Abstract: Zero Trust (ZT) is a security paradigm aiming to curtail an attacker’s lateral movements within a network by implementing least-privilege and per-request access control policies. However, its widespread adoption is hindered by the difficulty of generating proper rules due to the lack of detailed knowledge of communication requirements and the characteristic behaviors of communicating entities under benign conditions. Consequently, manual rule generation becomes cumbersome and error-prone. To address these problems, we propose ZT-SDN , an automated framework for learning and enforcing network access control in Software-Defined Networks. ZT-SDN collects data from the underlying network and models the network “transactions’’ performed by communicating entities as graphs. The nodes represent entities, while the directed edges represent transactions identified by different protocol stacks observed. It uses novel unsupervised learning approaches to extract transaction patterns directly from the network data, such as the allowed protocol stacks and port numbers and data transmission behavior. Finally, ZT-SDN uses an innovative approach to generate correct access control rules and infer strong associations between them, allowing proactive rule deployment in forwarding devices. We show the framework’s efficacy in detecting abnormal network accesses and abuses of permitted flows in changing network conditions with real network datasets. Additionally, we showcase ZT-SDN’s scalability and the network’s performance when applied in an SDN environment.

Abstract: Mobile Ad Hoc Networks (MANETs) are decentralized wireless networks, characterized by their dynamic topologies and node mobility. In the era of cutting-edge technologies, integrating Software-Defined Networking (SDN) with MANETs offers a promising solution to manage these challenges more efficiently. This paper presents a balanced discussion of MANETs and SDN, demonstrating how SDN principles, such as centralized control and network virtualization, can optimize MANET performance in terms of scalability, cost-efficiency, and security. A mathematical model is developed to analyze Capital Expenditures (CAPEX), Operational Expenditures (OPEX), and network efficiency.

Abstract: This paper presents a security framework within a multicontroller Software-Defined Networking (SDN) architecture, focusing on Application Programming Interface (API) security. Our proposed Machine Learning (ML) based solution is able to detect API-specific threats without consuming a significant amount of bandwidth, which makes inter-controller communication secure in terms of confidentiality, integrity, and availability. The experimental study demonstrates the framework has an excellent detection accuracy of 97% and a precision rate of 96%, which exceeds existing models to identify events of the anomaly sequence in complex network environments. It achieves low false positive and false negative rates, allowing misclassification of non-threats to be reduced while truthfully categorizing real threats. Moreover, the system showcases resilience and adaptability to various attack types, such as DDoS attacks and access violations, significantly retaining its effectiveness across dynamic network topologies. The tests show less than 5% increase in CPU and memory usage and negligible impact on network latency, retaining overall network performance and user experience. Overall, the framework’s ability to provide high accuracy and precision levels in dynamic network environments highlights its performance under realistic, dynamic, and adaptive SDN scenarios. These results show the proposed approach as an effective and efficient framework for securing communications over APIs in SDN architectures.

Abstract: This paper proposes a hybrid machine learning-based framework for Software Defined Networking (SDN) environments, integrating a Deep Q-Network (DQN) for intelligent routing optimization and an Autoencoder for anomaly detection. The system dynamically learns optimal routing policies while simultaneously identifying network threats in real-time. Both real and synthetic datasets were used to validate the framework, demonstrating improved network efficiency and detection accuracy. Experimental results confirm the framework’s capability to adapt to diverse traffic patterns, optimize network flow, and secure SDN infrastructures effectively.

Abstract: The rapid growth of cloud computing and Software-Defined Networking (SDN) has necessitated efficient resource management to handle dynamic traffic demands in large- scale datacenters. This paper proposes a distributed framework for joint load balancing and Virtual Network Function (VNF) scaling to mitigate overload and underload condi- tions in SDN-based cloud environments. By leveraging the Alternating Direction Method of Multipliers (ADMM) and heuristic optimization techniques, our approach minimizes deployment and forwarding costs while ensuring efficient resource utilization. We formu- late the problem using Mixed Integer Linear Programming (MILP) and relax it into linear programming (LP) models to reduce computational complexity. Performance evaluations demonstrate that our method achieves faster convergence and lower resource overhead compared to centralized approaches, validated through simulations on k-fat-tree topolo- gies. Our findings highlight the potential of distributed optimization for scalable and robust network management in modern datacenters.

