scholarly journals Metron

2021 ◽  
Vol 38 (1-2) ◽  
pp. 1-45
Author(s):  
Georgios P. Katsikas ◽  
Tom Barbette ◽  
Dejan Kostić ◽  
JR. Gerald Q. Maguire ◽  
Rebecca Steinert
Keyword(s):  
Load Balancing ◽  
High Speed ◽  
State Of The Art ◽  
Single Server ◽  
Packet Processing ◽  
Commodity Hardware ◽  
Multiple Servers ◽  
Underlying Network ◽  
Network Functions

Deployment of 100Gigabit Ethernet (GbE) links challenges the packet processing limits of commodity hardware used for Network Functions Virtualization (NFV). Moreover, realizing chained network functions (i.e., service chains) necessitates the use of multiple CPU cores, or even multiple servers, to process packets from such high speed links. Our system Metron jointly exploits the underlying network and commodity servers’ resources: ( i ) to offload part of the packet processing logic to the network, ( ii )  by using smart tagging to setup and exploit the affinity of traffic classes, and ( iii )  by using tag-based hardware dispatching to carry out the remaining packet processing at the speed of the servers’ cores, with zero inter-core communication. Moreover, Metron transparently integrates, manages, and load balances proprietary “blackboxes” together with Metron service chains. Metron realizes stateful network functions at the speed of 100GbE network cards on a single server, while elastically and rapidly adapting to changing workload volumes. Our experiments demonstrate that Metron service chains can coexist with heterogeneous blackboxes, while still leveraging Metron’s accurate dispatching and load balancing. In summary, Metron has ( i )  2.75–8× better efficiency, up to ( ii )  4.7× lower latency, and ( iii )  7.8× higher throughput than OpenBox, a state-of-the-art NFV system.

scholarly journals High-speed network traffic capturing and processing tools

2021 ◽  
Vol 33 (4) ◽  
pp. 49-68
Author(s):  
Dmitry Victorovich Larin ◽  
Aleksandr Igorevich Getman
Keyword(s):  
Operating Systems ◽  
Network Traffic ◽  
High Speed ◽  
High Performance ◽  
Virtual Network ◽  
Packet Processing ◽  
Commodity Hardware ◽  
High Speed Network ◽  
Traffic Rate ◽  
Network Functions

Network stacks currently implemented in operating systems can no longer cope with the packet rates offered by 10 Gbit Ethernet. Thus, frameworks were developed claiming to offer a faster alternative for this demand. These frameworks enable arbitrary packet processing systems to be built from commodity hardware handling a traffic rate of several 10 Gbit interfaces, entering a domain previously only available to custom-built hardware. In this paper, we survey various frameworks for high-performance packet IO and their interaction with a modular frameworks and specialized virtual network functions software for high-speed packet processing. We introduce a model to estimate and assess the performance of these packet processing frameworks. Moreover, we analyze the performance of the most prominent frameworks based on representative measurements in packet capturing scenarios. Therefore, we provide a comparison between them and select the area of applicability.

scholarly journals Intelligent Load Balancing Techniques in Software Defined Networks: A Survey

Electronics ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 1091 ◽  
Author(s):  
Thabo Semong ◽  
Thabiso Maupong ◽  
Stephen Anokye ◽  
Kefalotse Kehulakae ◽  
Setso Dimakatso ◽  
...  
Keyword(s):  
Load Balancing ◽  
Performance Metrics ◽  
Denial Of Service ◽  
Internet Traffic ◽  
Future Research ◽  
Single Server ◽  
Multiple Servers ◽  
Future Research Directions ◽  
Load Balancer ◽  
Multiple Clients

In the current technology driven era, the use of devices that connect to the internet has increased significantly. Consequently, there has been a significant increase in internet traffic. Some of the challenges that arise from the increased traffic include, but are not limited to, multiple clients on a single server (which can result in denial of service (DoS)), difficulty in network scalability, and poor service availability. One of the solutions proposed in literature, to mitigate these, is the use of multiple servers with a load balancer. Despite their common use, load balancers, have shown to have some disadvantages, like being vendor specific and non-programmable. To address these disadvantages and improve internet traffic, there has been a paradigm shift which resulted in the introduction of software defined networking (SDN). SDN allows for load balancers that are programmable and provides the flexibility for one to design and implement own load balancing strategies. In this survey, we highlight the key elements of SDN and OpenFlow technology and their effect on load balancing. We provide an overview of the various load balancing schemes in SDN. The overview is based on research challenges, existing solutions, and we give possible future research directions. A summary of emulators/mathematical tools commonly used in the design of intelligent load balancing SDN algorithms is provided. Finally, we outline the performance metrics used to evaluate the algorithms.

