Towards Evaluating Quality of Datasets for Network Traffic Domain

2021 ◽  
Author(s):  
Dominik Soukup ◽  
Peter Tisovcik ◽  
Karel Hynek ◽  
Tomas Cejka
Keyword(s):  
Network Traffic

Modernization of the software for measuring the quality of network traffic in the corporate network of the enterprise

2021 ◽  
pp. 104-113
Author(s):  
Е.Е. Истратова ◽  
Е.Н. Антонянц ◽  
А.О. Амельченко
Keyword(s):  
Network Traffic ◽  
Statistical Data ◽  
Client Server ◽  
Network Connection ◽  
Software Product ◽  
Corporate Network ◽  
Server Application

В статье представлены результаты модернизации ранее разработанного клиент-серверного приложения для исследования характеристик корпоративной сети. Результаты проведенных исследований позволили сделать вывод о том, что усовершенствованный программный продукт можно применять для сбора статистических данных о характеристиках сетевого подключения при передаче информации в корпоративной сети компании. The article presents the results of the modernization of a previously developed client-server application for the study of the characteristics of the corporate network. The results of the conducted research allowed us to conclude that the improved software product can be used to collect statistical data on the characteristics of the network connection when transmitting information in the corporate network of the company.

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.

Prediction Based on PSO-SVM in Power Communication Network Traffic

2014 ◽  
Vol 602-605 ◽  
pp. 2889-2892
Author(s):  
Zhen Dong Zhao ◽  
Rui Ju Xiao ◽  
Meng Meng Pei ◽  
Yi Zhou
Keyword(s):  
Communication Network ◽  
Electric Power ◽  
Network Traffic ◽  
Prediction Method ◽  
Parameters Optimization ◽  
Traffic Prediction ◽  
Model Parameters ◽  
Economy Running ◽  
Important Basis

Power communication network traffic prediction is important basis of safely assigning and economically running. The forecasting precision will directly affect the reliability, economy running and supplying power quality of power system. Paper first expounds the electric power communication network traffic prediction research present situation, summarized the characteristics of the forecast and the influencing factors, summarizes the commonly used method, is put forward to the return of the electric power communication network traffic based on libsvm prediction method, and the PSO (particle swarm optimization) algorithm is adopted to model parameters optimization, with the test set error as the decision, based on the optimization of model parameters, choice, makes the prediction precision is improved.

Improving the Optical Burst Switching Networks Quality of Service by Ensuring the Fairness among the Network Traffic Types

2015 ◽  
Vol 73 (2) ◽  
Author(s):  
Mohammed Al-Shargabi ◽  
Faisal Saeed ◽  
Zaid Shamsan ◽  
Abdul Samad Ismail ◽  
Sevia M Idrus
Keyword(s):  
Quality Of Service ◽  
Network Traffic ◽  
Optical Burst Switching ◽  
Burst Switching ◽  
Real Time Traffic ◽  
Traffic Loads ◽  
Significant Difference ◽  
Data Burst ◽  
Optical Burst

The Optical burst switching (OBS) networks have been attracting much consideration as a promising approach to build the next generation optical Internet. Aggregating the burst in the OBS networks from the high priority traffic will increase the average of the loss of its packets. However, the ratio of the high priority traffic (e.g. real-time traffic) in the burst is a very important factor for reducing the data loss, and ensuring the fairness between network traffic types. This paper introduces a statistical study based on the significant difference between the traffics to find the fairness ratio for the high priority traffic packets against the low priority traffic packets inside the data burst with various network traffic loads. The results show an improvement in the OBS quality of service (QoS) performance and the high priority traffic packets fairness ratio inside the data burst is 50 to 60%, 30 to 40%, and 10 to 20% for high, normal, and low traffic loads, respectively.

Time series forecasting with model selection applied to anomaly detection in network traffic

2020 ◽  
Vol 28 (4) ◽  
pp. 531-545
Author(s):  
Łukasz Saganowski ◽  
Tomasz Andrysiak
Keyword(s):  
Anomaly Detection ◽  
Network Traffic ◽  
Model Parameters ◽  
Problem Solution ◽  
Quality Of Data ◽  
Initial Stage ◽  
Statistic Model ◽  
Short Memory ◽  
Optimal Values

Abstract In herein article an attempt of problem solution connected with anomaly detection in network traffic with the use of statistic models with long or short memory dependence was presented. In order to select the proper type of a model, the parameter describing memory on the basis of the Geweke and Porter-Hudak test was estimated. Bearing in mind that the value of statistic model depends directly on quality of data used for its creation, at the initial stage of the suggested method, outliers were identified and then removed. For the implementation of this task, the criterion using the value of interquartile range was used. The data prepared in this manner were useful for automatic creation of statistic models classes, such as ARFIMA and Holt-Winters. The procedure of calculation of model parameters’ optimal values was carried out as a compromise between the models coherence and the size of error estimation. Then, relations between the estimated network model and its actual parameters were used in order to detect anomalies in the network traffic. Considering the possibility of appearance of significant real traffic network fluctuations, procedure of updating statistic models was suggested. The results obtained in the course of performed experiments proved efficacy and efficiency of the presented solution.

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.

Sign in / Sign up

Export Citation Format

Share Document