Search

Multipath TCP (MPTCP) is one of the leading transport layer protocols that enables multipath transmission to improve network performance. However, MPTCP can experience throughput degradation due to link congestion, which causes underutilizing of the network capacity. We proposed a new link congestion detection based on Software-Defined Networking (SDN) for MPTCP that detects and detours link congestion to achieve a stable MPTCP performance. Measurement results show that the proposed scheme enables efficient packet transmission by minimizing the effect of link congestion. Moreover, a combination of the proposed scheme and SDN monitoring enables dynamic traffic control based on the proposed link congestion detection.

Summary By controlling the network, the Internet of Things (IoT)‐connected software‐defined network (SDN) limits the scalability of IoT devices. Since SDN depends on a centralized controller that attackers can easily affect, it is incredibly susceptible to attacks. Secure access control to the SDN controller was the focus of the prior methods for controller scalability and restricted trust management. A framework called Safeguard Authentication Dynamic Access Control (SANDMAC) is suggested to safeguard and offer useful services to enterprises. Authentication confirms legitimacy after all users and applications have been registered. To improve network security, policies let users grant access to account attributes, legal activities, and temporal components. The administrator lessens conflicts between the methods by validating and saving the policies in the database. The services are provided to dependable customers using the forensic‐based investigation algorithm, depending on the quality of service and software level agreements requirements, decreasing reaction times and maximizing resource usage. Performance comparisons between the new and previous efforts are validated using a variety of parameters, and the proposed work is validated using the iFogSim application. According to the findings, SANDMAC significantly raises key performance indicators. SANDMAC specifically keeps false positives at 3.5% and accomplishes a low response time of 60 ms for roughly 800 authorized accesses. SANDMAC is a better option because of these enhancements, which result in longer network lifetimes and more dependable data transmission. [ABSTRACT FROM AUTHOR]

Software-defined networks (SDN) rely on flow tables to forward packets from different flows with different policies. To speed up packet forwarding, the rules in the flow table should reside in the forwarding plane as much as possible to reduce the chances of consulting the SDN controller, which is a slow process. The rules are usually cached in the forwarding plane with a Ternary Content Addressable Memory (TCAM) device. However, a TCAM has limited capacity, because it is expensive and power-hungry. As a result, wise caching of a subset of flow rules in TCAM is needed. In this paper, we address two related issues that affect caching efficiency: rules to be cached and rules to be replaced. For the first issue, caching an active rule hit by a flow may need to cache inactive rules due to rule dependency. We propose a two-stage caching architecture called CRAFT, which reduces inactive rules in cache by cutting down long dependent chains and by partitioning rules with massive dependent rules into non-overlapping sub-rules. For the second issue, unawareness of the flow traffic characteristics may evict heavy hitters instead of mice flows. We propose RRTC to address this issue, which is a rule replacement policy taking the real-time network traffic characteristics into consideration. By recognizing the heavy hitters and protecting their matching rules in TCAM, RRTC performs better than least recently used(LRU) policy in terms of cache hit ratio. Simulation results show that our combined rule caching and replacement framework outperforms previous work considerably. [ABSTRACT FROM AUTHOR]

Software-defined vehicular networks (SDVN) is a promising technology for wireless data transmissions between vehicles. SDVN inherits software-defined networking principles and aims to improve the typical performance of safety and non-safety applications of vehicular adhoc networks. Consequently, enhancing the performance of Intelligent Transportation System (ITS). However, the performance of these ITS applications largely depends on the computational capability of the controller node, which involves creating or destroying a data path from the source vehicle to the destination vehicle and generating flow rules for the requests coming from the data plane elements. As a result, SDVN often suffers from the problems of overburdening the controller node with route requests under heavy traffic generation at vehicles and single-point controller failure. To counter these problems, solutions based on multiple controllers are proposed. In fact, the load-balancing problem remains an important issue. So, routing of data with multiple controllers and load-balancing, both topics in SDVN, go hand in hand. In this paper, we survey this state-of-the-art that discusses the above-mentioned challenges, starting with the SDVN preliminaries. We scrutinize the existing routing methodologies and also discuss load-balancing techniques. Furthermore, we provide real-time applications and services of SDVN, discuss trending research, potential future research directions, and the real-life applicability of SDVN that have not been addressed previously. [ABSTRACT FROM AUTHOR]

The fifth-generation (5G) cellular infrastructure is expected to bring about the widespread use of connected vehicles. This technological progress marks the beginning of a new era in vehicular networks, which includes a range of different types and services of self-driving cars and the smooth sharing of information between vehicles. Connected vehicles have also been announced as a main use case of the sixth-generation (6G) cellular, with ultimate requirements beyond the 5G (B5G) and 6G eras. These networks require full coverage, extremely high reliability and availability, very low latency, and significant system adaptability. The significant specifications set for vehicular networks pose considerable design and development challenges. The goals of establishing a latency of 1 millisecond, effectively handling large amounts of data traffic, and facilitating high-speed mobility are of utmost importance. To address these difficulties and meet the demands of upcoming networks, e.g., 6G, it is necessary to improve the performance of vehicle networks by incorporating innovative technology into existing network structures. This work presents significant enhancements to vehicular networks to fulfill the demanding specifications by utilizing state-of-the-art technologies, including distributed edge computing, e.g., mobile edge computing (MEC) and fog computing, software-defined networking (SDN), and microservice. The work provides a novel vehicular network structure based on micro-services architecture that meets the requirements of 6G networks. The required offloading scheme is introduced, and a handover algorithm is presented to provide seamless communication over the network. Moreover, a migration scheme for migrating data between edge servers was developed. The work was evaluated in terms of latency, availability, and reliability. The results outperformed existing traditional approaches, demonstrating the potential of our approach to meet the demanding requirements of next-generation vehicular networks. [ABSTRACT FROM AUTHOR]

