WIDE Paper-List in 2006





    The Impact of Residential Broadband Traffic on Japanese ISP Backbones
                      wide-paper-mawi-rbbtraffic-00.txt









                     WIDE Project: http://www.wide.ad.jp/
                  If you have any comments on this document,
                       please contact to ad@wide.ad.jp.


Title: The Impact of Residential Broadband Traffic on Japanese ISP Backbones
Author(s): 名前 (メールアドレス)
	Kensuke Fukuda (fukuda@t.ecl.net)
	Kenjiro Cho (kjc@iijlab.net)
	Hiroshi Esaki (hiroshi@wide.ad.jp)
Date: 01/06/2006

  author =		[Kensuke Fukuda, Kenjiro Cho, Hiroshi Esaki]
  title =		[The Impact of Residential Broadband Traffic on Japanese ISP Backbones]
  type =		[magazine]
  institution =		[ACM SIGCOMM CCR]
  volume =		[35]
  number =		[1]
  pages =		[15-22]
  year =		[01/2005]
  site =		[http://www.iijlab.net/~kjc/papers/ivs-rbb-traffic.pdf]
  wideareaname =	[area4]
  widewgname =		[mawi]
  keyword =		[traffic measurement, residential broadband]
  references =		[]
  summary_ja =		[] 
  summary =		[
This paper investigates the effects of the rapidly-growing
residential broadband traffic on commercial ISP backbone networks.
We collected month-long aggregated traffic logs for different traffic
groups from seven major ISPs in Japan
in order to analyze the macro-level impact of residential broadband
traffic.  These traffic groups are carefully selected to be summable,
and not to count the same traffic multiple times.

Our results show that
(1) the aggregated residential broadband customer traffic in our data
exceeds 100Gbps on average.  Our data is considered to cover
41% of the total customer traffic in Japan, thus we can estimate that the
total residential broadband traffic in Japan is currently about
250Gbps in total.
(2) About 70% of the residential broadband traffic is constant
all the time.
The rest of the traffic has a daily fluctuation pattern
with the peak in the evening hours.
The behavior of residential broadband traffic deviates considerably
from academic or office traffic.
(3) The total traffic volume of the residential users is
much higher than that of office users, so backbone traffic is
dominated by the behavior of the residential user traffic.
(4) The traffic volume exchanged through domestic private peering is
comparable with the volume exchanged through the major IXes.
(5) Within external traffic of ISPs, international traffic is about 23%
for inbound and about 17% for outbound.
(6) The distribution of the regional broadband traffic is roughly
proportional to the regional population.

We expect other countries will experience similar traffic patterns as
residential broadband access becomes widespread.
]
  misc =		[]