Ethernet Devices Research Articles

Load Balancing between Paths using Software Defined Networks

Small networks usually use Ethernet devices that apply solutions such as the Spanning Tree Protocol (STP) to forward packets through a single path with no loops. However, this prevents the use of idle links that may reduce congestion and augment the aggregate bandwidth of the network. This work proposes a load balancing mechanism between paths using Software Defined Networks (SDNs). The proposed mechanism, named MLB (Multipath Load Balance), computes multiple paths with disjoint links that have the smallest number of hops between source and destination. Moreover, MLB has a “switching control” function that verifies whether the current occupation of the path exceeds a percentage of its capacity and if the potential new path computed by MLB has an occupation at least a percentage value smaller than that of the current path. MLB is implemented in Python and evaluated in Mininet. The results show that it is possible to increase the aggregate bandwidth by 95% and decrease the packet loss by about 95.5% compared with the standard operating mode of the OpenDaylight SDN controller.

A Migration Strategy for Profinet Toward Ethernet TSN-Based Field-Level Communication: An Approach to Accelerate the Adoption of Converged IT/OT Communication

The next era of industrial communication is said to be based on Ethernet time-sensitive networking (TSN). Current migration strategies enable a communication of existing industrial Ethernet (IE) devices over Ethernet TSN networks. Isochronous communication based on scheduled traffic and a free topology choice are mostly not possible for these devices. This work approaches an improved migration strategy that includes a new bridge mode called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">time-aware forwarding</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TAF</i> ) that is compatible with Ethernet TSN and that can be implemented with existing Profinet hardware. It enables scheduled traffic and a free topology choice for existing devices at the same time.

A Scalable, High-Performance, and Fault-Tolerant Network Architecture for Distributed Machine Learning

In large-scale distributed machine learning (DML), the network performance between machines significantly impacts the speed of iterative training. In this paper we propose BML, a scalable, high-performance and fault-tolerant DML network architecture on top of Ethernet and commodity devices. BML builds on BCube topology, and runs a fully-distributed gradient synchronization algorithm. Compared to a Fat-Tree network with the same size, a BML network is expected to take much less time for gradient synchronization, for both low theoretical synchronization time and its benefit to RDMA transport. With server/link failures, the performance of BML degrades in a graceful way. Experiments of MNIST and VGG-19 benchmarks on a testbed with 9 dual-GPU servers show that, BML reduces the job completion time of DML training by up to 56.4% compared with Fat-Tree running state-of-the-art gradient synchronization algorithm.

A Novel Algorithm for Loop Prevention and Fast Recovery (LPFR) in Ethernet Rings.

Traditional Ethernet networks use the rapid spanning tree protocol (RSTP) or the enhanced RSTP (eRSTP) to ensure a loop-free topology and provide redundant links as backup paths in case an active link has failed. However, when a failure occurs, the RSTP/eRSTP require a significant amount of reconfiguration time in order to find an alternative path. The RSTP/eRSTP are also limited by the number of nodes in a ring network, and their performance degrade when the number of nodes increases; the media redundancy protocol (MRP), which is used in industrial networks, has the same issues. In this paper, we introduce a new algorithm, called loop prevention and fast recovery (LPFR), which can be applied to Ethernet ring networks to provide a loop-free topology. When a failure occurs, LPFR requires only a very short amount of time to switch to an alternative path. LPFR needs a maximum of 6.1 ms for recovery time, versus ＜ 100 ms for the RSTP/eRSTP in a ring size of 20 nodes and ＜ 200 ms for the MRP in a ring size of 50 nodes. The LPFR offers a reduction in recovery time of up to 93.9 % compared to the RSTP/eRSTP, and 96.9 % compared to the MRP. However, in most cases, LPFR requires zero recovery time for such switching. In addition, in most situations, no frames are lost when a node switches to an alternative path. Unlike the RSTP/eRSTP and MRP, LPFR provides a better way for distributing the sent traffic among network links, which in turn improves network performance, reduces the probability of bottleneck occurrences, and reduces the frame latency between the source and the destination. This is because LPFR always sends the frame through the fastest path. The LPFR algorithm can run on a wide variety of ring sizes, which is not the case for the RSTP/eRSTP and MRP. Finally, the LPFR will use the Ethernet standard frame layout without any modifications or changes. This will allow all of the standard Ethernet devices and networks to be directly integrated into the LPFR networks without any proxies.