In an era characterized by the proliferation of the Internet of Things (IoT), the seamless interconnection of diverse devices has revolutionized various sectors. However, this rapid expansion has brought forth significant security concerns, making effective anomaly detection crucial for safeguarding IoT networks. This research introduces a pioneering framework for dynamic behavioral profiling and anomaly detection in Software-Defined IoT Networks (SD-IoT). By leveraging the inherent advantages of SDN, this framework enhances the security and resilience of IoT ecosystems. Through a meticulous step-by-step process, dynamic profiles of IoT devices' behavior are generated to capture evolving attributes over time. Machine learning-based anomaly detection algorithms analyzed profiles to identify deviations from normal behavior and to effectively detect potential security threats. Anomalies detected trigger real-time policy adaptations that contain and mitigate their impact. The SDN controller enforces these adapted policies, preventing anomaly propagation and ensuring network integrity. To evaluate the framework's efficacy, extensive experiments are conducted using a comprehensive datasets in the simulated IoT environment. The results demonstrated the accuracy of dynamic behavioral profiling, the adaptability of the policy adjustments, and the efficiency of the anomaly detection algorithm. The proposed framework holds immense promise in fortifying IoT networks against emerging threats, contributing to the security and stability of our increasingly interconnected world. The comparative analyses in the performance validation showed that the proposed model attained better anomaly detection performances than other existing models. [ABSTRACT FROM AUTHOR]

Software-defined networks (SDN) enable flexible and effective communication systems that are managed by centralized software controllers. However, such a controller can undermine the underlying communication network of an SDN-based system and thus must be carefully tested. When an SDN-based system fails, in order to address such a failure, engineers need to precisely understand the conditions under which it occurs. In this article, we introduce a machine learning-guided fuzzing method, named FuzzSDN, aiming at both (1) generating effective test data leading to failures in SDN-based systems and (2) learning accurate failure-inducing models that characterize conditions under which such system fails. To our knowledge, no existing work simultaneously addresses these two objectives for SDNs. We evaluate FuzzSDN by applying it to systems controlled by two open-source SDN controllers. Furthermore, we compare FuzzSDN with two state-of-the-art methods for fuzzing SDNs and two baselines for learning failure-inducing models. Our results show that (1) compared to the state-of-the-art methods, FuzzSDN generates at least 12 times more failures, within the same time budget, with a controller that is fairly robust to fuzzing and (2) our failure-inducing models have, on average, a precision of 98% and a recall of 86%, significantly outperforming the baselines. [ABSTRACT FROM AUTHOR]

Mobile users can access vital real-time services through wireless paradigms like software-defined network (SDN) topologies and the Internet of Things. Point-of-contact-based infrastructures and dynamic user densities increase resource access and service-sharing concurrency. Thus, controlling power consumption and network and device congestion becomes a major issue for SDN-based IoT applications. This paper uses the Controlled Service Scheduling Scheme (CS3) to address the challenge of simultaneous scheduling and power allocation. The suggested approach uses deep recurrent learning and probabilistic balancing for power allocation and service distribution during user-centric concurrent sharing intervals. The SDN control plane decides how much power to use for service delivery while forecasting user service demands directs the scheduling interval allocation. Power management is under the control plane of the SDN, whereas service distribution is under the data plane. Power-to-service requirements are evaluated probabilistically, and updates for both aircraft are obtained via the deep learning model. This allocation serves as the basis for training the learning model to alleviate power deficits across succeeding intervals. The simulation experiments are modeled using the Contiki Cooja simulator, where 200 mobile users are placed. The proposed plan delivers a 14.9% high-service distribution for various users, 18.29% less delay, 13.34% less failure, 5.54% less downtime, and 18.68% less power consumption. [ABSTRACT FROM AUTHOR]

The proliferation of software-defined networks (SDN) increases the necessity of security and forensic research in this field. Network forensics is of particular importance considering the ever-increasing traffic density and variety of devices, and SDN has great potential for improved forensic processes thanks to its ability to provide a centralized view and control of the network. This article's motivation is the lack of a standard forensic process in SDN. The main objective of this study is to examine the differences in the forensic processes of different SDN controllers, whether the southbound interface data is sufficient for the forensic processes, and whether it is possible to choose the best controller in terms of forensics. Four of the most widely used controllers have been selected and tested under seven different scenarios to observe how the results were obtained in terms of forensics. During the tests, in addition to the routine data accesses, attack preparation tools and denial-of-service attack tools were used to expand the scope. Experiments in which each scenario was applied for four different controllers demonstrated that different controllers have different characteristics in network forensics parameters, such as attack type detection, attacker information, service interruptions, packet size, and the number of packets. Experiments proved that southbound interface data is sufficient for forensic processes, different controllers have different characteristics in forensic processes, none of the most used controllers is the best to cover all forensic processes, and a standard forensic method is required for software-defined network forensics. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) attacks pose a challenging threat to the availability and performance of cloud-based Software-Defined Networks (SDNs). Detection and classification of DDoS attacks in such dynamic and highly virtualized environments is critical to maintaining network stability and ensuring uninterrupted services. Therefore, this study develops a metaheuristic with Multi-Layer Ensemble Deep Reinforcement Learning for DDoS Attack Detection and Mitigation (MMEDRL-ADM) technique in the Cloud SDN Environment. The presented MMEDRL-ADM technique leverages metaheuristics with deep learning model for the recognition of DDoS attacks in the SDN data plane. To accomplish this, the presented MMEDRL-ADM technique initially preprocesses the network data. Next, the MMEDRL-ADM technique designs African buffalo optimization algorithm-based feature selection (ABO-FS) to reduce the computation complexity and increase the detection rate. For DDoS attack detection, the multilayer ensemble deep reinforcement learning (MEDRL) technique is used. To adjust the hyperparameter values of the MEDRL technique, an improved grasshopper optimization algorithm (IGOA) is exploited. The design of MEDRL approach with IGOA based hyperparameter tuning demonstrates the novelty of the work. The experimental validation of the MMEDRL-ADM system is tested under a benchmark dataset. The comparison study highlighted the improved performance of the MMEDRL-ADM technique over other models. [ABSTRACT FROM AUTHOR]

Group management is practiced to deploy access control and to ease multicast and broadcast communication. However, the devices that constitute the Internet of Things (IoT) are resource-constrained, and the network of IoT is heterogeneous with variable topologies interconnected. Hence, to tackle heterogeneity, SDN-aided centralized group management as a service framework is proposed to provide a global network perspective and administration. Group management as a service includes a group key management function, which can be either centralized or decentralized. Decentralized approaches use complex cryptographic primitives, making centralized techniques the optimal option for the IoT ecosystem. It is also necessary to use a safe, scalable approach that addresses dynamic membership changes with minimal overhead to provide a centralized group key management service. A group key management strategy called a one-way Function Tree (OFT) was put forth to lower communication costs in sizable dynamic groups. The technique, however, is vulnerable to collusion attacks in which an appending and withdrawing device colludes and conspires to obtain unauthorized keys for an unauthorized timeline. Several collusion-deprived improvements to the OFT method are suggested; however, they come at an increased cost for both communication and computation. The Modified One-Way Function Tree (MOFT), a novel technique, is suggested in this proposed work. The collusion resistance of the proposed MOFT system was demonstrated via security analysis. According to performance studies, MOFT lowers communication costs when compared to the original OFT scheme. In comparison to the OFT's collusion-deprived upgrades, the computation cost is smaller. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Polytechnic is the property of Journal of Polytechnic and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The Internet of Things (IoT) has transformed our lives by introducing new services and enhancing productivity. However, the widespread adoption of IoT devices and communication units has posed challenges in network management. In response, there is a growing necessity to rethink and redesign IoT network control. Software-defined networking (SDN) has emerged as a promising solution, leveraging its programmability and centralized management capabilities. SDN can simplify network management, offer network abstraction, facilitate development, and efficiently handle the complexities of IoT networks. Despite these advantages, security concerns, particularly the threat of Distributed Denial of Service (DDoS) attacks, persist in the IoT landscape. This survey focuses on exploring the collaboration between SDN and IoT. It investigates various types of DDoS attacks and highlights different types of defense, detection, and mitigation methods employed to address DDoS threats in SDN-based IoT (SDN-IoT) networks.

The increasing need for smarter means of transportation has brought a greater focus on Vehicular Ad-Hoc Networks (VANETs). VANETs are characterized by frequent topology changes due to the high node mobility, and most of the existing network protocols for mobility management are not well prepared for persistent horizontal handovers. This work studies the integration of Software-Defined Networking (SDN) in the Intelligent Transportation Systems (ITS) universe for the mobility management of VANETs. The idea is to explore the Cooperative Intelligent Transport Systems (C-ITS) messages in the SDN universe allowing the SDN controller to have a deeper view of the topology state. This global view gives the controller proactiveness, anticipating handovers even before they happen, reducing handover delays, and thus, improving the user experience. To evaluate the proposed approach, two types of environments were considered, laboratory and real-world at city scale with connected vehicles and infrastructure. The performance results have shown great improvements compared with a non-proactive approach: exploring the benefits of integrating the ITS and SDN universes, we obtained an almost zero packet loss rate, a reduction in the average delay and an increase in the connectivity time.

