►
Description
At 16:30-17:15 on 18 July, Chang Yue, Chief Architect of Network Product Line of Huawei Technologies, will present "Challenges of Evolution Towards Autonomous Network"
A
Hey
so
it's
almost
time,
thank
you.
Everyone
for
coming
we're
gonna
start
the
technical
technology
session.
Today
we
are
very
fortunate
to
get
our
chief
architect
for
our
carrier
business
unit
to
talk
about
technology
and
how
he
has
been
instrumental
in
bringing
our
revenue
to
pass
the
hundred
billion
mark
last
year
so
we're.
Unfortunately,
that's
welcome,
trying
to
talk.
B
Good
afternoon,
everyone
so
and
I'm
aware
I
collide
to
have
opportunity
to
make
a
prize
and
prizes
the
presentation
about
our
ideas
and
some
practice
in
network
architect,
evolution
also
because
response
for
the
product
and
a
solution,
architecture
design.
So
we
think
we
feel
in
the
recent
years
we
a
network
word
is
the
great
challenge,
so
I
think
I
hope
my
sharing
will
be
will
be
benefit
and
helpful
for
ITF
to
to
let
us
to
face
the
challenge
together.
So
ok,
let's
begin
so.
B
During
during
the
past,
several
decades,
IETF
and
Engineering's
made
a
great
contribution
for
the
networking
in
the
world.
So
currently
the
IP
network
has
already
covered
almost
covered
all
of
the
world
and
become
very
important
infrastructure
for
the
information
world.
So
more
and
more
application
and
the
services
rely
on
the
network
in
France
infrastructure
such
as
a
cloud
in
the
night
and
in
the
future,
maybe
the
IOT
so
on
a
country.
So
this
application
rely
on
network.
B
On
the
contrary,
so
the
network
faced
the
great
challenges
for
new
requirements,
so
so
follow
IV
network
or
we
wasting,
as
there
are
major
three
segments
market,
the
first
cloud
network,
the
second
hysterical
Network
and
authorities
Enterprise
din
that
work.
So
today
my
topic
is
mainly
focused
on
mainly
focusing
on
the
telco
network.
So.
B
Currently,
our
faith,
currently
the
telco
network
Fister,
creates
challenges
in
in
in
the
industry.
So
in
the
summaries
for
from
the
from
from
the
external
we
can
say,
we
can
see
in
the
future.
More
and
more
application
and
network
will
rely
on
it,
so
they
are
in
the
future.
There
may
be
more
than
75
billion
devices
will
connect
it
by
the
welder
obeys
the
network,
but
at
the
same
time,
but
but
is
the
but
in
Turner
the
currently
the
network
mode,
the
delivery
mode,
the
operation
mode
there.
B
There
is
a
great
gap
for
the
requirement,
for
example,
so
the
objects
increased
greatly,
so
almost
almost
occupy
more
than
70
to
80
percent
of
the
TCO
of
sir
carrier.
So
this
means,
but
at
the
same
time
the
revenue
increase
is
very
slow,
so
list
means
it
is
difficult
for
carrier
to
invest
continuously
for
the
network
list,
the
first,
so
the
reason
for
for
our
packs
increase
are
wasting.
Maybe
maybe
the
may
be
low
maintenance
efficiency,
because
we
think
is.
B
B
I
think
we
need
to
think
about
system
architecture
in
your
nation,
so
we
we,
we
think
of
Nam
autonomous
network,
will
be
the
future
of
the
network
architect
so
before
to
think
about
autonomous
network,
where
we
make
a
deep
starting
about
the
current
network
of
OTT
and
telecom
network,
so
the
right
side,
the
left
side,
the
left-
that
is
a
typical
as
a
typical
cloud
network
in
fact
act.
So
we,
the
right
side,
is
a
typical
network
architecture
over
the
telco.
So
for
followed
for
a
cloud
network
we
can,
we
can
fund.