Instance Vehicle Monitoring and Tracking with Internet of Things Using Arduino

Abstract The Vehicle Tracking System has the capability of finding the Vehicle location, Gas Leakages, Vehicle Speed, and Vehicle Accident and at the same time notifies the owners of the vehicle through a GSM network with an SMS alert message. The drivers require their presence to their family or to their respective one’s. The main aim is to design a low cost and an efficient vehicle tracking and vehicle security circuit based on an Arduino microcontroller. This system can be made as a backup sector inside the vehicles to prevent them from stolen and easy to identify the location and prevent from other disaster factors. The main methodology of the device is to monitoring the vehicle speed via Ethernet shield through Internet of things. The protective system is maintained by analysing gas tank through gas sensor which details about the gas leakage. The advantages of this device are alarming the driver when there is any gas leakage in the vehicle and also informs about the speed of the car. A vibrating sensor is used to alert when the vehicle is struck with some accident by sending SMS to the required people via GSM Modem and all the data which can be viewed by the driver can be viewed by the people in home via Ethernet device.

FPGA Design for Multiline Acquisition and Ethernet Interface in High-Frame-Rate Ultrasound Machines

ABSTRACTThe study presents the design of a 32-channel field-programmable gate arrays (FPGA) for ultrasound instruments working at high frame rates of the order of 1000 fps. The FPGA does multiline acquisition and Ethernet framing of the received data stream from the analog-to-digital converters (ADCs). The study also presents implementation of innovative methods of moving window algorithm, critical window capture, and envelope detection in the FPGA, for data rate reduction to aid video processing in laptops. The FPGA has serial peripheral interfacing bus interface towards microcontroller. FPGA also has data interface towards ADCs and Gigabit Ethernet MAC device. The microcontroller has in-line management interface with Gigabit Ethernet MAC through the FPGA. The FPGA dataflow consists of received signal processing of captured ultrasound data from ADCs, temporary storage in FPGA, and forwarding to external Ethernet devices after Ethernet framing. All the functional blocks are integrated and synchronized with an external clock. Internal clock and control signal generation modules generate the requisite timing clocks. The FPGA design has been realized in prototype hardware. The prototype hardware has microcontroller-based control from a MATLAB-based graphical user interface for device configurations and image processing. The captured packets as well as the acquired image results are shown. The design is modular, flexible, have large-scale integration, cost-effective, and can be easily replicated.

Lark: An effective approach for software-defined networking in high throughput computing clusters

High throughput computing (HTC) systems are widely adopted in scientific discovery and engineering research. They are responsible for scheduling submitted batch jobs to utilize the cluster resources. Current systems mostly focus on managing computing resources like CPU and memory; however, they lack flexible and fine-grained management mechanisms for network resources. This has increasingly been an urgent need as current batch systems may be distributed among dozens of sites around the globe like Open Science Grid. The Lark project was motivated by this need to re-examine how the HTC layer interacts with the network layer.In this paper, we present the system architecture of Lark and its implementation as a plugin of HTCondor which is a popular HTC software project. Lark achieves lightweight network virtualization at per-job granularity for HTCondor by utilizing Linux container and virtual Ethernet devices; this provides each batch job with a unique network address in a private network namespace. We extended HTCondor’s description language, ClassAds, so users can specify networking requirements in the job submission script. HTCondor can perform matchmaking to make sure user-specified network requirements and resource-specific policies are fulfilled. We also extended the job agent, condor_starter, so that it can manage and configure the job’s network environment. Given this important building block as the core, we implement bandwidth management functionality at both the host and network levels utilizing software-defined networking (SDN). In addition to HTCondor, Wide area network bandwidth management for GridFTP traffic is designed and implemented. Our experiments and evaluations show that Lark can effectively manage network resources simultaneously for both applications inside the cluster environment. By not resorting to heavyweight VMs, we keep startup overheads minimal compared to “regular” batch jobs. This mechanism provides the users with better predictability of their job execution and the administrators more policy flexibility in allocation of network resources.

SPIDR: a read-out system for Medipix3 & Timepix3

The realisation of the Timepix3 chip opened the way for new opportunities in research areas such as particle tracking with both semiconductor sensors and gas filled time projection chambers, electron microscopy and imaging mass spectrometry. To exploit the full capability of the Timepix3 chip, Nikhef developed a compact read-out system, called SPIDR that can deal with the high data output of 80 Mhits per chip per second. The main read-out board connects to both 10 Gb Ethernet and 1 Gb Ethernet devices. The latter obviously at a reduced rate. The main board connects to individual chip-carrier boards via a standard FMC connector. The system is designed such that support for other readout chips is foreseen via reprogramming of the FPGA. Besides the Timepix3 chip also the Medipix3 chip is currently supported. Both the main board and the chip carrier boards are cooled, via the housing and a fan to obtain a stable temperature of around 40 ± 0.2 °C for the Timepix3 chips. We will present the system and the results obtained with the LHCb beam telescope at CERN and proton radiography data obtained with a time projection chamber based on GEM technology.