Efficient monitoring systems that optimize resource allocation, reduce energy usage through machine learning and flow aggregation routing techniques, are needed due to the escalating power consumption of data center networks, which, as has been recently reported, account for up to eight percent of global energy consumption, posing environmental operational concerns. We propose a software-defined data-center monitoring algorithm that reduces power consumption by: 1) using a GPU implementation of a Stacked Long Short-Term Memory Recurrent Neural Network (RNN) model for link utilization prediction, thus reducing monitoring overhead; and 2) utilizing a flow aggregation routing algorithm with feedback from online, OpenFlow-powered monitoring and machine learning modules. This combined approach results in a new algorithm called SMart-Fill Prefer Path First (SM-FPLF). In the context of SM-FPLF, the objective of this paper is to compare the: 1) training and validation loss curves for various models; 2) to evaluate the prediction accuracy of learning approaches for a range of prediction horizons; 3) to assess the time-cost and accuracy for different models, with a specific focus on the GuSLSTM and GuGRU models; 4) to analyze OpenFlow traffic with and without using the preferred prediction algorithm, the GuSLSTM model, assessing the accumulated power consumption per OpenFlow channel in the data-centre when SM-FPLF is applied. Our findings indicate that the GuSLSTM outperforms rival algorithms in terms of link utilization prediction accuracy over varying input sequence lengths. This accuracy is achieved whilst satisfying the SDN domain-specific requirement of a small computation time in a real-time implementation. Embedding a GuSLSTM in the SM-FPLF algorithm offers a power saving of 372 watts per OpenFlow channel, which is achieved in part due to a 13.7% CPU usage reduction in controllers and switches. These findings provide a valuable perspective into the performance and suitability of RNNs for real-time implementation as part of SDN solutions. They also shed light on their practical implications and benefits of using link utilization prediction in SDN management and power consumption optimization solutions.

Network management is a crucial task to maintain modern systems and applications running. Some applications have become vital for society and are expected to have zero downtime. Software-defined networks is a paradigm that collaborates with the scalability, modularity and manageability of systems by centralizing the network’s controller. However, this creates a weak point for distributed denial of service attacks if unprepared. This study proposes an anomaly detection system to detect distributed denial of service attacks in software-defined networks using generative adversarial neural networks with gated recurrent units. The proposed system uses unsupervised learning to detect unknown attacks in an interval of 1 second. A mitigation algorithm is also proposed to stop distributed denial-of-service attacks from harming the network’s operation. Two datasets were used to validate this model: the first developed by the computer networks study group Orion from the State University of Londrina. The second is a well-known dataset: CIC-DDoS2019, widely used by the anomaly detection community. Besides the gated recurrent units, other types of neurons are also tested in this work, they are: long short-term memory, convolutional and temporal convolutional. The detection module reached an F1-score of 99@ in the first dataset and 98@ in the second, while the mitigation module could drop 99@ of malicious flows in both datasets.

The increasing need for high-precision monitoring and network-wide observability has spurred significant interest in In-Band Network Telemetry (INT), which empowers the collection of monitoring data directly from the dataplane, thus, alleviating the various shortcomings of passive monitoring techniques. INT, in some of its initial forms (e.g., P4-INT), tends to accumulate per-hop telemetry values within each packet, introducing substantial transmission overhead. Recent efforts to alleviate this shortcoming spread per-hop telemetry values among multiple packets, but eventually cause other implications, such as INT data redundancy or collisions during state lookup, stemming from the probabilistic data structures that they employ. Along these lines, we stress on the need for a lightweight INT approach with deterministic behavior. To this end, we present a new INT approach (Controller-Assisted Lightweight In-Band Network Telemetry – CLINT) that relies on a telemetry controller for the coordination of INT nodes, through the update of telemetry states, which indicate at each instance the telemetry action that should be applied to each incoming packet. We discuss in detail the operation of CLINT, as well as its prototype implementation using P4 BMv2 and the P4Runtime API. Our evaluation results indicate that CLINT outperforms two state-of-the-art lightweight INT techniques (i.e., PINT and DLINT) in terms of monitoring efficiency and network update detection, while maintaining an insignificant control communication overhead.

Traffic classification (TC) in software-defined networks (SDN) using machine learning (ML) appears to be a viable option for improving network management. TC improves SDN operability, while SDN speeds up the feature selection (FS) process, especially when ML is used as a classification mechanism to extract measurements and related information from incoming data to the SDN controller. Despite these advantages, there is still a lack of adequate support for TC and FS tasks due to the frequent similarity of traffic profiles, making classification difficult. Furthermore, when combined with TC, stream learning (SL) poses numerous challenges. As a result, robust statistical flow features are needed to reduce the overhead of the SDN control plane. As a result, these statistical flow features could extract online features, handle concept drift, and process an infinite data stream using limited resources (time and memory). This paper aims to improve the overall performance of TC using the SL technique to select relevant FS to alleviate load from the SDN control plane by doing the following. First, an FS mechanism called Boruta is proposed. Second, we propose three streaming-based TC methods for SDN: Hoeffding adaptive trees (HAT), adaptive random forest (ARF), and k-nearest neighbour with adaptive sliding window detector (KNN-ADWIN). These techniques can dynamically handle the concept drift and solve the problem of memory and time consumption, lowering the overhead of the SDN controller. Third, real and synthetic traffic traces are used to evaluate the proposed FS and streaming TC performance. According to simulation results, the Boruta FS technique can achieve up to 95% average accuracy and up to 87% average per application in terms of precision, recall, and f-score, outperforming other works in the literature. Furthermore, results for SL techniques show that the proposed methods can maintain up to 85% average accuracy, 78% kappa, and average rates of 62-88% in precision, recall, and f-score. In addition, when compared to ART and KNN-ADWIN, the HAT consumes less time and memory (15s and 105KB, respectively).