B
B
It
is
easy
to
deploy
with
with
the
change
of
the
workload
and
application,
so
at
the
same
at
the
same
time,
so
there
is
a
very
clearly
boundary
of
the
cloud
services
at
a
network
operation
in
layer
so
and
all
of
this
process
are
realized
by
the
software
to
realize
the
automation,
but
for
the
ten
called
telco
or
network.
So
currently,
the
transport
and
and
natural
services
in
general,
converged
in
dedicated
hardware.
So
it
is
difficult
to
get
up
for
for
network
transport
and
network
services
independently.
B
We
will,
as
we
know
when,
when
we
do
I
loved
the
product.
We
know
the
network
services
and
the
network
transport
rely
on
different
process.
Different
hardware
features,
so
within
one
boss,
it
is
difficult
to
to
scale
up
independently,
so
the
second,
the
second
difference
is
so
currently
for
catechol
network.
There
are
services
and
management
system
are
sterile
system
so
and
sort
for
example.
There
are
a
lot
of
network
services
and
management
system
for
access
network
for
metro
network
for
for
for,
for
example,
for
the
core
network.
B
So,
at
the
same
time
as
a
boundary
of
the
network,
services
and
network
operation
is
not
very
clear,
so
in
some
area,
maybe
they
realize
the
service
system
will
talk
with
the
device
directly.
For
example,
maybe
some
use
case,
some
OS
system
talk
to
access
not
directly
so
but
for
other
for
more
for
more
for
other
scenario,
maybe
the
service,
the
services
platform
will
talk
of
its
network
with
with
the
operation
team
with
the
people.
So
here,
so
we
please.
This
means
a
lot
of
work
should
be
done
by
manual
by
people.
B
This
is
the
great
difference
between
the
OTT,
Network
and
telecom
network,
so
to
to
to
discuss
about
the
autonomous
network
architecture.
Maybe
it
is,
it
is
necessary
to
think
about
to
think
about
some
value
and
as
a
goal,
the
over
picture
of
the
value
of
the
goal
of
the
network,
so
I
think
the
the
final
heart
rate
is
increased.
The
revenue
and
the
decreased
TCO
that
there
are
three
three
major
value
of
relation,
so
that
is
that
is,
that
is
a
better
customer
experience.
B
Higher
operation,
efficiency
and
open
the
program
ability
for
operation,
vision,
I
think
zero
torch
operation
is
the
target,
so
maybe
in
the
future
we
need
is
so
fuller
for
the
heart
rate.
We
need
to
make
the
NOC
easy
and
simple
and
the
way
needed
to
solve
the
challenge
of
continuously
service
provisioning
for
the
network.
Currently,
it
is
difficult
to
continues
continuously
the
delivery
of
the
service
on
network
in
general
for
talent,
telco
carrier.
They
have
a
change
window
for
the
network
modification
and
another.
B
Another
challenge
is
how
to
make
medicate
make
rotation
from
the
legacy
and
network,
so
in
January.
If
currently,
for
the
customer
follow
a
telco
players.
If
they
want
to
introduce
a
new
device,
when
you
a
vendor,
it
is
the
it
will
investor
to
reach
to
to
adopts
a
new
device,
and
so
this
is
so
to
solve
this
problem.
We
need
to
think
about
the
architecture
and
some
technology
later
I
will
maybe
introduce
some
part
of
this.
B
So
this
is
a
general
idea
of
the
autonomous
networks,
reference
architecture,
so
the
right
side.
So
for
the
network
itself,
we
think
maybe
we
think.
Maybe
we
need
to
be
copying.
The
transport
and
network
services
function
completely
so
because
so
for
network
transport,
they
are
Network.
Transport
is
focused
answer
that
the
bandwidth
increase,
the
bandwidth
utilization
and
the
answer
a
guaranteed.
But
for
so
this
means
it's
a
transport
made
a
focused
on
the
physical
infrastructure,
but
for
network
services.