Formal timing analysis of CAN-to-Ethernet gateway strategies in automotive networks

Due to increased bandwidth and scalability demands, Ethernet technology is finding its way into recent in-vehicle networks. Tomorrow's heterogeneous networks will feature legacy buses [e.g. controller area network (CAN) or FlexRay] as well as high-speed Ethernet devices, connected by switches and gateways. As Ethernet offers significantly larger frame sizes than CAN, the efficient transmission of CAN data over an Ethernet backbone depends heavily on the way this data is multiplexed into Ethernet frames. This article focuses on the timing impact introduced by various CAN/Ethernet multiplexing strategies at the gateways. We present a formal analysis method to derive upper bounds on end-to-end latencies for complex multiplexing strategies, which is key for the design of safety-critical real-time systems. We capture complex inter-domain signal paths spanning multiple buses, gateways, and switches and show the applicability in a realistic automotive setup.

PoE(Power Over Ethernet)에서 임펄스성 서지보호 이중화 장치 설계

PoE(Power Over Ethernet)에서 임펄스성 서지보호 이중화 장치 설계

Desempeño de redes inalámbricas y redes industriales inalámbricas en procesos de control en tiempo real bajo ambientes industriales

El uso creciente de las redes Ethernet en el piso de la pirámide de automatización ha hecho que muchas compañías desarrollen dispositivos para operar bajo los requerimientos característicos de este nivel, en la actualidad denominada red Industrial Ethernet, a nivel industrial se encuentra en el mercado variedad de sensores y actuadores que incorporan esta tecnología, muchos de estos equipos se venden a muy alto costo, por eso en este artículo se evaluó el desempeño de dos redes inalámbricas, una con dispositivos del Ethernet convencional, y otra con dispositivos de industrial Ethernet variando cuatro parámetros que son: distancia, número de bytes, relación señal a ruido y la tasa de error de paquetes, midiendo los retardos y comparando con métricas estadísticas los resultados, para ello se usaron graficas Box Plot. Al final, se concluye que bajo los parámetros y condiciones evaluados, las redes inalámbricas pueden servir como sistema de comunicación en aplicaciones de control con retardos permisibles de hasta 50 ms, además, los resultados demuestran un mejor desempeño de las redes industrial Ethernet con respecto a las convencionales, con diferencias en los RTT de milisegundos, por lo tanto, se recomienda establecer qué riesgo representa para el proceso a controlar estos retardos y así determinar si los equipos convencional aplican, ya que bajo ciertas características como condiciones de humedad y temperatura pueden operar adecuadamente durante un tiempo considerable y a un menor costo que los dispositivos de Industrial Ethernet.

A semantic enhanced Power Budget Calculator for distributed computing using IEEE 802.3az

Energy efficiency is becoming an important requirement in more and more computing systems for optimizing resource allocation and task scheduling. By switching active copper Ethernet links to a low power model the IEEE 802.3az protocol can reduce the network energy consumption when no traffic exists. However, the effect of 802.3az heavily depends on network traffic patterns, which makes its utilization challenging in scheduling computing tasks. In this research, we examined the 802.3az technology with the goal of deploying it in distributed computing systems such as clusters. We devised an energy budget calculator that includes the energy model of 802.3az compliant Ethernet devices and supports the resource management service. We show a few practical examples of how applications can better plan their execution by integrating this knowledge in their decision strategies. We also present a solution for enhancing the calculator by using a semantic energy information system.

Zero-footprint Ethernet transformers using circuit-board embedded ferrites

Ethernet transformers are mass produced broadband signal coupling transformers, used for interfacing copper twisted-pair networking cable to Ethernet devices. In this paper, we present a process for fabricating Ethernet transformers by embedding ferrite core materials within printed circuit board, and then fabricating the windings around the embedded core. Sample transformers were fabricated with different winding configurations and core materials. It is then possible to clad the board with copper and fabricate routes or mount components to the board faces, making the transformer a zero-footprint component. The sample transformer's performance is experimentally evaluated, and the results are presented in this paper. All transformers were found to successfully couple up to 1000Base-T Ethernet.

Mathematical analysis of burst transmission scheme for IEEE 802.3az energy efficient Ethernet

The IEEE P802.3az Energy Efficient Ethernet (EEE) protocol specifies a Low Power Idle (LPI) mode in which Ethernet device can save energy by turning off components when its queue is empty, and defines a scheme for coordinating the transitions between the LPI and active modes. Depending on when Ethernet devices enter and exit the LPI mode, two schemes have been proposed: the frame transmission scheme and the burst transmission scheme. P. Reviriego et al. proposed the burst transmission scheme (the same as the packet coalescing scheme by Christensen et al.) where the link becomes active when either a fixed number of packets have arrived or a fixed time is passed from the epoch that the first packet has arrived. They showed by simulation that the burst transmission scheme has significantly lower energy consumption than the frame transmission scheme of EEE. In this paper, we provide an analytic model of the burst transmission scheme and obtain its energy consumption and packet delay. Our analytic results match the simulation results. In numerical results, we find the maximal timer which minimizes the energy consumption while satisfying the maximal packet delay within a pre-determined level.

