Performance Evaluation of SDN based Virtualization for Data Center Networks

Vora, Jayneel; Kaneriya, Shriya; Tanwar, Sudeep; Tyagi, Sudhanshu

doi:10.1109/iot-siu.2018.8519846

Cited by 11 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results show that CPU usage increases with the number of Open vSwitches connected and that the total number of devices is not the only criterion relating to the scalability of an SDN solution design. We have also analyzed the recent results presented in the literature, but most of them used Mininet and not real or virtualize IoT devices like in previous studies . Mininet uses container solution to virtualize hosts, and the controller is embedded.…”

Section: Resultsmentioning

confidence: 99%

An SDN approach to route massive data flows of sensor networks

Flauzac

Santamaria

Nolot

et al. 2020

Int J Communication

View full text Add to dashboard Cite

With the advent of the Internet of Things (IoT), more and more devices can establish a connection with local area networks and use routing protocols to forward all information to the sink. But these devices may not have enough resources to execute a complex routing protocol or to memorize all information about the network. With proactive routing protocols, each node calculates the best path, and it needs enough resources to memorize the network topology.With reactive routing protocols, each node has to broadcast the message to learn the right path that the packets must follow. In all cases, in large networks such as IoT, this is not an appropriate mechanism. This paper presents a new software-defined network (SDN)-based network architecture to optimize the resource consumption of each IoT object while securing the exchange of messages between the embedded devices. In this architecture, the controller is in charge of all decisions, and objects only exchange messages and forward packets among themselves. In the case of large networks, the network is organized into clusters. Our proposed network architectures are tested with 1000 things grouped in five clusters and managed by one SDN controller. The tests using OpenDayLight and IoT embedded applications have been implemented on several scenarios providing the ability and the scalability from dynamic reorganization of the end-devices. This approach explores the network performance issues using a virtualized SDN-clustered environment which contributes to a new model for future network architectures. KEYWORDScomputer network management, distributed computing, Internet of Things, network topology, software-defined networking, wireless sensor networks INTRODUCTIONWith the Internet of Things (IoT), we have more and more devices connected to our local area network. Many of these things are only sensor devices to control humidity or the temperature of a room or to measure atmospheric pressure to predict the weather. Each of these devices is connected to the local area network of an enterprise or on the metropolitan network of a town. Sometimes, these things involve remote control as with thermostats or exchange of information between themselves as with smoke detection systems. Our goal with each thing is not only to route information on a network but also to execute orders of some kind. With the new paradigm of software-defined networking (SDN), 1,2 being one of the major research subjects obtaining support from a large number of major industries, we can decouple the control Int J Commun Syst. 2020;33:e4309.wileyonlinelibrary.com/journal/dac

show abstract

Section: Resultsmentioning

confidence: 99%

An SDN approach to route massive data flows of sensor networks

Flauzac

Santamaria

Nolot

et al. 2020

Int J Communication

View full text Add to dashboard Cite

show abstract

“…It allows the controller to communicate with the network devices, such as switches and routers. 24 These interfaces configure network policies and traffic forwarding rules and collect data from the network devices, such as traffic statistics and network topology. The southbound API is responsible for implementing the Open-Flow protocol, SDN's most commonly used protocol.…”

Section: Software Defined Networkmentioning

confidence: 99%

“…The southbound API is the SDN controller's set of interfaces for southbound communication. It allows the controller to communicate with the network devices, such as switches and routers 24 . These interfaces configure network policies and traffic forwarding rules and collect data from the network devices, such as traffic statistics and network topology.…”

Section: Introductionmentioning

confidence: 99%

Unleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

Dhadhania,

Bhatia,

Mehta

et al. 2023

Security and Privacy

Self Cite

View full text Add to dashboard Cite

Modern computer networks' increasing complexity and scale need serious attention towards network anomaly detection. Software‐defined networking (SDN) and graph neural networks (GNN) have emerged as promising approaches for anomaly detection due to their ability to capture dynamic network behavior and learn complex patterns from large‐scale network data. The amalgamation of SDN and GNN for network anomaly detection presents promising opportunities for improving the accuracy and efficiency of network anomaly detection. This paper focuses on various trends, issues, and challenges by integrating GNN on the top of SDN for network anomaly detection. The article highlights the advantages of using SDN for providing fine‐grained control and programmability in network monitoring. At the same time, GNN can model network behavior as a graph and learn representations from graph‐structured data. The authors also discuss the limitations of traditional anomaly detection methods in SDN, such as rule‐based approaches, and the potential of GNN to overcome these limitations by leveraging their ability to capture non‐linear and dynamic patterns in network data. This paper also presents a case study of DoS attack detection using SDN. The result shows that SDN based approach helps to detect attacks with an accuracy of 97% with future research directions.

show abstract

“…• Crash: This fault can occur due to hardware and software errors in the system [43]. However, the consensus mechanism should be robust enough to handle and repair crashed nodes independently without affecting the operations of other nodes.…”

Section: Introductionmentioning

confidence: 99%

A Survey on Decentralized Consensus Mechanisms for Cyber Physical Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Modern industry 4.0 applications are shifting towards decentralized automation of computing and cyber-physical systems (CPS), which necessitates building a robust, secure, and efficient system that performs complex interactions with other physical processes. To handle complex interactions in CPS, trust and consensus among various stakeholders is a prime concern. In a similar direction, consensus algorithms in blockchain have evolved over the years that focus on building smart, robust, and secure CPS. Thus, it is imperative to understand the key components, functional characteristics, and architecture of different consensus algorithms used in CPS. Many consensus algorithms exist in the literature with a specified set of functionalities, performance, and computing services. Motivated from these facts, in this survey, we present a comprehensive analysis of existing state-of-the-art consensus mechanisms and highlight their strength and weaknesses in decentralized CPS applications. In the first part, we present the scope of the proposed survey and identify gaps in the existing surveys. Secondly, we present the review method and objectives of the proposed survey based on research questions that address the gaps in existing studies. Then, we present a solution taxonomy of decentralized consensus mechanisms for various CPS applications. Then, open issues and challenges are also discussed in deploying various consensus mechanisms in the CPS with their merits and demerits. The proposed survey will act as a road-map for blockchain developers and researchers to evaluate and design future consensus mechanisms, which helps to build an efficient CPS for industry 4.0 stakeholders.

show abstract

Performance Evaluation of SDN based Virtualization for Data Center Networks

Cited by 11 publications

References 8 publications

An SDN approach to route massive data flows of sensor networks

An SDN approach to route massive data flows of sensor networks

Unleashing the power of SDN and GNN for network anomaly detection: State‐of‐the‐art, challenges, and future directions

A Survey on Decentralized Consensus Mechanisms for Cyber Physical Systems

Contact Info

Product

Resources

About