In
fact,
it
focused
on
the
user
and
the
subscriber
itself
its
application.
B
So
this
means
for
user
and
the
for
server
for
user
for
tenant.
The
most
important
feature
is:
do
you?
Could
you
deploy
the
services,
actuality,
flexible,
yeah
and
have
a
good
and
they
can
guarantees
service?
Experience
looks
a
customer
we
can
found.
The
logic
is
different
for
a
transport
and
and
network
services.
B
So
this
is
why
we're
seeing
waiting
in
the
future,
the
network,
the
copying
of
transport
and
the
services
that
were
important
and
maybe
in
the
future,
based
on
the
based
on
the
hardware
and
silicon
technology,
progress
wasting,
maybe
for
the
transport
network,
it
will
be
more
rely
on
the
on
the
dedicate
hardware
and
the
chip
side,
but
for
the
network
services
more
rely
on
the
software
based
on
the
general-purpose
computing
capability.
So
this
is
the
follow,
follow,
Network
hardware,
our
network
itself
follow
network
services
and
the
management
system.
We
think.
B
System
so-
and
it's
very
important
so
late
means
we
need.
We
need
to
establish
a
common
platform
for
network
operation
and
a
common
network
service
platform
for
services.
So
in
one
hand
we
can
we
can
so
based
on
its
platform.
It
is
easy
to
maybe
it
is
benefited
to
to
deploy
the
network
transport
and
the
network
services
and
to
end
and
all
of
this,
and
all
of
this
system
should
be,
should
execute
by
software.
So
this
is
a
left-side.
So
how
to
realize
this
network
management
and
a
network
services
platform,
we
called
autonomous
control
system.
B
The
right
side
is
the
general
idea
of
less
octant
I
think
wasting
this.
This
ACS
system
should
be
consists
of
the
four
major
engines,
the
intended
engine,
autonomy,
autonomy,
automation,
engine,
an
elastic
engine
and
the
intelligent
engine,
and
all
of
the
engine
should
be
work.
Work
in
a
closed-loop
model,
this
music.
It
can
realize
the
Adamas
in
each
layer.
B
B
It
realized
very
a
decoupling
between
the
network
transport
and
the
network
services,
but
in
general
they
have
a
how
to
say
it
can
it
cannot
realize,
though
agnostic
so,
hopefully
examples
of
ax
line,
so
so
this
is
the
way
we
think.
Maybe
we
currently
are:
we
follow
that
protocol
evolution
we
think,
may
be.
The
following.
Three
principles
are
important.
The
first
is
the
natural
services
transportation
technology
are
no
erotic
naturally,
and
it
can
be
replaced
independently
means,
maybe
replace
the
whole
evolution
independently.
B
The
second
is
a
very
various
transportation
with
different
technology
can
be
used
for
the
specific
service
later
I
will
share
a
use
case
of,
as
divine
is
the
typical
scenario
for
a
second
for
a
second
principle,
and
a
third
days
multiple
can
do
of
services
can
be
supported
by
responding
transporting
transportation
technology.
I
think
we're
wasting
may
be
this.
This
principle
very
important
for
a
protocol
evolution.
B
For
a
transport
for
a
transport
layer,
we
think,
maybe
in
the
future,
the
the
the
target
of
the
of
the
obsolete
list
layer
how
to
guarantee
the
capacity
girls
and
the
resource
utilization
this
reasonable
cost.
The
second
is
how
to
visibility
and
a
guarantee
ice
array
of
its
services.
The
third
is
how
to
achieve
always
on
on
delay.
So.
B
They
see
this
is
to
realize
to
agree
to
realize
this
target
we
need
to
think
about.
We
think
some
some
something
need
to
think
think
about
the
first.
We
need
to
simplify
the
protocol
system
and
to
realize
two
supports
and
to
end
all
babies
next
slide.
Okay,
so
this
slide
show
some
so
our
some
ideas
about
about
the
protocol
evolution.
