scholarly journals Optimising Self-Similarity Network Traffic for Better Performance

2020 ◽  
pp. 164-176
Author(s):  
Ikharo A. B. ◽  
Anyachebelu K. T. ◽  
Blamah N. V. ◽  
Abanihi V. K.
Keyword(s):  
Network Traffic ◽  
Network Performance ◽  
Computer Network ◽  
Ann Model ◽  
Performance Measurements ◽  
Self Similarity ◽  
Traffic Modelling ◽  
Backpropagation Network ◽  
Self Similar

Given the ubiquity of the burstiness present across many networking facilities and services, predicting and managing self-similar traffic has become a key issue owing to new complexities associated with self-similarity which makes difficult the achievement of high network performance and quality of service (QoS). In this study ANN model was used to model and simulate FCE Okene computer network traffic. The ANN is a 2-39-1 Feed Forward Backpropagation network implemented to predict the bursty nature of network traffic. Wireshark tools that measure and capture packets of network traffic was deployed. Moreover, variance-time method is a log-log scale plot, representing variance versus a non-overlapping block of size m aggregate variance level engaged to established conformity of the ANN approach to self-similarity characteristic of the network traffic. The predicted series were then compared with the corresponding real traffic series. Suitable performance measurements used were the Means Square Error (MSE) and the Regression Coefficient. Our results showed that burstiness is present in the network across many time scales. The study also established the characteristic property of a long-range dependence (LRD). The work recommended that network traffic observation should be longer thereby enabling larger volume of traffic to be capture for better accuracy of traffic modelling and prediction.

Research on Self-Similarity Network Traffic Modeling

2011 ◽  
Vol 110-116 ◽  
pp. 2859-2865
Author(s):  
Yu Zhang ◽  
Teng Fei Yin
Keyword(s):  
Network Traffic ◽  
Network Performance ◽  
Mapping Function ◽  
Random Variable ◽  
Self Similarity ◽  
Mapping Model ◽  
Chaotic Mapping ◽  
Self Similar ◽  
Heavy Tailed ◽  
Definition Of

This paper introduces the phenomenon of self-similar network, and then it gives the mathematical definition of self-similar and analysis for the network performance. Based on this, this paper puts forward a new mapping model of ON / OFF and the chaotic mapping model based on the ideas. The model simplifies the chaotic mapping function mapping model by choosing a random variable with a linear piecewise function. The model length is subject to the state heavy-tailed. This model can capture network traffic self-similarity.

scholarly journals Basic characteristics of networks with self-similar traffic simulation

2019 ◽  
Vol 20 (1-2) ◽  
pp. 137-141
Author(s):  
Marek Aleksander ◽  
Roman Odarchenko ◽  
Sergiy Gnatyuk ◽  
Tadeusz Kantor
Keyword(s):  
Stochastic Process ◽  
Real Time ◽  
Experimental Research ◽  
Network Traffic ◽  
Network Performance ◽  
The Self ◽  
Self Similarity ◽  
Complex Models ◽  
Self Similar ◽  
Basic Characteristics

This paper is devoted to simulations the networks with self-similar traffic. The self-similarity in the stochastic process is identified by calculation of the Herst parameter value. Based on the results, received from the experimental research of network performance, we may conclude that the observed traffic in real-time mode is self-similar by its nature. Given results may be used for the further investigation of network traffic and work on the existing models of network traffic (particularly for new networks concepts like IoT, WSN, BYOD etc) from viewpoint of its cybersecurity. Furthermore, the adequacy of the description of real is achieved by complexifying the models, combining several models and integration of new parameters. Accordingly, for more complex models, there are higher computing abilities needed or longer time for the generation of traffic realization..

scholarly journals KLASIFIKASI PENGGUNAAN PROTOKOL KOMUNIKASI PADA TRAFIK JARINGAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR

2016 ◽  
Vol 16 (1) ◽  
pp. 67
Author(s):  
Komang Kompyang Agus Subrata ◽  
I Made Oka Widyantara ◽  
Linawati Linawati
Keyword(s):  
Quality Of Service ◽  
Network Traffic ◽  
Network Architecture ◽  
Nearest Neighbor ◽  
Computer Network ◽  
Data Communication ◽  
Data Capture ◽  
K Nearest Neighbor ◽  
High Level

