The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam makalah ini, kami membincangkan kesahihan model gamma berskala dan mencirikan perbezaan dalam trafik aplikasi peringkat hos dengan model ini dengan menggunakan jejak trafik sebenar yang dikumpul pada pautan transpasifik 150-Mbps. Mula-mula, kami menyiasat kebergantungan model (parameter α dan β, dan ketepatan pemasangan ε) pada skala masa Δ, kemudian cari skala masa yang sesuai untuk model. Kedua, kami memeriksa hubungan antara α, β, dan ε, untuk mencirikan perbezaan dalam jenis aplikasi. Penemuan utama kertas kerja adalah seperti berikut. (1) Jenis aplikasi yang berbeza menunjukkan kebergantungan yang berbeza bagi α, β, dan ε pada Δ, dan memaparkan Δ yang sesuai untuk model yang berbeza. Model ini lebih tepat jika trafik terdiri daripada paket yang dihantar secara berselang-seli daripada yang lain. (2) Model yang lebih sesuai diperolehi dengan nilai α dan β tertentu (cth, 0.1 < α < 1, dan β < 2 untuk Δ = 500 ms). Selain itu, trafik khusus aplikasi membentangkan julat khusus α, β dan ε untuk setiap Δ, supaya ciri ini boleh digunakan dalam kaedah pengenalan aplikasi seperti pengesanan anomali dan kaedah pembelajaran mesin yang lain.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Yosuke HIMURA, Kensuke FUKUDA, Patrice ABRY, Kenjiro CHO, Hiroshi ESAKI, "Characterization of Host-Level Application Traffic with Multi-Scale Gamma Model" in IEICE TRANSACTIONS on Communications,
vol. E93-B, no. 11, pp. 3048-3057, November 2010, doi: 10.1587/transcom.E93.B.3048.
Abstract: In this paper, we discuss the validity of the multi-scale gamma model and characterize the differences in host-level application traffic with this model by using a real traffic trace collected on a 150-Mbps transpacific link. First, we investigate the dependency of the model (parameters α and β, and fitting accuracy ε) on time scale Δ, then find suitable time scales for the model. Second, we inspect the relations among α, β, and ε, in order to characterize the differences in the types of applications. The main findings of the paper are as follows. (1) Different types of applications show different dependencies of α, β, and ε on Δ, and display different suitable Δs for the model. The model is more accurate if the traffic consists of intermittently-sent packets than other. (2) More appropriate models are obtained with specific α and β values (e.g., 0.1 < α < 1, and β < 2 for Δ = 500 ms). Also, application-specific traffic presents specific ranges of α, β, and ε for each Δ, so that these characteristics can be used in application identification methods such as anomaly detection and other machine learning methods.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.E93.B.3048/_p
Salinan
@ARTICLE{e93-b_11_3048,
author={Yosuke HIMURA, Kensuke FUKUDA, Patrice ABRY, Kenjiro CHO, Hiroshi ESAKI, },
journal={IEICE TRANSACTIONS on Communications},
title={Characterization of Host-Level Application Traffic with Multi-Scale Gamma Model},
year={2010},
volume={E93-B},
number={11},
pages={3048-3057},
abstract={In this paper, we discuss the validity of the multi-scale gamma model and characterize the differences in host-level application traffic with this model by using a real traffic trace collected on a 150-Mbps transpacific link. First, we investigate the dependency of the model (parameters α and β, and fitting accuracy ε) on time scale Δ, then find suitable time scales for the model. Second, we inspect the relations among α, β, and ε, in order to characterize the differences in the types of applications. The main findings of the paper are as follows. (1) Different types of applications show different dependencies of α, β, and ε on Δ, and display different suitable Δs for the model. The model is more accurate if the traffic consists of intermittently-sent packets than other. (2) More appropriate models are obtained with specific α and β values (e.g., 0.1 < α < 1, and β < 2 for Δ = 500 ms). Also, application-specific traffic presents specific ranges of α, β, and ε for each Δ, so that these characteristics can be used in application identification methods such as anomaly detection and other machine learning methods.},
keywords={},
doi={10.1587/transcom.E93.B.3048},
ISSN={1745-1345},
month={November},}
Salinan
TY - JOUR
TI - Characterization of Host-Level Application Traffic with Multi-Scale Gamma Model
T2 - IEICE TRANSACTIONS on Communications
SP - 3048
EP - 3057
AU - Yosuke HIMURA
AU - Kensuke FUKUDA
AU - Patrice ABRY
AU - Kenjiro CHO
AU - Hiroshi ESAKI
PY - 2010
DO - 10.1587/transcom.E93.B.3048
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E93-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2010
AB - In this paper, we discuss the validity of the multi-scale gamma model and characterize the differences in host-level application traffic with this model by using a real traffic trace collected on a 150-Mbps transpacific link. First, we investigate the dependency of the model (parameters α and β, and fitting accuracy ε) on time scale Δ, then find suitable time scales for the model. Second, we inspect the relations among α, β, and ε, in order to characterize the differences in the types of applications. The main findings of the paper are as follows. (1) Different types of applications show different dependencies of α, β, and ε on Δ, and display different suitable Δs for the model. The model is more accurate if the traffic consists of intermittently-sent packets than other. (2) More appropriate models are obtained with specific α and β values (e.g., 0.1 < α < 1, and β < 2 for Δ = 500 ms). Also, application-specific traffic presents specific ranges of α, β, and ε for each Δ, so that these characteristics can be used in application identification methods such as anomaly detection and other machine learning methods.
ER -