B
It
is
also
become
rarer
or
become
more
popular
we've
seen
in
the
future,
the
underlay
transport
network
should
be
a
basic
infrastructure
to
connect
his
a
Marty
cloud.
This
means
the
the
traffic
traffic
pattern
will
be
changed
and
the
network,
how
the
same
just
like
fabric,
can
support
all
kinds
of
traffic
among
the
dip
cloud
cloud,
so
they
say
the
what
we're
seeing,
maybe
in
the
future.
The
idea
is
that
the
underlay
transport
transport
transport
network
should
be
flight
in
network
can
provide
very
big
bandwidth
and
the
scale-up
ask
a
out
very
easily.
B
This
is
the
basic
idea
to
think
about
transport
transport
network
and
follow.
Follow
overlay.
Network
I
will
share
two
use
cases.
We
are
to
use
case
it
to
to
understand
the
requirement
of
this
network.
The
first
one
is
to
is
to
establish
the
cloud-based
overlay
and
network
for
the
customer,
so
we
we
we
do.
In
the
past
two
years
we
developed
our
way
to
alpha
list
network
based
on
our
public
cloud
visa
cooperative
with
France
Telecom,
their
telecom
and
China
Telecom.
So
the
idea
is,
we
hope
to
deploy.
B
The
target
is
for
the
customer
one
point:
access
for
a
global
network.
This
means,
if
the
customer
access
network
we
can,
we
can
deploy
the
virtual
virtualized
network
based
on
the
cloud
infrastructure
and
to
realize
the
globe
Global
connection
for
the
customer
work
quickly.
So
the
list
is
the
second,
so
service,
provisioning
in
minutes
and
adult
encourages
in
second.
Currently,
if
you
just
rely
on
telco
cloud,
it
is
difficult
to
realize
its
target.
So
this
is
a
this
is
what
what
we
are.
This
is
the
target
weight
developed.
B
This
is
network,
so,
besides
the
traditional
way
knife
such
as
a
DVR
in
the
VP's,
the
Gateway,
we
we
added
some
to
a
new,
we
being
us.
Why
is
the
VPN
gateway?
Well,
another
is
X
gateway.
Vpn
gateway
is
used
to
as
access
point
to
all
kinds
of
a
tool
to
the
customer,
while
the
wells
are
different
to
technology,
such
as
the
leased
line,
Marin
peers,
VIP
circle
appear
so
as
gateway
is
used
to
interconnect
waste,
which
is
a
different,
a
different
datacenter.
B
So
this
is
the
basic
solution
follow
for
the
overlay
virtualized
network.
So
when
we
develop
the
least
gateway
now
here
is
there
is
a
more
detailed
information
about
how
to
realize
the
services
requirement
so
to
follow
customer
access,
the
access
it
Center
and
access
their
their
own
way,
PC
in
a
local
position
or
in
a
remote
position
and
based
on
its
network.
B
18
also
can
support
the
customer
connect
to
their
network
Wells
a
cloud
so,
but
when
we
develop
today's
component,
such
as
the
weekly
tree
and
a
skit,
we
we
found
a
lot
of
challenges
never
faced
before
for
examples.
The
first
is
the
capacity
so
because
this
axe
gateway
and
the
wicket
we
will
connect
a
lot
of
customer.
So
the
here
the
capacity
is
not
as
a
challenge.
Not
it's
not
the
bandwidth.
It
is
control
plan
in
general.
B
B
So
this
means,
and
at
same
time
we
at
the
same
time
we
need
to
add
a
feature
easily,
because
the
way
we
all
support
IPSec,
we
were
suppose
I
said
live
here
and
we
were
supposed
MPs
and
in
future
we
get
to
ads
are
more
and
more
feature.
This
is
a
second
so
because
of
the
because
of
the
because
of
the
the
capacity
and
the
performance
requirement
or
the
traditional
network
network
product
available.
B
Reliability
cannot
satisfy
the
traditional
networks.
