In
view
of
the
disadvantages
traditional
competitive
swarm
optimizer
(CSO),
such
as
falling
into
local
minimization
or
poor
convergence
accuracy,
this
paper
proposed
an
enhanced
CSO
algorithm
called
based
on
individual
learning
mechanism
(ILCSO).
Firstly,
selection
rate
and
are
designed
to
dynamically
select
winner
loser.
The
losers
updated
by
precise
strategy
improve
exploitation
ability.
Secondly,
mutation
performance
improvement
is
introduced,
which
improves
search
ability
algorithm.
effectively
balances
global
exploration
with
mechanism,
probability
finding
optimal
solution.
Finally,
ILCSO
compared
six
classical
meta-heuristic
algorithms
CEC2014
benchmark
functions.
Wilcoxon
rank-sum
test
used
demonstrate
that
effective.
Experimental
results
statistical
analysis
show
has
higher
speed
accuracy.
Transactions on Emerging Telecommunications Technologies,
Journal Year:
2025,
Volume and Issue:
36(2)
Published: Jan. 24, 2025
ABSTRACT
Internet
of
Things
(IoT)
devices
is
extensively
employed
to
collect
physiological
health
data
and
provide
diverse
services
end‐users.
Nevertheless,
in
recent
applications,
cloud
computing‐based
IoT
proves
beneficial
for
standard
storage
ensuring
high‐security
information
sharing.
Due
limitations
battery
capacity,
storage,
computing
power,
are
often
considered
resource‐constrained.
Consequently,
signing
by
devices,
aimed
at
integrity
authentication,
typically
demands
significant
computational
resources.
Unsafe
high
latency
as
the
major
issues
IoT‐based
mechanism
duplicating
misusing
while
it
stored
database.
Hence,
blockchain
technologies
needed
security
over
data.
research
implement
an
efficient
blockchain‐based
system
mobile
edge
computing,
safeguarding
from
unauthorized
access.
In
this
approach,
contains
four
layers
that
layer,
entity
block‐chain
layer.
The
user's
optimal
location
where
storing
find
out
using
proposed
Hybrid
Battle
Royale
with
Archimedes
Optimization
Algorithm
(HBRAOA).
key‐based
homomorphic
encryption
algorithm
Elliptic
Curve
Cryptography
(ECC)
introduced
encrypt
most
key,
secure
storage.
This
method
leverages
same
HBRAOA
enhance
efficiency.
Next,
digital
signature
demonstrated
give
authorization
user,
distributed
Thus,
indexes
shared
layer
avoid
fault
tolerance
tamper‐proofing.
Finally,
receives
valuable
encrypted
data,
authenticated
users
known
keys
able
access
decrypting
them.
result
analysis
shows
performance
developed
model,
which
attains
27%,
98%,
35%,
18%
enhanced
than
Particle
Swarm
(PSO)‐ECC,
Black
Widow
(BWO)‐ECC,
(BRO)‐ECC
(AOA)‐ECC.
efficiency
scheme
optimization
strategy
validated
conducting
several
similarity
measures
conventional
methods.
Applied Mathematics and Nonlinear Sciences,
Journal Year:
2025,
Volume and Issue:
10(1)
Published: Jan. 1, 2025
Abstract
With
the
rapid
development
of
Internet
Things
(IoT)
technology
and
riguidinguting,
power
system
is
undergoing
unprecedented
changes.
Traditional
management
mainly
relies
on
centralized
data
processing
mode,
which
makes
it
challenging
to
meet
demand
when
volume
increases
rapidly
real-time
requirements
are
high.
This
paper
proposes
a
big
algorithm
based
edge
computing
IoT,
aiming
at
perception
response
optimization
problem
resource
potential
user
side.
The
aims
improve
operational
efficiency
reliability
through
analysis
while
reducing
energy
consumption
cost.
combines
IoT
technology,
computing,
extensive
methods
collect
usage
in
by
deploying
intelligent
sensing
devices
side
conducting
preliminary
nodes.
uses
machine
learning
algorithms
deeply
analyze
data,
identify
user-side
resources,
automatically
adjust
strategy
according
results
achieve
optimal
allocation
resources.
By
setting
up
simulation
environment,
proposed
tested.
Experimental
show
that
can
effectively
resources
realize
dynamic
balance
optimizing
strategy.
In
comparative
experiments,
compared
with
traditional
methods,
this
reduce
about
20%
15%.
Concurrency and Computation Practice and Experience,
Journal Year:
2025,
Volume and Issue:
37(6-8)
Published: March 13, 2025
ABSTRACT
Edge
computing
offers
crucial
computational
and
storage
support
to
vehicles
by
providing
various
services
within
the
framework
of
Internet
Vehicles
in
intelligent
transportation
systems.
Service
placement
(SP)
becomes
particularly
challenging
when
edge
resources
are
limited
exhibit
high‐mobility.
Many
current
dynamic
methods
rely
on
real‐time
placement,
often
leading
increased
costs,
instability,
frequent
changes.
This
paper
proposes
SACRF‐SP,
an
adaptive
service
algorithm
based
Soft
Actor‐Critic
(SAC)
Random
Forest
(RF),
for
urban
traffic
scenarios.
utilizes
SAC
method
identify
optimal
nodes
integrates
RF
model
predict
request
trends.
A
decision
network
is
constructed
assess
necessity
redeployment.
Extensive
simulation
experiments
demonstrate
that
SACRF‐SP
significantly
reduces
latency,
resource
usage,
frequency
