecture takes the form of hierarchical and multi-controller structure with dynamically clustering and federation techniques to provide elasticity, fault tolerance, and effective use of resources. An assignment-based strategy to load-aware controllers is presented to dynamically assign switches to controllers in regard to real-time traffic intensity, control workload, and latency constraints whereas seamless controller migration ensures continuity of services in the face of network dynamics. The control plane also uses flow rule partitioning and aggregation to decrease state overhead and minimize redundant control operations in order to further ensure scalability. There is control message batching, adaptive poll, event based update and they are combined to reduce signaling overhead and enhance responsiveness by a large margin. A latency-aware controllerswitch mapping algorithm is also used to minimize control path delays to get rule installation and network convergence on time. Extensive performance analysis shows that the proposed design is almost linearly scalable as the network size is increased, and control latency is significantly lower and throughput is much higher than traditional SDN control plane designs. These findings affirm that the suggested scalable control plane is practical in supporting large scale SDN implementation and is therefore applicable in future carrier grade, data center and wide area network deployments at realistic workloads with varying topological setups in the modern programmable networks in the world.

Dynamic Controller Activation With Setup Penalty and Capacity Awareness in SDN-Enabled LEO Satellite Networks

The growing demand for adaptive, resilient communication in software-defined networking (SDN)-enabled low Earth orbit (LEO) satellite networks underscores the importance of optimized SDN controller management. In particular, the overhead introduced by setup penalties and constraints on controller capacity significantly impacts key performance metrics, including satellite-to-controller delay, reassignment frequency, and the number of concurrently active controllers. These factors collectively influence the network’s ability to provide low-latency services while maintaining resource utilization in dynamic orbital environments. To investigate these dynamics, we develop a simulation framework based on OMNeT++ and INET, extending the open-source satellite simulator OS3 with enhanced satellite mobility and dynamic routing. The framework integrates SDN functionality into LEO satellite networks using the OpenFlow protocol, enabling centralized, programmable control with real-time adaptability. A central challenge in such networks is not only assigning satellites to appropriate controllers, but also dynamically activating and deactivating SDN controllers to match evolving topologies and traffic demands. To address this, we consider the baseline Dynamic Satellite-to-Controller Assignment (DSCA), the proposed Optimal Dynamic Satellite-to-Controller Assignment (Opt-DSCA), and their scalable heuristic variants (H-DSCA and H-Opt-DSCA). Opt-DSCA jointly minimizes satellite-to-controller delay and the number of active controllers, while incorporating setup penalties and activation costs to discourage unnecessary satellite migrations and redundant controller utilization. Simulation results reveal that both setup penalties and controller activation thresholds are critical determinants of system behavior across both optimization-based and heuristic schemes. Lower penalties enhance adaptability but result in more frequent reassignments and higher variability in controller state transitions. Conversely, higher penalties improve robustness by limiting controller switching, though at the cost of reduced flexibility and increased latency. These findings highlight the necessity of jointly optimizing reassignment policies and controller activation strategies to support robust, low-latency, and resource-aware SDN architectures for large-scale LEO satellite constellations.

Adaptive Traffic-Aware Load Balancing Mechanism in Data Center Networks Using P4 Switches

As Data Center Networks (DCNs) continue to scale, the limitations of traditional centralized Software-Defined Networking (SDN) architectures become increasingly apparent, as they fail to meet the stringent demands for low latency and quality of service (QoS). In this paper, we propose an adaptive traffic-aware load balancing mechanism (ATL), a telemetrydriven in-switch scheme implemented on the programmable data plane (PDP) using P4 and driven by In-band Network Telemetry (INT). The current traffic regime is inferred by analyzing the remaining capacity (RC) of each link and its short-term variation (VAR), and adopts a dual-optimization strategy: (i) separating elephant flows (large flows) and mice flows (small flows) onto disjoint path sets to mitigate head-of-line blocking and packet reordering; (ii) dynamically adjusting the flowlet threshold $\left(F^{*}\right)$ to strike a balance between maximizing parallelism and ensuring in-order delivery. We prototyped and evaluated ATL in a Mininet/BMv2 environment, targeting bandwidth-constrained scenarios representative of IoT and edge deployments. The results show that, compared to existing methods such as ECMP, HULA, AWCMP, and APS, ATL consistently reduces both the average and 99th-percentile AFCT while achieving superior elephant-flow throughput, with notable improvements in traffic stability and packet-ordering preservation. Furthermore, ATL demonstrates a favorable cost-performance trade-off ratio of 1:0.99, confirming its efficiency and feasibility within the resource-constrained P4 switch environment.

Mitigating Security Challenges in 5G Wireless Networks

An AI-assisted, cross-layer security orchestration framework that integrates epoch-wise telemetry with ML-based risk estimation and formalizes mitigation as a Constrained Markov Decision Process (CMDP), and empirical evidence that adaptive mitigation can reduce security risk without sacrificing service guarantees is provided.