Advances in computational intelligence and robotics book series,
Journal Year:
2025,
Volume and Issue:
unknown, P. 435 - 478
Published: Feb. 28, 2025
The
rapid
evolution
of
Artificial
Intelligence
(AI)
has
significantly
impacted
the
software
development
lifecycle
(SDLC),
introducing
tools
that
enhance
efficiency,
accuracy,
and
innovation.
This
chapter
examines
integration
AI-powered
across
SDLC
stages,
including
planning,
design,
coding,
testing,
deployment,
maintenance.
AI
automates
tasks
like
code
generation,
bug
detection,
test
case
creation,
reducing
errors
accelerating
development.
It
also
enhances
decision-making,
fosters
team
collaboration,
optimizes
resources
through
predictive
analytics
intelligent
project
management
tools.
highlights
AI's
role
in
quality
improvement,
using
machine
learning
to
detect
anomalies
predict
failures
early.
Ethical
security
challenges
are
addressed,
stressing
responsible
use
human
oversight.
By
chapter's
end,
readers
will
understand
how
reshape
development,
enabling
creation
robust,
scalable,
user-friendly
applications
while
navigating
ethical
effectively.
IEEE Transactions on Services Computing,
Journal Year:
2022,
Volume and Issue:
16(2), P. 1505 - 1521
Published: May 11, 2022
Recently,
fog
computing
has
been
introduced
as
a
modern
distributed
paradigm
and
complement
to
cloud
provide
services.
The
system
extends
storing
the
edge
of
network,
which
can
remarkably
solve
problem
service
in
delay-sensitive
applications
besides
enabling
location
awareness
mobility
support.
Load
balancing
is
an
important
aspect
networks
that
avoids
situation
with
some
under-loaded
or
overloaded
nodes.
Quality
parameters
such
resource
utilization,
throughput,
cost,
response
time,
performance,
energy
consumption
be
improved
by
load
balancing.
In
recent
years,
research
algorithms
carried
out,
but
there
no
systematic
study
consolidate
these
works.
This
article
investigates
load-balancing
systematically
four
classifications,
including
approximate,
exact,
fundamental,
hybrid
algorithms.
Also,
this
metrics
all
advantages
disadvantages
related
chosen
networks.
evaluation
techniques
tools
applied
for
each
reviewed
are
explored
well.
Additionally,
essential
open
challenges
future
trends
discussed.
IEEE Access,
Journal Year:
2023,
Volume and Issue:
11, P. 12555 - 12586
Published: Jan. 1, 2023
Fog
computing
has
emerged
as
a
paradigm
for
resource-restricted
Internet
of
things
(IoT)
devices
to
support
time-sensitive
and
computationally
intensive
applications.
Offloading
can
be
utilized
transfer
resource-intensive
tasks
from
resource-limited
end
resource-rich
fog
or
cloud
layer
reduce
end-to-end
latency
enhance
the
performance
system.
However,
this
advantage
is
still
challenging
achieve
in
systems
with
high
request
rate
because
it
leads
long
queues
nodes
reveals
inefficiencies
terms
delays.
In
regard,
reinforcement
learning
(RL)
well-known
method
addressing
such
decision-making
issues.
large-scale
wireless
networks,
both
action
state
spaces
are
complex
extremely
extensive.
Consequently,
techniques
may
not
able
identify
an
efficient
strategy
within
acceptable
time
frame.
Hence,
deep
(DRL)
was
developed
integrate
RL
(DL)
address
problem.
This
paper
presents
systematic
analysis
using
DRL
algorithms
offloading-related
issues
computing.
First,
taxonomy
offloading
mechanisms
based
on
divided
into
three
major
categories:
value-based,
policy-based,
hybrid-based
algorithms.
These
categories
were
then
compared
important
features,
including
problem
formulation,
techniques,
metrics,
evaluation
tools,
case
studies,
their
strengths
drawbacks,
directions,
mode,
SDN-based
architecture,
decisions.
Finally,
future
research
directions
open
discussed
thoroughly.
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 39058 - 39080
Published: Jan. 1, 2024
The
proliferation
of
Internet
Things
(IoT)
devices
and
other
IT
forms
in
almost
every
area
human
existence
has
resulted
an
enormous
influx
data
that
must
be
managed
stored.
One
viable
solution
to
this
issue
is
store
handle
massive
amounts
cloud
environments.
Real-time
analysis
always
been
critical.
However,
it
becomes
even
more
crucial
as
technology
the
IoT
develop,
new
applications
emerge,
such
autonomous
cars,
smart
cities,
for
healthcare,
agriculture,
industries.
Given
volume
data,
moving
a
remote
time-consuming
produces
severe
network
congestion,
rendering
administration
rapid
processing
difficult.
Fog
computing
provides
close-to-device
at
network's
periphery,
fog
can
analyze
near
real-time.
increased
amount
gadgets
they
produce
formidable
challenge
nodes.
Task
offloading
may
enhance
by
excess
nodes
due
restricted
resources
fog.
Management
tasks
optimized
devices.
This
review
article
overviews
related
works
on
task
IoT-Fog-Cloud
Environment.
In
addition,
we
discuss
about
networks
Software-defined
(SDN)
challenges
offloading.
IEEE Access,
Journal Year:
2024,
Volume and Issue:
12, P. 39936 - 39952
Published: Jan. 1, 2024
This
paper
presents
a
novel
offloading
technique
designed
to
enhance
the
efficiency
of
Internet
Things
(IoT)
applications
within
sophisticated
three-layer
architecture
situated
in
fog
computing
environment.
The
IoT
layer
contains
various
intelligent
devices
that
generate
large
number
tasks,
each
characterized
by
distinct
specifications
such
as
size,
computational
demand,
communication
requirements,
and
latency
constraints.
owing
limited
storage
capacity
resource-constrained
devices,
it
is
essential
offload
these
tasks
different
layers
ensure
effective
processing
while
satisfying
required
Quality
Service
(QoS)
goals.
To
address
this
challenge,
fuzzy
logic-based
task
scheduler
employed
make
informed
decisions,
considering
attributes
determining
most
suitable
layers—whether
locally
at
layer,
on
collaborative
nodes,
or
cloud.
Furthermore,
study
leverages
Deep
Q
Network
(DQN)
method,
form
deep
reinforcement
learning,
identify
optimal
node
for
maintain
balanced
workload
distribution
across
nodes.
experimental
findings
demonstrate
proposed
scheme
outperforms
state-of-the-art
solutions
terms
latency,
power
consumption,
network
usage,
throughput,
rate
comparison
with
Non-offload,
First-Fit,
GASDEO,
NAFITO-FLA
methods.