ABSTRACT—Network traffic internet is data communication in a network characterized by a set of statistical flow with the application of a structured pattern. Structured pattern in question is the information from the packet header data. Proper classification to an Internet traffic is very important to do, especially in terms of the design of the network architecture, network management and network security. The analysis of computer network traffic is one way to know the use of the computer network communication protocol, so it can be the basis for determining the priority of Quality of Service (QoS). QoS is the basis for giving priority to analyzing the network traffic data. In this study the classification of the data capture network traffic that though the use of K-Neaerest Neighbor algorithm (K-NN). Tools used to capture network traffic that wireshark application. From the observation of the dataset and the network traffic through the calculation process using K-NN algorithm obtained a result that the value generated by the K-NN classification has a very high level of accuracy. This is evidenced by the results of calculations which reached 99.14%, ie by calculating k = 3. Intisari—Trafik jaringan internet adalah lalu lintas ko­mu­nikasi data dalam jaringan yang ditandai dengan satu set ali­ran statistik dengan penerapan pola terstruktur. Pola ter­struktur yang dimaksud adalah informasi dari header paket data. Klasifikasi yang tepat terhadap sebuah trafik internet sa­ngat penting dilakukan terutama dalam hal disain perancangan arsitektur jaringan, manajemen jaringan dan keamanan jari­ngan. Analisa terhadap suatu trafik jaringan komputer meru­pakan salah satu cara mengetahui penggunaan protokol komu­nikasi jaringan komputer, sehingga dapat menjadi dasar pe­nen­tuan prioritas Quality of Service (QoS). Dasar pemberian prio­ritas QoS adalah dengan penganalisaan terhadap data trafik jaringan. Pada penelitian ini melakukan klasifikasi ter­hadap data capture trafik jaringan yang di olah menggunakan Algoritma K-Neaerest Neighbor (K-NN). Apli­kasi yang digu­nakan untuk capture trafik jaringan yaitu aplikasi wireshark. Hasil observasi terhadap dataset trafik jaringan dan melalui proses perhitungan menggunakan Algoritma K-NN didapatkan sebuah hasil bahwa nilai yang dihasilkan oleh klasifikasi K-NN memiliki tingkat keakuratan yang sangat tinggi. Hal ini dibuktikan dengan hasil perhi­tungan yang mencapai nilai 99,14 % yaitu dengan perhitungan k = 3. DOI: 10.24843/MITE.1601.10

A Novel Flash P2P Network Traffic Prediction Algorithm based on ELMD and Garch

2020 ◽  
Vol 19 (01) ◽  
pp. 127-141
Author(s):  
Yimu Ji ◽  
Ye Wu ◽  
Dianchao Zhang ◽  
Yongge Yuan ◽  
Shangdong Liu ◽  
...  
Keyword(s):  
Network Traffic ◽  
Network Performance ◽  
Video On Demand ◽  
P2p Network ◽  
Prediction Algorithm ◽  
Campus Network ◽  
Local Mean Decomposition ◽  
Traffic Rate ◽  
Local Mean

To improve the quality of service and network performance for the Flash P2P video-on-demand, the prediction Flash P2P network traffic flow is beneficial for the control of the network video traffic. In this paper, a novel prediction algorithm to forecast the traffic rate of Flash P2P video is proposed. This algorithm is based on the combination of the ensemble local mean decomposition (ELMD) and the generalized autoregressive conditional heteroscedasticity (GARCH). The ELMD is used to decompose the original long-related flow into the summation of the short-related flow. Then, the GRACH is utilized to predict the short-related flow. The developed algorithm is tested in a university’s campus network. The predicted results show that our proposed method can further achieve higher accuracy than those obtained by existing algorithms, such as GARCH and Local Mean Decomposition and Generalized AutoRegressive Conditional Heteroskedasticity (LMD-GARCH) while keeping lower computational complexity.

