Journal of Cloud Computing Advances Systems and Applications,
Год журнала:
2022,
Номер
11(1)
Опубликована: Дек. 3, 2022
Abstract
Allocating
resources
is
crucial
in
large-scale
distributed
computing,
as
networks
of
computers
tackle
difficult
optimization
problems.
Within
the
scope
this
discussion,
objective
resource
allocation
to
achieve
maximum
overall
computing
efficiency
or
throughput.
Cloud
not
same
grid
which
a
version
physically
separate
clusters
are
networked
and
made
accessible
public.
Because
wide
variety
application
workloads,
allocating
multiple
virtualized
information
communication
technology
within
cloud
paradigm
can
be
problematic
challenge.
This
research
focused
on
implementation
an
LSTM
algorithm
provided
intuitive
dynamic
system
that
analyses
heuristics
utilization
ascertain
best
extra
provide
for
application.
The
software
solution
was
simulated
near
real-time,
allocated
by
trained
model.
There
discussion
benefits
integrating
these
with
routing
algorithms,
designed
specifically
data
centre
traffic.
Both
Long-Short
Term
Memory
Monte
Carlo
Tree
Search
have
been
investigated,
their
various
efficiencies
compared
one
another.
Consistent
traffic
patterns
throughout
simulation
were
shown
improve
MCTS
performance.
A
situation
like
usually
impossible
put
into
practice
due
rapidity
shift.
On
other
hand,
it
verified
employing
LSTM,
problem
could
solved,
acceptable
SLA
achieved.
proposed
model
load
balancing
techniques
allocation.
Based
result,
shows
accuracy
rate
enhanced
approximately
10–15%
models.
result
reduces
error
percent
average
request
blocking
probability
9.5–10.2%
different
means
technique
improves
network
usage
taking
less
amount
time
due,
memory,
central
processing
unit
good
predictive
approach
In
future
research,
we
implement
machine
learning
approaches
energy
using
firefly
algorithms.
Neurocomputing,
Год журнала:
2023,
Номер
545, С. 126327 - 126327
Опубликована: Май 15, 2023
Deep
neural
networks
(DNNs)
are
currently
being
deployed
as
machine
learning
technology
in
a
wide
range
of
important
real-world
applications.
DNNs
consist
huge
number
parameters
that
require
millions
floating-point
operations
(FLOPs)
to
be
executed
both
and
prediction
modes.
A
more
effective
method
is
implement
cloud
computing
system
equipped
with
centralized
servers
data
storage
sub-systems
high-speed
high-performance
capabilities.
This
paper
presents
an
up-to-date
survey
on
current
state-of-the-art
for
computing.
Various
DNN
complexities
associated
different
architectures
presented
discussed
alongside
the
necessities
using
We
also
present
extensive
overview
platforms
deployment
discuss
them
detail.
Moreover,
applications
already
systems
reviewed
demonstrate
advantages
DNNs.
The
emphasizes
challenges
deploying
provides
guidance
enhancing
new
deployments.
Journal of Imaging,
Год журнала:
2023,
Номер
9(10), С. 207 - 207
Опубликована: Сен. 30, 2023
The
growth
in
the
volume
of
data
generated,
consumed,
and
stored,
which
is
estimated
to
exceed
180
zettabytes
2025,
represents
a
major
challenge
both
for
organizations
society
general.
In
addition
being
larger,
datasets
are
increasingly
complex,
bringing
new
theoretical
computational
challenges.
Alongside
this
evolution,
science
tools
have
exploded
popularity
over
past
two
decades
due
their
myriad
applications
when
dealing
with
complex
data,
high
accuracy,
flexible
customization,
excellent
adaptability.
When
it
comes
images,
analysis
presents
additional
challenges
because
as
quality
an
image
increases,
desirable,
so
does
be
processed.
Although
classic
machine
learning
(ML)
techniques
still
widely
used
different
research
fields
industries,
there
has
been
great
interest
from
scientific
community
development
artificial
intelligence
(AI)
techniques.
resurgence
neural
networks
boosted
remarkable
advances
areas
such
understanding
processing
images.
study,
we
conducted
comprehensive
survey
regarding
AI
design
optimization
solutions
proposed
deal
Despite
good
results
that
achieved,
many
face
field
study.
work,
discuss
main
more
recent
improvements,
applications,
developments
targeting
propose
future
directions
constant
fast
evolution.
Artificial Intelligence Review,
Год журнала:
2024,
Номер
57(5)
Опубликована: Апрель 23, 2024
Abstract
With
the
acceleration
of
Internet
in
Web
2.0,
Cloud
computing
is
a
new
paradigm
to
offer
dynamic,
reliable
and
elastic
services.
Efficient
scheduling
resources
or
optimal
allocation
requests
one
prominent
issues
emerging
computing.
Considering
growing
complexity
computing,
future
systems
will
require
more
effective
resource
management
methods.
In
some
complex
scenarios
with
difficulties
directly
evaluating
performance
solutions,
classic
algorithms
(such
as
heuristics
meta-heuristics)
fail
obtain
an
scheme.
Deep
reinforcement
learning
(DRL)
novel
method
solve
problems.
Due
combination
deep
(RL),
DRL
has
achieved
considerable
current
studies.
To
focus
on
this
direction
analyze
application
prospect
scheduling,
we
provide
comprehensive
review
for
DRL-based
methods
Through
theoretical
formulation
analysis
RL
frameworks,
discuss
advantages
scheduling.
We
also
highlight
different
challenges
directions
existing
Comprehensive Reviews in Food Science and Food Safety,
Год журнала:
2023,
Номер
22(6), С. 4378 - 4403
Опубликована: Авг. 21, 2023
Abstract
The
egg
is
considered
one
of
the
best
sources
dietary
protein,
and
has
an
important
role
in
human
growth
development.
With
increase
world's
population,
per
capita
consumption
also
increasing.
Ground‐breaking
technological
developments
have
led
to
numerous
inventions
like
Internet
Things
(IoT),
various
optical
sensors,
robotics,
artificial
intelligence
(AI),
big
data,
cloud
computing,
transforming
conventional
industry
into
a
smart
sustainable
industry,
known
as
Egg
Industry
4.0
(EI
4.0).
EI
concept
potential
improve
automation,
enhance
biosecurity,
promote
safeguarding
animal
welfare,
intelligent
grading
quality
inspection,
efficiency.
For
transformation,
it
analyze
available
technologies,
latest
research,
existing
limitations,
prospects.
This
review
examines
non‐destructive
sensing
technologies
for
industry.
It
provides
information
insights
on
different
components
4.0,
including
emerging
production,
grading.
Furthermore,
drawbacks
current
workarounds,
future
trends
were
critically
analyzed.
can
help
policymakers,
industrialists,
academicians
better
understand
integration
automation.
productivity,
control,
optimize
resource
management
toward
development