Abstract: ABSTRACT The Internet of Things (IoT) is an advanced technology that has seen significant growth over the past years. Because of the energy limitations of IoT devices, implementing effective managing practices to develop IoT applications remains a complicated task. One of the most critical IoT challenges that needs to be considered is routing, because of its significant impact on the consumption of energy. Software‐defined networking (SDN) is a method that decouples the control plane from the data plane, which enables the network administrators to program effectively. This work focuses on an energy‐aware communication protocol in SDN for a heterogeneous IoT model based on the proposed fractional poor rich optimization (FPRO). Initially, SDN is simulated and the SDN controller helps to map devices to particular applications for performing the counting process. The SDN poses triple layers, like the request analysis layer, routing layer, and communication layer. In the request analysis layer, the user requests are taken by the network devices. In the routing layer, clustering and routing are performed. Here, clustering is done by Bayesian fuzzy clustering (BFC) and routing is performed with FPRO. Here, FPRO is formed by combining fractional calculus (FC) with poor and rich optimization (PRO). Fitness is developed by considering the attributes that involve distance, delay, energy, and link cost. At last, the communication layer is used for transmitting data among nodes using optimal paths. The proposed FPRO‐based SDN showed superior performance with the least delay of 0.166 s, higher energy of 0.935 J, and higher throughput of 0.935 Mbps for 200 nodes.

Abstract: Software-Defined Networking (SDN) has ushered in a new era of network architecture, offering unparalleled flexibility and adaptability. However, this inherent flexibility also exposes SDN to security vulnerabilities, including Distributed Denial of Service (DDoS) attacks. Detecting and mitigating DDoS attacks within SDN environments is an imperative challenge. This work introduces an innovative DDoS detection scheme harnessing the power of Echo State Networks (ESN) tailored for SDN. Through a series of simulation experiments, we meticulously evaluate the proposed DDoS detection scheme. The results conclusively establish the scheme's effectiveness in accurately identifying and mitigating DDoS attacks, achieving an impressive average success rate of 97.78%. This research marks a significant advancement in fortifying the security of SDN networks, shielding them from disruptive DDoS threats, and emphasizes the potential of Echo State Networks as a valuable tool in the field of cybersecurity.

Abstract: SeqFuzzSDNAbstractControllers for software-defined networks (SDNs) are centralised software components that enable advanced network functionalities, such as dynamic traffic engineering and network virtualisation. However, these functionalities increase the complexity of SDN controllers, making thorough testing crucial. Unlike traditional network components (e.g., switches), SDN controllers are stateful, maintaining a holistic view of the network and interacting with multiple network devices through sequences of control messages. Identifying stateful failures in an SDN controller is challenging due to the infinite possible sequences of control messages, which result in an unbounded number of stateful interactions between the controller and network devices.In this article, we propose SeqFuzzSDN, a learning-guided fuzzing method for testing stateful SDN controllers.SeqFuzzSDN aims to:efficiently explore the state space of the SDN controller under test,generate effective and diverse tests (i.e., control message sequences) to uncover failures, andinfer accurate failure-inducing models that characterise the sequences of control messages leading to failures.In addition, we compare SeqFuzzSDN with three extensions of state-of-the-art (SOTA) methods for fuzzing SDNs, as none of them are directly comparable to SeqFuzzSDN.Our findings show that, compared to the extended SOTA methods, SeqFuzzSDN (1) generates more diverse message sequences (i.e., diverse stateful behaviours) that lead to failures within the same time budget, and (2) produces more accurate failure-inducing models, significantly outperforming the other extended SOTA methods in terms of sensitivity.PrerequisiteIn order to build and install SeqFuzzSDN, the following tools are required:Python >= 3.9Maven >= 3.9Java JDK >= 11MininetBuildThe source codes of the SeqFuzzSDN are implemented using Python3.9+ and Java11+. They can be compiled on any Linux distribution that supports Python3.9+ and Java11+, and the dependency libraries cited above.To compile the sources, the following steps are required:```bash$ cd src/leafsdn$ git clone$ make clean build```
After compilation, the python wheel of the application and the jar file of the fuzzer will be available under the folder`/dist/`.DeployTo install the application and the fuzzer, run the following command:```bash$ make deploy```The executable files will be installed under the folder `$XDG_HOME_BIN` (By default `~/.local/bin`).The configuration files will be installed under the folder `$XDG_CONFIG_HOME` (By default `~/.config`).UsageTo run a fuzzing campaign```bashusage: leafsdn run [-h] [--list-scenarios] [--failure FAILURE] [--log-level {trace,debug,info,warning,error}] [--fuzzer-jar-path FUZZER_JAR_PATH] [--fuzzer-socket-address FUZZER_SOCKET_ADDRESS] [--resume ITERATION PHASE]name {onos} scenario iterations exec_per_iter
Run fuzzing experiments on SDN controllers
positional arguments:name Name of the campaign to run{onos} Name of the controller to use for the campaignscenario Name of the scenario to run for the experiment. Run "leafsdn run --list-scenarios" to list the available scenarios.iterations Number of iterations to run for the experimentexec_per_iter Number of executions per iteration to run for the experiment
optional arguments:-h, --help Show this help message and exit--list-scenarios List the available scenarios and exit--failure FAILURE, -f FAILUREWhich failure to focus in the campaign. Default is `None`.--log-level {trace,debug,info,warning,error}Set the log level--fuzzer-jar-path FUZZER_JAR_PATHOverride the path to the fuzzer jar file--fuzzer-socket-address FUZZER_SOCKET_ADDRESSOverride the socket address of the fuzzer.--resume ITERATION PHASEResume the experiment from the specified iteration and phase```
2. To evaluate a fuzzing campaign```bashusage: leafsdn evaluation [-h] [--if-summary-exists] [--skip-plot [...]] campaign
Evaluate a fuzzing campaign from SeqFuzzSDN
positional arguments:campaign Name of the campaign to evaluate
optional arguments:-h, --help show this help message and exit--if-summary-exists What to do if the campaign has already been evaluated. Valid options are "update", "skip", or "error". Default is "error".--skip-plot [ ...] Skip the evaluation of certain parts of the campaign. Allowed values are "all" or any of the following: "data_models_performance", "efsm_sensitivity", "entropy_of_efsm_state_exercises", "error_rate", "pareto_front","traces_diversity_increase"```---
## Data Availability
The raw data that were generated during the experiments are not available in this artifact due to their large size (over 100GB, compressed).The treated data are however available in this artifact. To access those data or re-run the evaluation, extract the empirical folder under the same folder as SeqFuzzSDN.To access the raw data, please contact the authors of SeqFuzzSDN.

