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
Certaines relations entre les modèles de perte de paquets successifs et l'espacement des paquets sont décrites. Pour observer un modèle de perte de paquets successifs, une méthode possible consiste à étudier les paquets de test générés à certains intervalles (par exemple, intervalle de Poisson, intervalle régulier constant). Cependant, la perte successive de paquets dépend fortement de l'intervalle généré. Si les paquets de test sont générés à de longs intervalles, le modèle de perte successive ne peut pas être affiché. Ainsi, dans un tel procédé, où les intervalles entre les paquets peuvent parfois être longs ou courts, la succession des pertes de paquets doit être considérée en termes d'espacement des paquets. Pour clarifier la relation entre la perte successive de paquets et l'espacement des paquets, nous analysons les données basées sur l'observation d'un réseau réel avec la taille de la fenêtre de perte comme paramètre. Nous constatons que lorsque l'espacement des paquets est plus étroit, c'est-à-dire qu'il a un intervalle plus court, la probabilité devient plus élevée que le paquet suivant immédiatement une perte de paquet unique soit également perdu.
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.
Copier
Teruko MIYATA, Harumoto FUKUDA, Satoshi ONO, "Impact of Packet Spacing Time on Packet Loss under Loss Window Size for FEC-Based Applications" in IEICE TRANSACTIONS on Information,
vol. E82-D, no. 4, pp. 846-853, April 1999, doi: .
Abstract: Certain relationships between successive packet loss patterns and packet spacing are described. To observe a successive packet loss pattern, one possible method is to investigate test packets that are generated at certain intervals (e. g. , Poisson interval, constant regular interval). However, successive packet loss strongly depends on the interval generated. If test packets are generated with long intervals, then successive loss pattern cannot be shown. Thus, in such a method, where the packet intervals may sometimes be long or short, the successiveness of the packet loss should be considered in terms of the packet spacing. To clarify the relationship between the successive packet loss and the packet spacing, we analyze data based on observation of an actual network with the loss window size as a parameter. We find that when the packet spacing is narrower, i. e. , has a shorter interval, the probability becomes higher that the packet immediately following a single packet loss would also be lost.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_4_846/_p
Copier
@ARTICLE{e82-d_4_846,
author={Teruko MIYATA, Harumoto FUKUDA, Satoshi ONO, },
journal={IEICE TRANSACTIONS on Information},
title={Impact of Packet Spacing Time on Packet Loss under Loss Window Size for FEC-Based Applications},
year={1999},
volume={E82-D},
number={4},
pages={846-853},
abstract={Certain relationships between successive packet loss patterns and packet spacing are described. To observe a successive packet loss pattern, one possible method is to investigate test packets that are generated at certain intervals (e. g. , Poisson interval, constant regular interval). However, successive packet loss strongly depends on the interval generated. If test packets are generated with long intervals, then successive loss pattern cannot be shown. Thus, in such a method, where the packet intervals may sometimes be long or short, the successiveness of the packet loss should be considered in terms of the packet spacing. To clarify the relationship between the successive packet loss and the packet spacing, we analyze data based on observation of an actual network with the loss window size as a parameter. We find that when the packet spacing is narrower, i. e. , has a shorter interval, the probability becomes higher that the packet immediately following a single packet loss would also be lost.},
keywords={},
doi={},
ISSN={},
month={April},}
Copier
TY - JOUR
TI - Impact of Packet Spacing Time on Packet Loss under Loss Window Size for FEC-Based Applications
T2 - IEICE TRANSACTIONS on Information
SP - 846
EP - 853
AU - Teruko MIYATA
AU - Harumoto FUKUDA
AU - Satoshi ONO
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 1999
AB - Certain relationships between successive packet loss patterns and packet spacing are described. To observe a successive packet loss pattern, one possible method is to investigate test packets that are generated at certain intervals (e. g. , Poisson interval, constant regular interval). However, successive packet loss strongly depends on the interval generated. If test packets are generated with long intervals, then successive loss pattern cannot be shown. Thus, in such a method, where the packet intervals may sometimes be long or short, the successiveness of the packet loss should be considered in terms of the packet spacing. To clarify the relationship between the successive packet loss and the packet spacing, we analyze data based on observation of an actual network with the loss window size as a parameter. We find that when the packet spacing is narrower, i. e. , has a shorter interval, the probability becomes higher that the packet immediately following a single packet loss would also be lost.
ER -