Justice
supports
the
1+1
control
plan
and
as
a
backup,
but
wasting
to
support
this
natural
wasting
m2n
model
should
be
supported.
So
there
are
a
lot
of
technology
should
be
should
be
should
be
solved.
Clearly
is
a
typical
example
is,
as
we
know,
currently,
the
PGP
connections
rely
on
the
P
TCP,
but
when
we,
when
we
realize
that
when
we
realize
the
network
function
on
a
server,
we
know
the
reliable,
the
availability
of
server
is
not
very
high
in
general.
B
Server
will
be,
will
be
done
so
currently
do
you
for
the
BGP
rely
on
the
TCP.
It
is
a
great
challenge
to
realize
the
high
availability,
for
example,
and
to
end
a
model
for
control
plan.
So
let
means
we
need
to
win
you
to
run
several
control
plan
at
the
same
time,
and
maybe
you
and
maybe
select
is
the
best
best
result
of
the
different
control
plan
and
in
the
future
we
hope
we
can
upgrade
the
the
control
plan.
How
to
say
it.
B
Individually
and
maybe
raising
the
different
version
of
the
software,
so
listen,
all
of
this
feature
rely
on
the
BGP
connection.
The
robust
of
HP
connection
may
be.
Currently
we
use
some
software
technology
of
our
complex
software
software
technology
to
solve
the
issue,
but
we
think
maybe,
if
we
think
about
the
the
the
evolution
look
at
the
BGP.
Maybe
is
it
better?
So
here's
just
a
sample
for
following
us,
so
another
another
use
Kizer
as
Devon,
so
currently,
as
the
divine
is
a
very
hot
topic
in
the
industry,
so
I
think
it.
B
B
So
the
first
scale,
because
in
general,
is,
are
thousands
of
thousands
of
site
for
a
enterprise,
so
the
scale
is
very
important,
so
the
second
is
is
how
to
say
advanced
erosion
technology
is
necessary
in
general
for
the
sd1,
because
they
are
maybe
they
are
in
general.
There
are
several
eternal
to
to
transport
a
service
example.
One
is
a
amperes
another
internet,
so
how
to
how
to
select
the
selects
a
different
channel
so
not
based
on
the
service
experience
based
on
the
policy.
So
this
is
listed.
B
A
very
murky
feature
for
lies,
dy
and
another
important
thing
is
security,
because
we
deployed
the
network
on
the
Internet.
The
security
consideration
and
the
deployment
are
very
important,
just
as
the
third
challenge
is
both
the
policy
network
policy,
because
when
we
deploy
the
winger's
so
dynamically,
so
how
to
guarantees
the
policy
consistent.
It
is
another
challenge.
All
of
these
things,
in
fact,
different
vendor
have
a
have
a
different,
innovative
ideas
to
solve
these
challenges,
but
currently
almost
others.
All
of
this
solution
are
based
on
the
prepay
Terry,
a.
B
Preferred
solution
to,
for
example,
is
banned
by
the
BGP,
so
we
hope
maybe
ideas
can
can,
can
do
more
contributing
in
in
this
area,
because
if
Sol
it
means
in
the
future,
it
can
help
to
realize
into
working
with
the
different
vendors
as
divine
solution.
So
this
is.
This
is
the
second
use
case
about
the
overlay.
Network.
B
So
we
think
model
definition
is
very,
very
important
to
to
realize
the
automation,
and
so
this
is
that
okay,
so
currently,
there
ITF
has
already
has
already
made
a
lot
of
has
already
established
a
workgroup
and
draft
for
the
model.
Definition
at
the
same
time,
in
the
industry
there
are,
there
are
a
lot
of
organization
and
vendors
and
a
customer
to
define
their
own
young
model,
for
example,
open
config,
for
example,
as
a
cisco
and
the
highway
will
has
already
released
as
their
their
their
private
model.
So
I
think,
I
think,
wasting
we
think.