Software-Defined Networking (SDN) is susceptible to security threats despite all the network programmability and flexibility offered, and hence SDN must be safeguarded.This work proposes an Intelligent Intrusion Detection System for Software-Defined Networks (SD-IIDS) that creates two equally competent ensemble Machine Learning (ML) classification models for detecting Distributed Denial of Service (DDoS) attacks in SDN. The developed ensemble models act as binary and multi-class classification algorithms. The models are Support Vector Classifier bagged with Random Forest (SVC-RF), and Random Forest bagged with Logistic Regression (RF-LR). The multi-class SVC-RF and RF-LR detect the the DDoS attack types with 98.83% and 99.54% accuracy and minimal False Alarm Rate (FAR) of 0.0189 and 0.012, respectively. The binary SVC-RF and RF-LR algorithms classify the network traffic into malicious and legitimate classes, with 99.42% and 99.79% accuracy and a nominal FAR of 0.0005 and 0.002, respectively. This work's core innovation is choosing the champion model among the two ensemble ML models based on its classification performance metrics and complexity analysis. The other major contribution of the work is botnet detection leveraging data mining techniques. The multi-class RF-LR ensemble outperformed multi-class SVC-RF with 99.45% precision and 99.46% sensitivity. The optimal performance metrics imply that the proposed ensemble models have greater efficacy than the individual ML models. This work paves the way for future research to detect the most potent volume-based and protocol-based DDoS attacks in SDN. [ABSTRACT FROM AUTHOR]

Traffic engineering of software-defined networks (SDNs) refers to network traffic monitoring and network status analysis to improve network performance, which can be achieved by addressing a variety of issues such as routing, congestion control, flow control, and load balancing. In this paper, a new traffic engineering approach is proposed that attempts to manage the traffic of SDN by adjusting the retransmission timeout. In the proposed approach, the initial retransmission timeout is determined based on transmission and propagation delays, and then this time is adaptively adjusted according to the priority of the packets, which depends on the type of packet and the number of elapsed hops. The conducted simulations in the Mininet tool have validated the effectiveness of the proposed approach in comparison to counterpart methods in terms of average throughput, average bandwidth utilization, end-to-end delay, and packet loss ratio. Eventually, analysis of the time complexity and message complexity demonstrates that the overhead of the proposed approach is negligible. [ABSTRACT FROM AUTHOR]

Software-defined networks (SDN) are no more a new technology as many industries are adopting it in a hybrid or full stack mode. SDN has already proved its technological advantages compared to the traditional networking technologies. The proposed work RADS leverages the architectural advantages of SDN and employs a flexible dynamic threshold approach to detect the anomalies in near real time using machine learning algorithms (ARIMA), and within 150 ms, the user is alerted about the attack so that necessary actions can be taken. A proof of concept for RADS is developed using mininet to create the SDN topology, Elasticsearch as the database to store the packet information and result of machine learning model. ARIMA, linear regression and Prophet models are considered for detecting anomalies, and the resulting graphs show the time taken to detect the attack is achieved in near real time. [ABSTRACT FROM AUTHOR]

In the ever-evolving landscape of wireless communication, the demand for efficient spectrum utilization is paramount. The research begins by acknowledging the existing challenges in CR within SDNs, particularly the need for adaptive strategies to dynamically allocate spectrum resources. A critical research gap lies in the absence of an approach that seamlessly integrates Gated Dual-Path RNNs and Adaptive Dimensional Search to enhance the adaptability and efficiency of CR systems. The proposed methodology leverages the power of Gated Dual- Path RNNs for real-time learning and decision-making, coupled with an Adaptive Dimensional Search algorithm for dynamic spectrum allocation. This study introduces a novel approach, the Gated Dual- Path Recurrent Neural Network (RNN) Empowered Adaptive Dimensional Search, tailored for Cognitive Radio (CR) in Software- Defined Networks (SDNs). The escalating proliferation of wireless devices and applications has exacerbated the spectrum scarcity problem, necessitating intelligent solutions to optimize spectrum utilization. This dual-path architecture enables the CR system to capture temporal dependencies in the spectrum environment and adaptively adjust its parameters for optimal performance. The experimental results demonstrate the efficacy of the proposed approach, showcasing significant improvements in spectrum utilization efficiency, throughput, and adaptability compared to traditional methods. The Gated Dual-Path RNN Empowered Adaptive Dimensional Search proves to be a robust solution for enhancing CR capabilities in SDNs, paving the way for more intelligent and adaptive wireless communication systems. [ABSTRACT FROM AUTHOR]