Abstract: A Software-Defined Networking (SDN)-based load balancer physically separates the network control plane from the forwarding plane and more than one device is able to be controlled at the same time when load balancing using SDN”. However, because of the higher loads on the control plane, the network capacity seems to be decreased. Therefore, to resolve this issue, the load could be split amongst different controllers. The uneven balancing of load amongst the controllers remains a challenging problem for the dynamic and scalability nature of SDN. Here, this paper aims to make a review on SDN load balancing systems. Accordingly, the literature review analyses the diverse techniques on SDN load balancing systems. At first, the survey portrays the diverse techniques adopted in each reviewed papers. Moreover, it offers the comprehensive analysis on the performance achievements and the respective maximum attainments in every contribution. Furthermore, the analysis concerns on diverse network configuration and topologies, and it also analyses the various tools adopted in each of the reviewed papers. Finally, it portrays the research issues that may help the researchers to carry out further analysis on SDN load balancing systems.

Abstract: Distributed Mobility Management (DMM) for vehicular communication networks was introduced to mitigate these issues of high-mobility scenarios, but load balancing and latency problems are still encountered. This paper proposes SDN-LB-DMM, a load-balanced handover control scheme for DMM leveraging Software-Defined Networking (SDN) to address these limitations. The proposed approach integrates a unified cost matrix that combines Received Signal Strength Indicator (RSSI) and access point (AP) loading to optimize the assignment of multiple mobile nodes (MNs) to next access points (NAPs) under an SDN controller. The handover decision is formulated as a linear programming model, solved using the Simplex method and refined with the Branch and Bound technique to achieve optimal integer solutions. Simulation results demonstrate that SDN-LB-DMM improves throughput, and reduces latency and packet loss.

Abstract: Software-Defined Networks employ software-based controllers and application programming interfaces to communicate with underlying hardware infrastructure in order to control network traffic. This study addressed two challenges. Firstly, it suggested the Bellman-Ford algorithm to overcome the drawbacks of Dijkstra's algorithm for packet routing between nodes in dynamic and large-scale networks. Second, the Bellman-Ford algorithm was used to determine the best among two software-defined network controllers: Floodlight and POX. Our results have showed that Floodlight is better than POX in terms of minimum, maximum, and average_RTT which may improve the experience of application usage and allow the applications to be more responsive.

Abstract: ABSTRACT Bufferbloat is a significant issue in network switches, arising from excessive packet buffering that leads to increased latency and degraded network performance. This happens when switches accumulate too many packets in their buffers, which causes transmission delays and negatively affects network efficiency. To address this problem, active queue management (AQM) algorithms are employed to dynamically adjust queue sizes and prevent congestion by selectively dropping packets. However, determining the optimal buffer size is crucial, as buffers that are too small can result in packet loss and reduced throughput. The integration of software‐defined networking (SDN) technology offers a promising solution by enabling efficient network configuration and monitoring. By incorporating AQM algorithms within SDN environments, significant improvements in network performance can be achieved. This paper introduces a novel hybrid active queue management (HAQM) algorithm, which combines elements of both packet‐oriented and delay‐oriented AQM techniques within an SDN framework. The evaluation demonstrates that the HAQM algorithm effectively enhances network performance by mitigating issues related to packet loss, delay, and jitter, outperforming existing algorithms like CoDel, CoBALT, ARED, and ECN.