B
Itf
is
very
important
to
lead
all
of
this
all
of
this
organization
and
the
players
to
define
the
relative
standard
model.
It
is
very
important
for
the
industry,
so
this
is
okay.
This
is
about
young
model,
so
the
last
last
very
important,
very
important
design
is
about
the
holistic
and
intelligent
of
the
autonomous
and
network.
B
So
we
can
here
is:
is
a
use
Kies
about
two
compounds
to
show
the
challenges
for
the
autonomous
network
so
and
in
general,
currently
the
the
root
cause,
so
how
to
say
the
the
network
should
be
I
should
have
thought
can
influence
the
services
deployed
on
the
network,
but
but
in
layers,
as
there
are
different
world,
so
in
general
for
network
operation,
the
the
the
fault
can
be
caused
by
the
configuration
so
the
park
of
hardware
and
stored
we're
at
the
software
so
butter
for
our
services.
They
don't
care
about
these
issues.
B
They
care
about
service
experience,
so
yeah
the
policy
can
be,
can
be
execute
correctly.
So
theory,
there
is
no
correlation
correlation
between
the
network
fault
and
the
services,
experience
and
fault.
Currently
this
is
the
list
of
the
major
challenge
for
the
network
network
operation
and
the
for
the
and
the
customer.
So
we
think
why
the
reason
reason
for
that.
The
first
is
the
lack
of
data
full
of
thought
because
and
analysis.
So
the
second
T
is
so
it
is.
B
It
is
a
lack
of
lack
officer
mechanism
to
allow
the
application
or
service
experience
so
and
the
majority
feeler
are
detect
passive
passively.
This
means
may
be
driven
by
the
complaint
of
the
end
customer.
Those
may
be
customers
say:
oh
I
cannot
access
Internet.
Oh,
my
video
quality
is
very
bad,
but
currently
we
can.
The
the
currently
and
network
operation
cannot
found
these
issues
proactively.
This
is
the
third
is
lack
of
the
capability
to
correlated
to
the
issues
between
the
network
and
application.
B
So
all
of
this
how
to
solve
these
challenges
icing
the
basis
telemetry
is
very
important.
We
need
to
change
the
traditional
network,
maintain
a
network
status
collector
and
make
mechanism
to
the
future
so
from
the
polling
polling
based,
polling
based
and
focused
on
the
device.
The
stators
expand
to
the
telemetry,
based
focusing
on
real-time
status
of
the
network
and
from
expand
from
static
topology
based
focused
on
device
link
to
the
dynamic
path
focused
on
application
flows
and
extend
from.
B
The
just
expand
from
the
folks
on
the
management
tool,
not
only
management
plan
but
also
control
plan
and
the
forwarding
plan
so
and
at
the
same
time,
based
on
this
data,
we
can
correlate.
We
can
establish
correlation
between
the
network
status
and
the
services
daters.
It
is
benefit
for
the
full
analysis
and
maybe
not
stab
fully
intelligent
of
the
network.
B
So
this
chart
shows
the
overview,
the
full
stack
for
the
network
analysis
and
the
intelligence
based
on
this
chart.
Maybe
we
can
we
can
we
can.
We
can
understand
the
issues
we
mentioned
and
more,
while
so
from
the
bottom
bottom
up
are
wasting
as
they
are
at
least
the
three
layers
for
the
network
analysis
and
the
intelligent
in
the
future.
The
bottom
line
is:
is
a
network
device
itself,
so
in
here,
so
we
we
think
we
need
to
expand.
B
We
need
to
strengthen
the
data
collection
capability,
not
only
focused
on
the
management,
but
also
includes
control
plan
and
the
data
data
plan.
This
means
as
a
challenges.
This
means
we
need
to
develop
some
new
protocols
and
and
format
and
Mechanics
for
this
for
different
data
collection,
for
example,
for
data
plan,
the
the
volume
of
data
is
very,
very
huge.
Maybe
we
need
to
really
to
design
some
new
mechanics
to
two
classes
data.