Enhancements of G3-PLC Technology for Smart-Home/Building Applications

To enable the smart grid concept, it is fundamental to consider the in-home/building context where, beside the conventional home networking services, home automation and smart energy management services have to be offered. In this paper, we consider the in-home/building scenario, for which we propose a convergent network architecture to enhance the performance of the narrowband power line communication (PLC) G3-PLC technology through its integration with an Ethernet-based network. To this end, we define the protocols characterizing the network modules, namely, switches and routers, which allow for integrating the G3-PLC with Ethernet devices. Since Ethernet represents a convergent standard for many communication devices, by adding this functionality to G3-PLC, interconnectivity with other heterogeneous nodes can be offered. Furthermore, since the G3-PLC medium access control layer is based on a carrier sense multiple access scheme, its performance decreases when the number of network nodes contending for the channel increases. Therefore, we evaluate the network performance when an optimized time division multiple access scheme is adopted. The proposed convergent network architecture has been implemented in the OMNeT++ network simulator.

Physical-Layer Identification of Wired Ethernet Devices

This work sets forth a systematic approach for the investigation and utilization of the signal characteristics of digital devices for use in a security context. A methodology, built upon an optimal detector, the matched filter, is proposed that allows for the reliable identification and tracking of wired Ethernet cards by use of their hardware signaling characteristics. The matched filter is found to be sensitive enough to differentiate between devices using only a single Ethernet frame; an adaptive thresholding strategy employing prediction intervals is used to cope with the stochastic nature of the signals. To demonstrate the validity of the methodology, and to determine which portions of the signal are useful for identification purposes, experiments were performed on three different models of 10/100 Ethernet cards, totaling 27 devices in all. In selecting the cards, an effort was made to maximize intramodel similarity and thus present a worst-case scenario. While the primary focus of the work is network-based authentication, forensic applications are also considered. By using data collected from the same devices at different times, it is shown that some models of cards can be reidentified even after a month has elapsed since they were last seen.

Opportunistic power saving algorithms for Ethernet devices

Network interfaces in most wired or wireless computing devices are greatly under-utilized, squandering energy while waiting for new packets to arrive. In this paper, we propose simple opportunistic algorithms to determine when to power down idle network interfaces in order to save much of that wasted energy. We also develop an analytic model to predict the amount of energy saved and the packet delay. The algorithms are compared to the best known opportunistic method, and it is shown that they provide significantly greater power savings without inflicting noticeable delays to Internet traffic.

Enforcing the timing behavior of real-time stations in legacy bus-based industrial Ethernet networks

This paper proposes a virtual token-passing mechanism, which allows the coexistence of legacy industrial Ethernet devices with enhanced (real-time) devices in the same bus network. The VTPE mechanism allows the implementation of real-time (RT) applications upon legacy bus-based industrial networks, enforcing the adequate timing behavior of the supported applications. It enables the traffic separation between legacy Ethernet stations and enhanced (RT) stations. A set of experiments has been performed, which allowed to measure the message access delay and the token rotation time. The achieved results clearly demonstrate that the VTPE architecture enables the support of RT communication upon legacy bus-based industrial Ethernet networks, even when the communication medium is shared with uncontrolled traffic sources.

406 イーサネットを用いたパラレル計測における計測時刻同時性の検討(GS5(2) 実験,計測,モニタリング)

406 イーサネットを用いたパラレル計測における計測時刻同時性の検討(GS5(2) 実験,計測,モニタリング)

Technology-oriented review and vision of 40-Gb/s-based optical transport networks

Research and development of 40-Gb/s-based technologies are very significant for not only increasing the total capacity of wavelength-division multiplexing transmission systems but also providing higher speed interfaces to routers and Ethernet devices in order to create new services in the twenty-first century. The technologies of digital and analog integrated circuits are progressing steadily, and the LiNbO/sub 3/ Mach-Zehnder external modulator has already reached the performance level required for practical use. Adaptive, intelligent compensation for problems such as chromatic dispersion and polarization-mode dispersion can make the design of optical transport networks more flexible. As an example, we achieved 3.5-Tb/s (43 Gb/s/spl times/88 ch) transmission over a 600-km nonzero dispersion-shifted fiber by using LiNbO/sub 3/ modulators and virtually imaged phased array variable-dispersion compensators.