To address the challenges posed by traditional network architectures, the SoftwareDefined Network (SDN) architecture was introduced. However, SDNs are not immune to many security threats (e.g. Dos, Backdoors). In this paper, we present an advanced intrusion detection system that leverages federated learning (FL) and deep learning (DL) techniques to check whether attacks occur or not on SDN. FL has been employed as a collaborative learning technique, enabling various data planes to conduct local training on their respective client datasets. Following local training on each data plane, the local model parameters are securely transmitted to the controllerserver. At the controllerserver, these local training parameters are aggregated to construct a global model. The resulting aggregation outcome is then shared back with each local model to update them, enhancing their ability to detect attacks. Three datasets were used to evaluate the efficacy of the suggested method: UNSW-NB15, NF-UQ-NIDS-v2, and CICIDS2017. The obtained results demonstrate a strong performance in anomaly detection, with an accuracy value reach to 95.68% [ABSTRACT FROM AUTHOR]

Health monitoring systems (HMS) with wearable IoT devices are constantly being developed and improved. But most of these gadgets have limited energy and processing power due to resource constraints. Mobile edge computing (MEC) must be used to analyze the HMS information to decrease bandwidth usage and increase reaction times for applications that depend on latency and require intense computation. To achieve these needs while considering emergencies under HMS, this work offers an effective task planning and allocation of resources mechanism in MEC. Utilizing the Software Denied Network (SDN) framework; we provide a priority-aware semi-greedy with genetic algorithm (PSG-GA) method. It prioritizes tasks differently by considering their emergencies, calculated concerning the data collected from a patient’s smart wearable devices. The process can determine whether a job must be completed domestically at the hospital workstations (HW) or in the cloud. The goal is to minimize both the bandwidth cost and the overall task processing time. Existing techniques were compared to the proposed SD-PSGA regarding average latency, job scheduling effectiveness, execution duration, bandwidth consumption, CPU utilization, and power usage. The testing results are encouraging since SD-PSGA can handle emergencies and fulfill the task’s latency-sensitive requirements at a lower bandwidth cost. The accuracy of testing model achieves 97 to 98% for nearly 200 tasks. [ABSTRACT FROM AUTHOR]

Software-Defined Networking (SDN), which is used in Industrial Internet of Things, uses a controller as its "network brain" located at the control plane. This uniquely distinguishes it from the traditional networking paradigms because it provides a global view of the entire network. In SDN, the controller can become a single point of failure, which may cause the whole network service to be compromised. Also, data packet transmission between controllers and switches could be impaired by natural disasters, causing hardware malfunctioning or Distributed Denial of Service (DDoS) attacks. Thus, SDN controllers are vulnerable to both hardware and software failures. To overcome this single point of failure in SDN, this paper proposes an attack-aware logical link assignment (AALLA) mathematical model with the ultimate aim of restoring the SDN network by using logical link assignment from switches to the cluster (backup) controllers. We formulate the AALLA model in integer linear programming (ILP), which restores the disrupted SDN network availability by assigning the logical links to the cluster (backup) controllers. More precisely, given a set of switches that are managed by the controller(s), this model simultaneously determines the optimal cost for controllers, links, and switches. [ABSTRACT FROM AUTHOR]

In this paper, a routing method based on reinforcement learning (RL) under software-defined networks (SDN), namely the Q-learning widest-path routing algorithm (Q-WPRA), is proposed. This algorithm processes the reward function according to the link bandwidth in the execution environment to find the optimal (i.e., widest) transmission path with the maximum bandwidth between the source and the destination through RL. The experimental results reveal that the Q-WPRA is outperformance than Dijkstra’s algorithm and Dijkstra’s widest-path algorithm to find the widest transmission path in SDN environment under different bandwidths, loss rates, and background traffic.

The fifth-generation (5G) cellular infrastructure is expected to bring about the widespread use of connected vehicles. This technological progress marks the beginning of a new era in vehicular networks, which includes a range of different types and services of self-driving cars and the smooth sharing of information between vehicles. Connected vehicles have also been announced as a main use case of the sixth-generation (6G) cellular, with ultimate requirements beyond the 5G (B5G) and 6G eras. These networks require full coverage, extremely high reliability and availability, very low latency, and significant system adaptability. The significant specifications set for vehicular networks pose considerable design and development challenges. The goals of establishing a latency of 1 millisecond, effectively handling large amounts of data traffic, and facilitating high-speed mobility are of utmost importance. To address these difficulties and meet the demands of upcoming networks, e.g., 6G, it is necessary to improve the performance of vehicle networks by incorporating innovative technology into existing network structures. This work presents significant enhancements to vehicular networks to fulfill the demanding specifications by utilizing state-of-the-art technologies, including distributed edge computing, e.g., mobile edge computing (MEC) and fog computing, software-defined networking (SDN), and microservice. The work provides a novel vehicular network structure based on micro-services architecture that meets the requirements of 6G networks. The required offloading scheme is introduced, and a handover algorithm is presented to provide seamless communication over the network. Moreover, a migration scheme for migrating data between edge servers was developed. The work was evaluated in terms of latency, availability, and reliability. The results outperformed existing traditional approaches, demonstrating the potential of our approach to meet the demanding requirements of next-generation vehicular networks.