So
above
the
network
is
a
collective,
a
collector,
so
basically
on
Clark
layer
it
can
adopt
to
a
different
interface
to
network.
B
So
I
think
the
interface
between
the
collector
and
and
the
network
are
very
important
so
here,
if,
if
ITF
can
lead
to
define
the
relative
standard
protocol
and
and
encoding
and
the
format
for
a
data,
fuller,
fuller
data
collector-
it
is
very
very
benefit
for
the
industry
above
the
collector.
So
we've
seen
we
we
think,
maybe
there
yeah
it
is
necessary
to
deploy
two
layers
analysis.
Why
is
the
online
online
analysis
near
to
the
network
itself?
And
that
may
be
another?
Is
the
offline
offline
analyzes
data
system
mainly
used
for
training
and
studying?
B
So
this
is
a
so.
It's
fuller,
fuller,
fuller
for
the
online
analysis
platform,
a
it
will
pro
pro
while
the
data
leak
can
gather
all
kinds
of
data
and
share
the
data
folder
for
the
for
the
network
of
my
tenants.
So
it
is
very
important
to
solve
the
Salo
system
maintenance
issues.
So
this
is
the.
This
is
the
basic
architecture
the
next
I
will
I
will
share
a
use
case
to
to
about
about
the
network,
intelligent
realization
what
is
with
his
basically
model
and
what
is
a
challenge.
B
So
this
this
story
has
very
interesting:
it's
not
where
little
related
ways
protocol.
It
is
really.
It
is
about
the
physical
network,
so
was
full
of
pong,
a
physical
pong
access
network.
So
for
ftth
we
know
as
cattle
that
the
telco
vendor
will
provide
a
very
huge
and
a
large-scale
passive
optical
network
to
tune
a
customer
to
a
little
home
gateway
so
to
maintenance,
listen
network,
it's
very,
very
challenge,
so
because
it
is
it's
a
passive
network.
B
How
to
how
to
how
to
found
or
located
is
a
fault
of
the
network,
and
the
here
is
the
fault
occurred.
It
is
very
difficult
because
this
is
a
passive
Network
and
under
the
situation
as
the
environment
is
very,
very
complexed.
So
thus
issues
is
not
only
the
broke
broken,
but
also,
maybe
some
how
to
say.
Maybe
some
the
quality
is
decreased,
for
example,
maybe
for
5oe
for
over
bending
the
fybel.
Maybe
the
the
current
here
will
be
decreased
or
not
broken,
maybe
is
the
connector
is
losing
its
also.
B
The
stimulus
space
means
in
the
situation
is
very
complex,
so
the
second
is
why
we
need
to
wean
you
to
located
the
accurate
position
of
the
fault,
because
all
of
these
issues
should
be
should
be
solved
by
by
by
sight
engineering
workload.
So,
ladies,
the
great
challenge
so
based
when,
when
we
face
this
challenge,
we
we
use
the
big
data
technology,
so
collect
a
lot
of
data
from
aunty
and
and
ort
and
extract
the
feature
of
this
data
and
training
the
model
for
a
training.
B
The
model
training
efforts
pad
model
so
realize
so
currently
we
achieved
a
really
good
result
will
reduce
the
40%
of
total
as
the
resist
and
and
increase
the
prediction
prediction
of
the
fault
80
percent,
but
we
they
said
list
the
good
good
hand.
The
other
hand
is
with
the
left
side
left
left
part
and
so
to
realize
this
realized
analysis
and
the
prediction
we
have
to
collected
a
huge
of
data
so
here
is.
It
is
real
example
for
a
10k
access
access
customer
for
one
week
we
have
to.
B
We
have
to
collect
more
than
six
terabyte
data
to
analyze
and
analyzes.
It
is
the
great
cost
for
data
transportation
and
the
data
storage
in
a
data
process,
so
the
challenges,
so
this
means
Big
Data,
cannot
solve
everything,
especially
with
the
condition
of
the
cost.
