Software-Defined Networking (SDN) is a new type of technology that embraces high flexibility and adaptability. The applications in SDN have the ability to manage and control networks while ensuring load balancing, access control, and routing. These are considered the most significant benefits of SDN. However, SDN can be influenced by several types of conflicting flows which may lead to deterioration in network performance in terms of efficiency and optimisation. Besides, SDN conflicts occur due to the impact and adjustment of certain features such as priority and action. Moreover, applying machine learning algorithms in the identification and classification of conflicting flows has limitations. As a result, this paper presents several machine learning algorithms that include Decision Tree (DT), Support Vector Machine (SVM), Extremely Fast Decision Tree (EFDT) and Hybrid (DT-SVM) for detecting and classifying conflicting flows in SDNs. The EFDT and hybrid DT-SVM algorithms were designed and deployed based on DT and SVM algorithms to achieve improved performance. Using a range flows from 1000 to 100000 with an increment of 10000 flows per step in two network topologies namely, Fat Tree and Simple Tree Topologies, that were created using the Mininet simulator and connected to the Ryu controller, the performance of the proposed algorithms was evaluated for efficiency and effectiveness across a variety of evaluation metrics. The experimental results of the detection of conflict flows show that the DT and SVM algorithms achieve accuracies of 99.27% and 98.53% respectively while the EFDT and hybrid DT-SVM algorithms achieve respective accuracies of 99.49% and 99.27%. In addition, the proposed EFDT algorithm achieves 95.73% accuracy on the task of classification between conflict flow types. The proposed EFDT and hybrid DT-SVM algorithms show a high capability of SDN applications to offer fast detection and classification of conflict flows.
Software Defined Networking (SDN) is an emerging networking paradigm that provides more flexibility and adaptability in terms of network definition and control. However, SDN is a logically centralized technology. Therefor the control plane (i.e. controller) scalability in SDN in particular, is also one of the problems that needs further focus. OpenFlow is one of the protocol standards in SDN, which allow the separation of the controller from the forwarding plane. The control plane has an SDN embedded firewall and is able to enforce and monitor the network activity. This firewall can be used to control the throughput. However, it may affect SDN performance. In this paper, throughput will be used as a performance metric to evaluate and assess the firewall impact on two protocols; Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) that passes through the forwarding planes. The evaluations have been verified through simulating the SDN OpenFlow network using MININET. The results show that an implementation of firewall module in SDN creates a significant 36% average drop for TCP and 87% average drop for UDP in the bandwidth which eventually affect the quality of the network and applications.
Ahigh-speedrailway (HSR) has gained very high popularity for passengersdue to the fast, reliable, economical and convenient during traveling a verylong-distance journey. Thedemandfor advancedbroadbandservices such aswatching4K movies, cloud computing andonline gaming, has exponentiallyincreased fortravelerson thehigh-speedtrain(HST).The HSTcan’t providegood bandwidth to facilitate these services for travelers via existingtechnologies such as cellular networksand satellite networks because offrequent handoffs, high penetration and fading.So, the bandwidth degradesdramatically due to these issues. Research workers have developed proposalsto handle these problems by advanced transmission technologies for HSR.Until now,varioustransmissionschemeshave beensuggestedby researchworks with thefocusfor either high bandwidth or signal qualityimprovement. This paper presents a survey on advanced transmissiontechnologies for high bandwidth and good signal quality. In this paper, acomprehensive survey of the appropriate literature published that concentrateon advanced transmission methods in HSR communications in getting higherbandwidth efficiency and maximize the signal quality is presented. Advancedtransmission method can be categorized into orthogonal frequencydivisionmultiplexing (OFDM), multiple-input multiple-output (MIMO) and radio-over-fiber (RoF).
Internet of Vehicles (IoV) is developed by integrating the intelligent transportation system (ITS) and the Internet of Things (IoT). The goal of IoV is to allow vehicles to communicate with other vehicles, humans, pedestrians, roadside units, and other infrastructures. Two potential technologies of V2X communication are dedicated short-range communication (DSRC) and cellular network technologies. Each of these has its benefits and limitations. DSRC has low latency but it limits coverage area and lacks spectrum availability. Whereas 4G LTE offers high bandwidth, wider cell coverage range, but the drawback is its high transmission time intervals. 5G offers enormous benefits to the present wireless communication technology by providing higher data rates and very low latencies for transmissions but is prone to blockages because of its inability to penetrate through the objects. Hence, considering the above issues, single technology will not fully accommodate the V2X requirements which subsequently jeopardize the effectiveness of safety applications. Therefore, for efficient V2X communication, it is required to interwork with DSRC and cellular network technologies. One open research challenge that has gained the attention of the research community over the past few years is the appropriate selection of networks for handover in a heterogeneous IoV environment. Existing solutions have addressed the issues related to handover and network selection but they have failed to address the need for handover while selecting the network. Previous studies have only mentioned that the network is being selected directly for handover or it was connected to the available radio access. Due to this, the occurrence of handover had to take place frequently. Hence, in this research, the integration of DSRC, LTE, and mmWave 5G is incorporated with handover decision, network selection, and routing algorithms. The handover decision is to ensure whether there is a need for vertical handover by using a dynamic Q-learning algorithm. Then, the network selection is based on a fuzzy-convolution neural network that creates fuzzy rules from signal strength, distance, vehicle density, data type, and line of sight. V2V chain routing is proposed to select V2V pairs using a jellyfish optimization algorithm that takes into account the channel, vehicle characteristics, and transmission metrics. This system is developed in an OMNeT++ simulator and the performances are evaluated in terms of mean handover, handover failure, mean throughput, delay, and packet loss.
Conventional networking devices require that each is programmed with different rules to perform specific collective tasks. Next generation networks are required to be elastic, scalable and secured to connect millions of heterogeneous devices. Software defined networking (SDN) is an emerging network architecture that separates control from forwarding devices. This decoupling allows centralized network control to be done network-wide. This paper analyzes the latency and jitter of SDN against a conventional network. Through simulation, it is shown that SDN has an average three times lower jitter and latency per packet that translate to improved throughput under varying traffic conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.