Mobile users can access vital real-time services through wireless paradigms like software-defined network (SDN) topologies and the Internet of Things. Point-of-contact-based infrastructures and dynamic user densities increase resource access and service-sharing concurrency. Thus, controlling power consumption and network and device congestion becomes a major issue for SDN-based IoT applications. This paper uses the Controlled Service Scheduling Scheme (CS3) to address the challenge of simultaneous scheduling and power allocation. The suggested approach uses deep recurrent learning and probabilistic balancing for power allocation and service distribution during user-centric concurrent sharing intervals. The SDN control plane decides how much power to use for service delivery while forecasting user service demands directs the scheduling interval allocation. Power management is under the control plane of the SDN, whereas service distribution is under the data plane. Power-to-service requirements are evaluated probabilistically, and updates for both aircraft are obtained via the deep learning model. This allocation serves as the basis for training the learning model to alleviate power deficits across succeeding intervals. The simulation experiments are modeled using the Contiki Cooja simulator, where 200 mobile users are placed. The proposed plan delivers a 14.9% high-service distribution for various users, 18.29% less delay, 13.34% less failure, 5.54% less downtime, and 18.68% less power consumption.

Critical issues such as connection congestion, long transmission delay, and packet loss become even worse during epidemic, disaster, and so on. In this study, a link load balancing method is proposed to address these issues on the data plane, a plane of the software-defined network (SDN) architecture. These problems are NP-complete, so a meta-heuristic approach, discrete particle swarm optimization, is used with a novel hybrid cost function. The superiority of the proposed method over existing methods in the literature is that it provides link and switch load balancing simultaneously. The goal is to choose a path that minimizes the connection load between the source and destination in multipath SDNs. Furthermore, the proposed work is dynamic, so selected paths are regularly updated. Simulation results prove that with the proposed method, streams reach the target with minimum time, no loss, low power consumption, and low memory usage.

As the scale and complexity of networks grow rapidly, management, maintenance, and optimization of them are becoming increasingly challenging tasks for network administrators. Software-Defined Networking (SDN) was introduced to facilitate these tasks as it offers logically centralized control, a global view of the network, and software-based traffic analysis, thus, it is widely adopted of SDN to manage large-scale networks. On the other hand, SDN is not immune to cyber attacks. In fact, its centralized architecture makes it more vulnerable to certain types of attacks, such as denial of service. Various attack mitigation strategies are proposed to strengthen the security of SDNs including statistical, threshold-based, and Machine Learning (ML) methods. Among them, Deep Learning (DL)-based models attained the best results as they were able to extract the complex relationship between input parameters and output that could not be achieved with other solutions. Hence, this paper presents a comprehensive survey of the literature on the utilization of different DL algorithms for the security of SDN. We first explain the types of attacks that SDNs are exposed to, then present papers that applied DL to detect and/or mitigate these attacks. We further discuss the public datasets used to train DL models and evaluate their advantages and disadvantages. Finally, we share insights into future research directions to improve the efficiency of DL methods for SDN security. [ABSTRACT FROM AUTHOR]

Software-defined networks (SDNs), while offering a revolutionary global view of the network, remain susceptible to a variety of attacks. This vulnerability necessitates innovative solutions for preserving data privacy and enhancing network security. The work presented herein introduces an innovative network anomaly detection methodology leveraging both federated learning (FL) and deep learning (DL) techniques. In contrast to traditional collaborative learning, where potential privacy compromises arise from the distribution of local training data to a central server, the proposed methodology enables each switch in the network to collect data from its connected hosts and independently train a local Long Short-Term Memory (LSTM) model. Subsequently, each switch encrypts and forwards its model parameters to the controller. Upon receipt, the controller decrypts the parameters from each switch, computes their average, and formulates a global LSTM model. This model is disseminated to every switch in the network, enabling each host to retrain its local model according to the global parameters. This iterative process is conducted multiple times to maintain the timeliness of the information. Evaluation of the proposed methodology using the UNSW-NB15 dataset, in conjunction with NF-UQ-NIDS-v2 and CICIDS2017 datasets, demonstrated its efficacy in anomaly detection, with performance exceeding a 96.75% accuracy rate. [ABSTRACT FROM AUTHOR]

Currently, the Internet of Thing has become an integral part of the world's Internet infrastructure. One of the important matters in this field is the security of the network. Some networks like Software-defined Networking are proposed to improve it. In this paper, cyber-attacks have been simulated and various parameters such as the average rate of receiving traffic, the average response time and network delay have been analyzed. In the following, a new plan for switch buffers and their effect on the state of CPU performance, the controller bandwidth and the amount of packet loss have been discussed. The new buffer structure is proposed using a hash table, which uses a DRAM combination structure. To implement the proposed technique, AS5710-54X-EC switch and floodlight controller were used, and also Eclipse Neon 3.1 was used for writing modules. The results imply that this method had a great impact on detecting attacks in SDN-based IoT frameworks. [ABSTRACT FROM AUTHOR]