So
this
means
we
sync
the
domain
knowledge
introduced
to
to
improve
the
processor
that
data
data
addresses
efficiency.
It's
very
very
important.
B
So
this
is
the
use
case
to
share
this
the
use
case,
because
we
think
maybe
we
can
so
for
routing,
for
routing
issues,
analysis
and
and
and
troubleshooting
for
routing
issues,
and
maybe
in
the
future,
to
predict
the
routing
issues.
It
is
a
very,
very
important
for
the
IP
network,
so
this
is
the
big
problem
from
birth
over
the
IP
technology:
how
to
how
to
detect
the
failure
of
the
routing?
How
to
predict
the
failure
of
the
row
team?
B
Maybe
we
can
we
can
introduce
a
new
technology,
a
data
analyst
technology,
full
fault
for
this
error,
but
we
think
we
think
the
domain
knowledge
is
very,
very
important
to
just
rely
on
the
generic,
the
big
data
technology
I.
Don't
think
it
can
achieve
a
very
good
result.
This
is
this
is
why
I
share
the
huge
keys
for
the
network?
B
Ok,
so
the
last
nice
part
about
security,
our
security
is
very
important,
especially
in
recent
in
recent.
A
lot
of
organization,
the
country
and
people
think
console
security
is
a
big
challenge
for
the
network
forest
OSHA
and
follow
for
the
world.
So
but
I
think
we
we
need
to
work
together
to
solve
these
challenges,
so
we
cannot.
B
So
maybe
there
are
some
different
consideration
about
the
network
security.
How
to
adopt
this
technology
to
this
solution,
I
suggest
that
maybe
ITF
can
work
more
close
with
other
as
deal
with
other
organization
to
to
to
solve
the
challenge.
Okay,
we
are
we
talk
about
her
I
talk
a
lot
about
the
architect
in
a
technology
about
the
autonomous
network
and,
frankly,
speaking,
I
think
we
think
it
is
a
long
journey
to
achieve
the
autonomous
network
we
just
in
the
in
the
initial
state
so
based
on
our
way.
We
stink
sauce
just
likes
our
automatic
driver.
B
We
try
to.
We
try
to
define
the
maturity
level,
a
suggestion
to
evaluate
each
and
to
evaluate
the
autonomous
network
from
the
level
0
to
the
level
5.
There
are
some
detail,
information
about
it,
but
even
a
summarized,
just
like
a
human
being
I
think
wheezing
way
things
they
are.
There
are
three
through
a
capability
table
is
a
very
into
the
first
hand
to
execute
that
do
something,
and
the
second
is
the
IO
or
a
year
to
gather
information
of
the
world
and
the
first
third
ISM,
and
so
we
we
use
this.
B
These
ideas
to
think
about
the
autonomous
and
network
to
maybe
is
in
the
inner,
in
the
first
phrase,
to
realize
the
automation
and
the
next
step.
Maybe
we
have
realized,
we
can
I
mean
we
can
have
a
more
or
have
a
have,
a
most
drunkle
ability
to
avoid
environment
and
the
based
on
the
autumn
execution
and
their
Wireless
of
the
network.
We
can
establish
the
intelligent
to
realize
the
closed
loop
and
and
the
to
realize
the
autonomous
and
that
work
in
the
future.
Okay.
This
is
this
is
okay.
B
The
last
part
is
a
summarized
about
about
my
presentation:
I
think.
Maybe
there
are
three
well
I
mentioned.
It's
really
major
topic.
The
first
is
D
Cobbing
network
transportation
and
services,
so
a
second
is
D
covering
the
network
operation
and
the
service
IT
system.
The
third
is
the
closed
loop
control
to
realize
the
autonomous
and
AI
in
in
a
network.
So
I
always
think
who
is
there
a
lot
of
what
we
need
to
do
to
realize
the
the
autonomous
network
thanks
everyone.