Abstract: Traditional network architectures, characterized by their rigid, hardware-centric configurations, are increasingly challenged by the demands of modern applications, cloud computing, and the Internet of Things (IoT). These static infrastructures often lack the flexibility, scalability, and programmability required to manage dynamic and large-scale networks efficiently. Software-Defined Networking (SDN) emerges as a transformative paradigm that decouples the control plane from the data plane, offering centralized network intelligence and programmability. This abstraction enables network administrators to manage and configure network behavior dynamically through software-based controllers, leading to improved agility, automation, and policy enforcement. This paper explores the core principles of SDN, its architecture, benefits, and key use cases. Furthermore, it highlights the challenges in adoption, such as security, interoperability, and scalability. By analyzing current trends and future prospects, this study demonstrates how SDN is poised to reshape traditional network infrastructures, making them more adaptive and responsive to the evolving needs of digital ecosystems.

Abstract: This study explores how Software-Defined Networking (SDN) can improve network security by using its centralized control and programmability. Traditional networks are often fixed and slow to respond to new cyber threats, but SDN separates the control part from the part that moves data, making networks easier to manage and protect in real time. The research involved questionnaires and interviews with IT experts at Bohol Northern Star College to understand current SDN security practices, challenges, and benefits. A system design was created that uses SDN with tools like firewalls, intrusion detection systems, and machine learning to detect and stop attacks faster. The results showed that SDN helps improve threat detection, policy enforcement, and network monitoring, making networks more secure and flexible. However, the study also found that SDN has risks such as vulnerabilities in its software and the need for careful controller setup to avoid new security problems. Overall, SDN offers a powerful way to enhance network security, especially in environments like cloud computing and IoT, if implemented with strong protections and multi-controller setups to increase resilience.

Abstract: Abstract 5G communication networks rely heavily on optical fiber backbones for high capacity and low latency. Natural disasters like earthquakes, hurricanes, floods, and fires pose severe threats to infrastructure, causing fiber cuts, power outages, and equipment failures that can disrupt services when they are needed most. This paper presents comprehensive study of resilient optical network design for disaster-resistant 5G infrastructure. We review various disasters and their impacts on 5G networks, and we analyze resilient optical architectures (mesh topologies, ring networks, dual-homing of nodes, software-defined networking) that enhance survivability. We explore fault protection mechanisms like Automatic Protection Switching (APS) for fast failover, dynamic rerouting through intelligent control planes, and geographic route diversity to prevent single points of failure. Real-world case studies, including global and Indian examples, show both successes and shortcomings during disasters. To address these challenges, we propose a 5G optical transport network design with hybrid mesh-ring topology, dual-homed links, and SDN-based adaptive restoration for resilient recovery. Key challenges like cost, complexity, and operational constraints are examined, and future directions are outlined, including AI-driven network management, Beyond 5G (B5G) integration of satellite/FSO (Free Space Optics) links, and quantum-safe communications for secure and resilient networks. The goal is to guide the development of 5G and beyond communication infrastructures to maintain essential connectivity even amid large-scale disasters.

Abstract: Software Defined Network (SDN) has been widely used in modern network architecture. The integration of SDN into microgrid communication infrastructures offers enhanced flexibility, yet also introduces attack surfaces. As critical components of the Internet of Things (IoT) for energy systems, microgrid systems interact with numerous distributed sensors and controllers, making secure and reliable communications essential. It is well known that a labeled security dataset is indispensable for the community to validate the security solutions, in particular to the SDN intrusion detection systems. This study presents the SDN-MG25 dataset based on a realistic microgrid–SDN testbed, which is the first of its kind. This dataset contains benign network traffic generated from enterprise-level user activities, network flow records of microgrid communications, SDN activities, system call traces, and microgrid power measurements from an integrated SDN-based microgrid system. Additionally, a variety of SDN-related attack scenarios, such as fake link injection, flow rule tampering, and packet-in flooding, are implemented. A preliminary analysis is presented to evaluate the SDN-MG25 dataset. The SDN-MG25 dataset is publicly available for research in SDN-based microgrid and IoT energy environments.

Abstract: Edge computing has emerged as a critical paradigm for supporting latency-sensitive applications in Software-Defined Networking (SDN) environments. This paper proposes a dynamic resource orchestration framework that optimizes task offloading and resource allocation at the edge using a distributed optimization approach. By integrating Lyapunov optimization with SDNs centralized control, our method minimizes latency and energy consumption while ensuring quality of service (QoS). We formulate the problem as a Mixed Integer Non-Linear Programming (MINLP) model and propose a heuristic-based relaxation to enhance scalability. Simulations on edge-cloud topologies demonstrate that our approach achieves lower latency and higher resource efficiency compared to centralized methods, validated through extensive performance evaluations.