![]() A network classifier identifies the type of application following some fields of header packets and patterns. It needs to be dynamic, scalable, and requires less human interaction. A well-designed network classifier (NC) is the key to implement effective management of network resources. To meet the steady demand of high transmission rates of internet, Network administrators need to design and configure a specific class of service (CoS) to offer better QoS. However, SDN over the Docker platform implores attention for improvement and refinement. In this paper, we have addressed the issue and proposed a way to support different complex topologies for Docker-based virtual network. By default, Docker containers can be interconnected in a linear-bus topology complex topologies are not natively well supported and managed. They, as an open source platform, receive support from developers all around the world. Docker containers not only maximise the use of physical hardware, sharing of computing power, storage, and memory capacity but also facilitate communication and data sharing between cloud applications. #PARA QUE SERVE O APP NETWORKVIEW PORTABLE#Docker containers introduce a new way to deploy network applications into a portable image that runs anywhere and can be saved enhancing the user’s experience. They prefer maximising physical hardware by sharing computing power, storage, and memory capacity. Network administrators avoid investing in hardware resources, unless strictly necessary. In this paper, we address this issue and propose a new Docker container-based virtual network. Although Mininet emulator is widely used for working with OpenFlow (Open Virtual Switch, n.d.) virtual switches (OVS), it carries certain limitations in customising switches and adding applications to hosts. To build SDN networks, researchers have focused their studies on existing SDN-supported NFV (Tseng et al., 2019) and emulators such as Mininet ( n.d.), OFNet ( n.d.), and Estinet ( n.d.). Compared to traditional networks, SDN is easier to deploy, facilitates the implementation of network services, and offers scalable management within the networking infrastructure. It separates the control plane from the data plane, offering a global view of the network. SDN has attracted interest in networking by introducing the logical centralisation of control. It is dynamically manageable, and ideal for high-bandwidth applications (David, 2020). Software-defined network (SDN) is an emerging architecture that promises better performance and low latency. New online games, video streaming, and other services have encouraged Internet service providers to optimise and adapt their network architectures to new technologies for offering better security, availability, quality of experience (QoE), and reliability to potential customers. In recent years, with the rapid growth of mobile communications, social networks, and new technologies, data traffic has exponentially increased (Cisco Visual Networking Index, 2018). This study will certainly serve to further research on optimising SDN and QoS. Based on the evaluations, an improvement in latency performance has been demonstrated, where analysing a packet, controller processing time takes on an average of 10 µs. Finally, we propose a new controller algorithm for Ryu platforms, which integrates the DNC and classifies both TCP and UDP flows in real-time. We then propose a dynamic network classifier (DNC) generated from PAA over a novel Docker-based SDN network. Additionally, we present a new performance accelerator algorithm (PAA), which incorporates these three ML classifiers and accelerates the overall performance significantly. In this paper, using three ML techniques, we first classify network flows with 3, 5, and 7 parameters giving up to 97.14% accuracy. ML offers good performance to real-time traffic solutions without depending on well-known TCP or UDP port numbers, IP addresses, or encrypted payloads. This paper focuses on the implementation of a network traffic classifier using a novel Docker-based SDN network. Software-defined networking (SDN) with machine learning (ML) has become an emerging solution for network scheduling, quality of service (QoS), resource allocations, and security. With the rapid technological growth in the last decades, the number of devices and users has drastically increased. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |