SlideShare a Scribd company logo
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
Parallel Particle Swarm Optimization for Reducing
Data Redundancy in Heterogeneous Cloud Storage
M.Vidhya1
Mr.N.Sadhasivam2
,
1
Department of Computer Science and Engineering, 2
Department of Computer Science and Engineering,
Bannari Amman Institute of Technology, Bannari Amman Institute of Technology,
Sathyamangalam . Sathyamangalam.
vidhyam284@gmail.com sadhasivamn82@gmail.com
Abstract— Cloud storage is usually distributed infrastructure, where data is not stored in a single device but is spread to
several storage nodes which are located in different areas. To ensure data availability some amount of redundancy has to
be maintained. But introduction of data redundancy leads to additional costs such as extra storage space and
communication bandwidth which required for restoring data blocks. In the existing system, the storage infrastructure is
considered as homogeneous where all nodes in the system have same online availability which leads to efficiency losses.
The proposed system considers that distributed storage system is heterogeneous where each node exhibit different online
availability. Monte Carlo Sampling is used to measure the online availability of storage nodes. The parallel version of
Particle Swarm Optimization is used to assign redundant data blocks according to their online availability. The optimal
data assignment policy reduces the redundancy and their associated cost.
Index Terms— cloud storage, data redundancy, online availability, optimal data assignment, particle swarm optimization
——————————  ——————————
1 INTRODUCTION
LOUD storage systems are built upon storage resources from
different computers or different dedicated storage devices to
build a large storage service which provides more reliable,
scalable and efficient storage service. The cloud storage services
such as Amsazon, Facebook, Gmail use distributed storage systems.
The cloud service providers render small capacity of storage for free
and additional storage capacity for pay on monthly or annual basis.
The cloud service providers and the users agreed upon the service
level agreement which provide the quality of service measures such
as response time, data availability, data reliability and reasonable
costs. The amount of data that is replicated depends on the service
level a customer chooses.
In the storage system the redundancy is maintained to ensure
data availability. The two mechanisms to maintain data redundancy
are replication and erasure coding. In replication mechanism, the
entire file is stored multiple times in different storage nodes which
increases the storage space for which the user have to pay additional
costs. When the storage node fails, the entire file has to be
transmitted to restore the lost data over the communication links
which cause additional communication costs. Another mechanism is
erasure coding in which the data file is divided into fixed number of
data blocks which are further encoded into number of redundant
blocks. The cloud storage system uses the (k, n) erasure code where
the file is divided into k data blocks which are encoded into n
redundant blocks. At any time k redundant blocks are enough to
construct original file.
IJTET©2015
The storage system consists of set of storage nodes N. At any
time the set of nodes M is chosen from N which is a random sample
of N to store data blocks. In the set of nodes M, there may be some
nodes available and some may not be available. By monitoring every
node in the system for longer period of time, the mean node
availability is calculated which is based on how much time the node
active on the network.
The data assignment function is used to assign redundant data
blocks to set of storage nodes based on their online availability. the
number of possible combinations to assign redundant data blocks is
computationally hard for large scale storage systems. to solve such
large scale combinatorial problems, the heuristic algorithms are used.
The optimization algorithm works by defining the search space and
to maximize the specified function. There are numerous algorithms
available but particle swarm optimization is proved to have better
performance for distributed environment. The computational speed
of particle swarm optimization algorithm is faster compared to other
evolutionary techniques such as genetic algorithm. The PSO
algorithm is easy to implement because it has few parameters and
convergence speed is faster.
The particle swarm optimization algorithm may suffer from
premature convergence that is the chance of falling into local
optimum is higher. The algorithm falls into local optimum due to
loss of diversity in population because each particle updates and
follows the single global best particle. If the particle falls into local
optimum, then the algorithm can‘t overcome from the local best
73
C
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
solution. So to overcome such problems the parallel version of
particle swarm optimization algorithm is used. In this the entire
population is divided into subgroups and each subgroup performs
independently for some time. After some time interval, the best of
each swarm is chosen to find the best particle which has maximum
value. Based on that value, all particles update their position. Here
the convergence rate of the algorithm is improved because the
particles moved towards the global best particle which is the best of
all the sub swarms. But when the convergence rate is reduced, the
algorithm‘s computational speed also gets reduced. Here all the sub
swarms are independent. So they are executed in parallel on different
machines which improve the computational time.
The optimal data redundancy is the minimum amount of
redundancy required to the data availability for accessing data at any
time. The redundancy ratio decides how many times the data blocks
are replicated. The value of redundancy ratio should be low to keep
minimum redundancy.
2 RELATED WORK
Cloud storage services have obtained importance in the recent years
[1, 6, 7, 23]. These services allow users to store data outside of their
storage infrastructure. To store large amounts of data from millions
of users, cloud storage systems build their services over distributed
storage infrastructures that are more scalable and reliable than
centralized storage systems. Different works have proposed
distributed data storage infrastructures, some of which built on grid
infrastructures [1, 7], and some others built on P2P networks [20]. To
achieve the required data availability, all the storage systems need to
store data with redundancy. But the use of redundancy also increases
storage and communication costs. To maintain the storage system
accessible, the redundancy has to be reduced.
The peer-to-peer (P2P) storage system such as Wuala [21] allows
users to share part of their hard drives to obtain a reliable and online
storage capacity. Chandra and Weissman [5] proposed the idea of
letting users to contribute their unused storage resources to satisfy
the storage requirements of these research projects. A similar
approach was advocated by the developers of Open Cirrus [4] to
aggregate unused resources from different small and heterogeneous
datacenters.
The existing storage solutions treat all nodes in the system are
equal and they have same online availability. But the nodes in
distributed storage infrastructure are heterogeneous. They exhibit
different online availabilities. So the proposed system uses
heterogeneity to calculate data availability, the Particle Swarm
Optimization algorithm is used to place redundant data blocks
according to node‘s availability and minimum data redundancy is
obtained that satisfies the targeted availability.
By reducing redundancy, distributed storage systems can reduce
storage and communication costs. In [2], Blakes and Fodrigues
described a limit beyond which communication costs cannot be
reduced without increasing storage costs and the reverse is also true.
The data redundancy schemes [17, 22, 23] provide better
communication-storage trade-offs. Unfortunately, all these works
have assumed homogeneous properties for all the storage nodes in
the system.
IJTET©2015
The main objective of this paper is to optimize distributed
storage systems by considering the real heterogeneities present in
cloud [4] systems, or any other existing distributed systems. In [7],
Deng and Wang considered node heterogeneities in grid storage
systems. However, they did not use such heterogeneities to reduce
the amount of data redundancy required. In [15], Pamies-Juarez et al.
describe heterogeneities using simple heuristic approaches to reduce
data redundancy. In [16], Pamies-Juarez et al. provided the method to
calculate data availability for any scale of storage system and use
optimization method to assign data blocks to set of nodes. They
provide the simple measure to find optimal data redundancy. In [11],
Gonsalves & Egashira describes the parallel version of PSO
algorithm without introducing any complexity. In this paper, the
parallel version of algorithm is used to improve the data availability
and to reduce the data redundancy of nodes compared to standard
Particle Swarm Optimization algorithm.
3 PROBLEM DESCRIPTION
In distributed storage system in order to maintain data availability
some amount of redundancy has to be maintained .But introducing
redundancy leads to additional storage and communication costs. So
the need for effective redundancy scheme is required which balances
the both data availability and its associated costs. In literature [9, 14,
17, 20], the erasure codes are proved to provide better redundancy
for distributed storage systems. To improve data availability the data
objects should be stored in high reliable nodes. To calculate node‘s
availability for any scale Monte Carlo Sampling method is used.
The existing system use Particle Swarm Optimization algorithm
to assign data blocks to different nodes based on their availability. In
original PSO, each particle updates its position based on its personal
best and the global best. Here the global best is the best of entire
swarm. All the particles in the swarm are moved towards on single
position called global best. So the algorithm converges faster which
is called premature convergence leads to poor performance. That is
the algorithm fails to find a global optimal solution or even
sometimes best local optimal solution. This has occurred due to
decline of population diversity. When the algorithm parameters are
not tuned properly there is a chance of falling in the local optima. In
general, maintaining diversity will reduce convergence rate which is
used to remove swarm stagnation in a poor local optimal solutions.
To overcome such problems a parallel approach called Parallel
Particle Swarm Optimization is used.
4 REDUCING DATA REDUNDANCY USING
PARTICLE SWARM OPTIMIZATION
4.1 Monte Carlo method to measure data availability
Data availability is referred as the degree to which data can be
instantly accessed. The term is specified in service level agreements
of cloud storage provider. In distributed storage infrastructure, data
availability is defined as the possibility of detecting k blocks out of
the n redundant blocks so that erasure codes construct original data
object from k redundant blocks. In [14], Lluis et al. defined the data
availability d, as a function D (k, n, g, N) which relies on erasure
74
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
code parameters k and n, the data assignment function g and the set
of nodes N.
Monte Carlo Sampling technique is used to measure the data
availability of storage system in heterogeneous distributed
infrastructure. The distributed storage system consists of N nodes. So
there are
N
2 possible combinations to store n redundant blocks. The
data assignment function g assigns n redundant blocks to storage
nodes based on their online availability.
4.2 Steps to measure data availability
a) The set VS of V samples is taken from
N
2 (i.e. VS 
N
2 ) randomly
b) The set A is the combination which together store k or
more redundant data blocks is selected from VS samples
(i.e. A VS ) based on individual node‘s availability
c) The data availability Vd is measured by average of number
of samples together store k or more redundant blocks to
number of samples taken from
N
2 i.e. 






V
A
dV
4.3 Data assignment using particle swarm optimization
The data assignment function is used to assign redundant data blocks
to set of storage nodes based on their online availability. The number
of possible combinations to assign redundant data blocks is
computationally hard for large scale storage systems. To solve best
assignment of redundant blocks to storage nodes which maximizes
the data availability, the Particle Swarm Optimization algorithm is
used. The PSO is proved to be very efficient in distributed
environment for performance. Optimization algorithms work by
defining the workspace and to maximize the specified function. The
search space is the set of possible combinations of storage nodes and
the function to be maximized is data availability.
4.4 Algorithm for PSO
a) Initialize the swarm from the solution space that is
randomly distributing n redundant blocks to set of storage
nodes N
b) Evaluate the fitness function data availability d=(D, n, k, g)
c) Update individual and global bests
d) Update velocity and position of particles
The velocity is given by
)(11
1 t
ii
t
i
t
i XlbestrcwVV 
)(22
t
iXgbestrc  (1)
Here w is the inertia weight, 1r and 2r are random variables
IJTET©2015
between [0, 1] and 1c , 2c are acceleration constants.
The position is given by
11 
 t
i
t
i
t
i VXX
(2)
e) The step b is performed until the minimum data availability
is met.
4.5 Finding optimal data redundancy
The optimal data redundancy is minimum data redundancy that is
required to satisfy required data availability dˆ . The required data
availability is taken as some nine‘s such as 0.9, 0.99, 0.9999 etc. The
redundancy ratio r =
n
k
which satisfies the minimum data
availability is the optimal data redundancy. To find optimal
redundancy r, the n value is fixed (i.e. n=|N|. β for large β) and the k
value is changed from k=n to 1.
4.6 Algorithm for finding r
a) Set k=|N|
b) Calculate data availability D(n, k, g, N)
c) while D(n ,k, g, N) < dˆ and k≠0
d) k=k-1
e) end while
5 PARALLEL PARTICLE SWARM OPTIMIZATION
ALGORITHM FOR DATA ASSIGNMENT
FUNCTION
The existing system uses PSO algorithm for data assignment
function but the original PSO algorithm suffers from premature
convergence and it can‘t suitable for parallel operation. The parallel
version of particle swarm optimization algorithm divides the
population into sub-population and applies the algorithm
individually to these sub-populations to reduce computation time.
5.1 Algorithm for PPSO
a) Divide the population into k independent swarms randomly
and initialize the individual swarm
b) The fitness function of each independent swarm is
evaluated
c) The particle best and the swarm best of individual swarm is
determined
d) The velocity and position of each particle in every swarm
is updated
e) The steps 2 through 4 is repeated for N iterations
75
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
f) The global best is determined by comparing the swarm best
of all the swarms. The fitness function data availability
should be maximized for the global best. It is specified by
the following equation
,,max( 21 sbestsbestgbest 
),...,3 ksbestsbest
(3)
g) The independent swarms are interacted using gbest value.