Study of the Impact of Self-Similarity on the Network Node Traffic

1970 ◽  
Vol 111 (5) ◽  
pp. 27-32
Author(s):  
L. Kaklauskas ◽  
L. Sakalauskas
Keyword(s):  
Network Traffic ◽  
Buffer Capacity ◽  
Service Discipline ◽  
Network Node ◽  
Self Similarity ◽  
Packet Losses ◽  
Queue Discipline ◽  
Self Similar ◽  
Stochastically Bounded ◽  
The Impact

The article analyses a stochastically bounded the GI/G/m//N circuit switched network model with packet losses, with stochastic input network traffic, stochastic served network node, and deterministic and finite network node buffer capacity. Max-plus algebra instrumentality is used for the network processes analysis. FIFO tail drop or LIFO tail drop buffer is used. We have established that the average waiting time in the queue had increased when the queue service discipline was FIFO as compared with LIFO, while the offered traffic was Poisson and the served in the node traffic was self-similar. The network traffic is served faster in the network node with the buffer queue discipline LIFO, while the offered traffic is Poisson and its intensity exceeds the served in the node traffic 10 times. Ill. 2, bibl. 24 (in English; abstracts in English and Lithuanian).http://dx.doi.org/10.5755/j01.eee.111.5.350

scholarly journals Perancangan Performansi Quality Of Service Dengan Metode Virtual Routing Redudancy Protocol (VRRP)

2019 ◽  
Vol 5 (1) ◽  
pp. 87-92
Author(s):  
Mugi Raharjo ◽  
Frengki Pernando ◽  
Ahmad Fauzi
Keyword(s):  
Routing Protocol ◽  
Network Performance ◽  
Computer Network ◽  
The Internet ◽  
Performance Bond ◽  
Main Activity ◽  
A Company ◽  
Computerized System ◽  
Internet Network

The need for a network is the intenet is indeed already is common at this time. Do a computerized system in each routine office as well as the occurrence of problems in computer networks in a company can make the effectiveness and flexibility in an agency or company became very disturbed. In PT. PELITA Cengkareng, Tangerang Paper needs a stable internet network is the key to a company's main activity is to do every day. For it is need for a change in the system of internet network. To support all activities in the company who need access to a computer network or the internet. A stable traffic as well as the existence of a performance bond that was always adequate internet desperately needed in an era as it is today. For that VRRP (Virtual Routing Protocol Redudancy) is the solution to increase network performance can be done by the existence of this method. The existing network of companies will have a backup connectivity to backup when there are problems at the major networks

scholarly journals Traffic Behavior Analysis During the Transition from One Level of the Network Hierarchy to Another

2021 ◽  
pp. 5-10
Author(s):  
Lyudmila Gomazkova ◽  
◽  
Oleg Bezbozhnov ◽  
Osamah Al-Qadi ◽  
Sergey Galich ◽  
...  
Keyword(s):  
Network Traffic ◽  
Computer Network ◽  
Hierarchical Network ◽  
Self Similarity ◽  
Similarity Degree ◽  
C Programming Language ◽  
Hierarchical Topology ◽  
C Programming ◽  
Network Hierarchy ◽  
Traffic Behavior

The hierarchical network model is the most preferable in the design of computer networks, as it allows you to create a more stable structure of network, rationally allocate available resources, and also provide a higher degree of data protection. In this work, the study of the behavior of the traffic during the transition from one level of the network hierarchy to another, based on the study of the values of the traffic self-similarity degree during this transition. For the study, a simulation model of a computer network with a hierarchical topology was developed using the NS-3 simulator. Also, a window application was developed in the Visual C# programming language. With the help of this application the degree of self-similarity of the traffic was investigated using the files obtained as a result of processing the trace file. Thus, as a result of the study, it can be stated that any changes in the degree of self-similarity of the network traffic when this traffic moves from one level of the hierarchy to another level depends on such a condition as the direction of traffic movement. The initial degree of selfsimilarity of network traffic also effects on the network traffic self-similarity degree.

Sign in / Sign up

Export Citation Format

Share Document