Digital twins and the Internet of Things (IoT) have gained significant research attention in recent years due to their potential advantages in various domains, and vehicular ad hoc networks (VANETs) are one such application. VANETs can provide a wide range of services for passengers and drivers, including safety, convenience, and information. The dynamic nature of these environments poses several challenges, including intermittent connectivity, quality of service (QoS), and heterogeneous applications. Combining intelligent technologies and software-defined networking (SDN) with VANETs (termed intelligent software-defined vehicular networks (iSDVNs)) meets these challenges. In this context, several types of research have been published, and we summarize their benefits and limitations. We also aim to survey stochastic modeling and performance analysis for iSDVNs and the uses of machine-learning algorithms through digital twin networks (DTNs), which are also part of iSDVNs. We first present a taxonomy of SDVN architectures based on their modes of operation. Next, we survey and classify the state-of-the-art iSDVN routing protocols, stochastic computations, and resource allocations. The evolution of SDN causes its complexity to increase, posing a significant challenge to efficient network management. Digital twins offer a promising solution to address these challenges. This paper explores the relationship between digital twins and SDN and also proposes a novel approach to improve network management in SDN environments by increasing digital twin capabilities. We analyze the pitfalls of these state-of-the-art iSDVN protocols and compare them using tables. Finally, we summarize several challenges faced by current iSDVNs and possible future directions to make iSDVNs autonomous. [ABSTRACT FROM AUTHOR]

This research focuses on the realization of rapid reconfiguration in a cloud manufacturing environment to enable flexible resource scheduling, fulfill the resource potential and respond to various changes. Therefore, this paper first proposes a new cloud and software-defined networking (SDN)-based manufacturing model named software-defined cloud manufacturing (SDCM), which transfers the control logic from automation hard resources to the software. This shift is of significance because the software can function as the “brain” of the manufacturing system and can be easily changed or updated to support fast system reconfiguration, operation, and evolution. Subsequently, edge computing is introduced to complement the cloud with computation and storage capabilities near the end things. Another key issue is to manage the critical network congestion caused by the transmission of a large amount of Internet of Things (IoT) data with different quality of service (QoS) values such as latency. Based on the virtualization and flexible networking ability of the SDCM, we formalize the time-sensitive data traffic control problem of a set of complex manufacturing tasks, considering subtask allocation and data routing path selection. To solve this optimization problem, an approach integrating the genetic algorithm (GA), Dijkstra’s shortest path algorithm, and a queuing algorithm is proposed. Results of experiments show that the proposed method can efficiently prevent network congestion and reduce the total communication latency in the SDCM.

Group management is practiced to deploy access control and to ease multicast and broadcast communication. However, the devices that constitute the Internet of Things (IoT) are resource-constrained, and the network of IoT is heterogeneous with variable topologies interconnected. Hence, to tackle heterogeneity, SDN-aided centralized group management as a service framework is proposed to provide a global network perspective and administration. Group management as a service includes a group key management function, which can be either centralized or decentralized. Decentralized approaches use complex cryptographic primitives, making centralized techniques the optimal option for the IoT ecosystem. It is also necessary to use a safe, scalable approach that addresses dynamic membership changes with minimal overhead to provide a centralized group key management service. A group key management strategy called a one-way Function Tree (OFT) was put forth to lower communication costs in sizable dynamic groups. The technique, however, is vulnerable to collusion attacks in which an appending and withdrawing device colludes and conspires to obtain unauthorized keys for an unauthorized timeline. Several collusion-deprived improvements to the OFT method are suggested; however, they come at an increased cost for both communication and computation. The Modified One-Way Function Tree (MOFT), a novel technique, is suggested in this proposed work. The collusion resistance of the proposed MOFT system was demonstrated via security analysis. According to performance studies, MOFT lowers communication costs when compared to the original OFT scheme. In comparison to the OFT’s collusion-deprived upgrades, the computation cost is smaller.

Cloud services are now well established. Thanks to specific providers’ pioneering work, they offer on-site the benefit of predictability, continuity, and quality of service provided by virtualization technologies. In this context, SDN (Software Defined Networking) aims at providing tenant management of the transmission and various abstractions of the network infrastructure underlying the applications. Cloud platforms can also support virtualized network functions to complement the execution of online (web servers) or batch (compute or data-intensive) tasks. Scheduling and placing network functions into the cloud is a daunting task. One reason is that it requires time-consuming provisioning and configuration steps. This paper presents a generic framework that schedules network service function chains considering their internal dependencies. Toward this goal, our solution considers network functions’ placement, not their configuration. We are confronted with the general problem of defining the ordered sequence of service functions to be performed in a way that retains some criteria. Our framework considers dependencies within a service function chain but not between chains. We also perform experiments to highlight the benefits and properties of modeling work. The proposed generic framework can be instantiated with multiple multi-criteria decision supports and other techniques for placing final network functions. We conduct intensive experiments to find the best combination of strategies until the computing system exceeds 850 cores. Lessons learned are finally presented at the end of the paper. [ABSTRACT FROM AUTHOR]