High-speed data plane and network functions virtualization by vectorizing packet processing

2019 ◽  
Vol 149 ◽  
pp. 187-199 ◽  
Author(s):  
Leonardo Linguaglossa ◽  
Dario Rossi ◽  
Salvatore Pontarelli ◽  
Dave Barach ◽  
Damjan Marjon ◽  
...  
Keyword(s):  
High Speed ◽  
Packet Processing ◽  
Data Plane ◽  
High Speed Data ◽  
Network Functions

scholarly journals An Investigation of Using Traffic Load in SDN Based Load Balancing

2020 ◽  
pp. 65-74
Keyword(s):  
Load Balancing ◽  
Network Performance ◽  
Traffic Load ◽  
System Throughput ◽  
The Internet ◽  
Single Server ◽  
Multiple Servers ◽  
Load Balancer ◽  
The Internet Of Things ◽  
Sdn Controller

The number of devices connected to networks and the internet such as the Internet of Things, machine to machine, social media or speech traffic, etc., are rapidly increased that results in a huge amount of traffic. This leads to congestion that increases packet loss and reduces system performance. Therefore, a single server cannot handle this traffic and need to use some approaches to optimize network performance. The use of a load balancer to distribute network traffic among multiple servers could minimize the load on a single server, provide availability, scalability, and enhance network performance. A load balancer in a traditional network is a dedicated hardware device that is expensive, close vender, and non-programmable. A load balancer contains few algorithms that network engineers cannot change or create a new one. In contrast, Software Defined Network (SDN) that utilizes load balancer is programmable (hardware independent) and more agilely. The objective of this investigation is to implement the Least packet load algorithm, which is used in the traditional load balancer, using an SDN-controller Python Network Operating system (POX) in order to distribute load among servers. Moreover, it discusses some research opportunities that this work introduces to improve load balancing in SDN. This work is validated through extensive simulations and emulations that compare the proposed algorithm with four of the most widely cited schemes. The results indicate that the proposed algorithm improved network performance and achieve up to 21% increase to system throughput compared to other benchmark approaches.

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

scholarly journals Neuro-Inspired Computing with Spin-VCSELs

2021 ◽  
Vol 11 (9) ◽  
pp. 4232
Author(s):  
Krishan Harkhoe ◽  
Guy Verschaffelt ◽  
Guy Van der Sande
Keyword(s):  
Processing Speed ◽  
Delay Time ◽  
High Speed ◽  
State Of The Art ◽  
Polarization Modulation ◽  
Time Interval ◽  
Computing Technique ◽  
High Modulation ◽  
Short Time ◽  
Modulation Speed

Delay-based reservoir computing (RC), a neuromorphic computing technique, has gathered lots of interest, as it promises compact and high-speed RC implementations. To further boost the computing speeds, we introduce and study an RC setup based on spin-VCSELs, thereby exploiting the high polarization modulation speed inherent to these lasers. Based on numerical simulations, we benchmarked this setup against state-of-the-art delay-based RC systems and its parameter space was analyzed for optimal performance. The high modulation speed enabled us to have more virtual nodes in a shorter time interval. However, we found that at these short time scales, the delay time and feedback rate heavily influence the nonlinear dynamics. Therefore, and contrary to other laser-based RC systems, the delay time has to be optimized in order to obtain good RC performances. We achieved state-of-the-art performances on a benchmark timeseries prediction task. This spin-VCSEL-based RC system shows a ten-fold improvement in processing speed, which can further be enhanced in a straightforward way by increasing the birefringence of the VCSEL chip.

scholarly journals Efficient Placement of Service Function Chains in Cloud Computing Environments

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 323
Author(s):  
Marwa A. Abdelaal ◽  
Gamal A. Ebrahim ◽  
Wagdy R. Anis
Keyword(s):  
Energy Consumption ◽  
Load Balancing ◽  
Response Time ◽  
Optimization Problem ◽  
Service Providers ◽  
Virtual Network ◽  
Placement Problem ◽  
Service Function ◽  
Network Functions ◽  
Bandwidth Consumption

The widespread adoption of network function virtualization (NFV) leads to providing network services through a chain of virtual network functions (VNFs). This architecture is called service function chain (SFC), which can be hosted on top of commodity servers and switches located at the cloud. Meanwhile, software-defined networking (SDN) can be utilized to manage VNFs to handle traffic flows through SFC. One of the most critical issues that needs to be addressed in NFV is VNF placement that optimizes physical link bandwidth consumption. Moreover, deploying SFCs enables service providers to consider different goals, such as minimizing the overall cost and service response time. In this paper, a novel approach for the VNF placement problem for SFCs, called virtual network functions and their replica placement (VNFRP), is introduced. It tries to achieve load balancing over the core links while considering multiple resource constraints. Hence, the VNF placement problem is first formulated as an integer linear programming (ILP) optimization problem, aiming to minimize link bandwidth consumption, energy consumption, and SFC placement cost. Then, a heuristic algorithm is proposed to find a near-optimal solution for this optimization problem. Simulation studies are conducted to evaluate the performance of the proposed approach. The simulation results show that VNFRP can significantly improve load balancing by 80% when the number of replicas is increased. Additionally, VNFRP provides more than a 54% reduction in network energy consumption. Furthermore, it can efficiently reduce the SFC placement cost by more than 67%. Moreover, with the advantages of a fast response time and rapid convergence, VNFRP can be considered as a scalable solution for large networking environments.

scholarly journals Cavitation patterns in high-pressure homogenization nozzles with cylindrical orifices: Influence of mixing stream in Simultaneous Homogenization and Mixing

2021 ◽  
Author(s):  
V. Gall ◽  
E. Rütten ◽  
H. P. Karbstein
Keyword(s):  
High Pressure ◽  
Process Design ◽  
High Speed ◽  
State Of The Art ◽  
Back Pressure ◽  
High Pressure Homogenization ◽  
Unit Operation ◽  
Mixing Chamber ◽  
Cavitation Intensity ◽  
Droplet Sizes

AbstractHigh-pressure homogenization is the state of the art to produce high-quality emulsions with droplet sizes in the submicron range. In simultaneous homogenization and mixing (SHM), an additional mixing stream is inserted into a modified homogenization nozzle in order to create synergies between the unit operation homogenization and mixing. In this work, the influence of the mixing stream on cavitation patterns after a cylindrical orifice is investigated. Shadow-graphic images of the cavitation patterns were taken using a high-speed camera and an optically accessible mixing chamber. Results show that adding the mixing stream can contribute to coalescence of cavitation bubbles. Choked cavitation was observed at higher cavitation numbers σ with increasing mixing stream. The influence of the mixing stream became more significant at a higher orifice to outlet ratio, where a hydraulic flip was also observed at higher σ. The decrease of cavitation intensity with increasing back-pressure was found to be identical with conventional high-pressure homogenization. In the future, the results can be taken into account in the SHM process design to improve the efficiency of droplet break-up by preventing cavitation or at least hydraulic flip.

scholarly journals The Influence of the Axial Rub Added in the Radial Rub on the Wear of the Seal Fins during the High Speed Rub of Labyrinth-Honeycomb Seal

Materials ◽  
2021 ◽  
Vol 14 (8) ◽  
pp. 1997
Author(s):  
Bin Lu ◽  
Haijun Xuan ◽  
Xiaojian Ma ◽  
Fangjun Han ◽  
Weirong Hong ◽  
...  
Keyword(s):  
Wear Rate ◽  
High Speed ◽  
State Of The Art ◽  
Negative Influence ◽  
Axial Thrust ◽  
Cross Sectional ◽  
Honeycomb Seal ◽  
Aero Engine ◽  
Honeycomb Seals ◽  
Clearance Change

Labyrinth-honeycomb seals are a state-of-the-art sealing technology commonly used in aero-engine interstage seal. The undesirable severe rub between the seal fins and the honeycomb due to the clearance change may induce the cracking of the seal fins. A pervious study investigated the wear of the seal fins at different radial incursion rates. However, due to the axial thrust and mounting clearance, the axial rub between the seal fins and the honeycomb may occur. Hence, this paper focuses on the influence of the axial rub added in the radial rub on the wear of the seal fins. The rub tests results, including rubbing forces and temperature, wear rate, worn morphology, cross-sectional morphology and energy dispersive spectroscopy results, are presented and discussed. Overall, the participation of the axial rub leads to higher rubbing forces, temperature, and wear rate. The tribo-layer on the seal fin is thicker and the cracks are more obvious at high axial incursion rate. These phenomena indicate the axial rub has a negative influence on the wear of the seal fins and should be avoided.

Sign in / Sign up

Export Citation Format

Share Document