The velocities of particles are updated according to the
following equation
)1()( ,,  twvtv jiji
))1()1(( ,,11  txtprc jiji
))1()1(( ,,22  txtprc jijs
(4)
))1()1(( ,,33  txtprc jijg
where jix , is the position of ith particle in jth swarm, jiv ,
is the velocity of ith particle in jth swarm, jip , is the pbest
of ith particle in jth swarm, jsp , is the swarm best of jth
swarm, gp is the global best among all the sub-
swarms, 1c , 2c , 3c are acceleration parameters and
1r , 2r , 3r are the random variables.
h) The position of all the particles are updated according to
the following equation
)()1()( ,,, tvtxtx jijiji  (5)
i) The steps 2 to 8 are repeated for M iterations and the output
is the best optimal assignment of data blocks
6 EXPERIMENTAL RESULTS
6.1 Parameter Settings
The number of particles is 120 and the maximum number of
iterations is 50. The acceleration parameters for PSO is 1c , 2c =1
and the inertia weight parameter value for both PSO and PPSO is
0.7. The number of subgroups for parallel particle swarm
optimization algorithm is 8. The acceleration parameters for parallel
particle swarm optimization algorithm are 1c =1, 2c =1 and 3c =1.
The fitness function is data availability d= (D, k, n, g) which must
meet the minimum data availability dˆ = {0.9, 0.99, 0.999}.
6.2 Performance Metrics
a) Speedup
It is the measure used to compute the ratio between the average
IJTET©2015
execution time on single processor ][ 1tA and the average execution
time on multiple processors ][ ktA .The speedup due to k processors
is defined by
][
][ 1
k
k
tA
tA
S  (6)
TABLE 1
COMPARISON OF EXECUTION TIMES OF BOTH PSO AND
PPSO
Here the k value chosen is 8. The execution times of both PSO
and PPSO are shown in the table 1. The speedup of Parallel Particle
Swarm Optimization is 3.2 times faster than original Particle Swarm
Optimization.
b) Efficiency
The efficiency is defined as the percentage of speedup caused by k
processors. It is given by
%100*
k
S
E k
k 
(7)
From the experiments the Parallel Particle Swarm Optimization
algorithm is 40% efficient than Particle Swarm Optimization
algorithm. The results prove that the parallel version of particle
swarm optimization algorithm is efficient for data assignment
function in distributed cloud storage which reduces the computation
time of data assignment function.
6.3 Redundancy savings
Redundancy Saving Ratio (RSR) is the metric used to measure the
redundancy savings caused by distributed heterogeneous
environment instead of homogeneous environment.
The data redundancies orhom and heteror are caused by
76
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
homogeneous and heterogeneous storage systems. The Redundancy
Saving Ratio is defined as
100*1 hom







hetero
o
r
r
RSR
(8)
TABLE 2
THE REDUNDANCY SAVING RATIOS OF REAL
AVAILABILITY DATASETS
The number of storage nodes is 100. The fixed value for redundant
blocks is n=100.|N| (i.e. β=100). The homogeneous environment
uses unitary assignment function that is each block gets exactly one
block. The heterogeneous environment uses parallel particle swarm
optimization algorithm to assign data blocks to nodes based on their
online availabilities. The four real time availability datasets are used
for the experiments. The availability datasets are Planetlab nodes
[19], Skype super-nodes [10], Microsoft desktop PCs [3], and Seti@-
Home‘s desktop grid nodes[18]
The results from table 2 shows that the redundancy savings are
high for highly heterogeneous environments
7 CONCLUSION AND FUTURE WORK
The proposed system uses parallel version of particle swarm
optimization which reduces the computation time of the algorithm.
The parallel particle swarm optimization algorithm assigns data
blocks according to their online availabilities. By considering
heterogeneous environment where each node have different online
availabilities, the data assignment function assigns data blocks
according to them. The redundancy savings are high almost 75% of
redundancies are removed which also reduce storage and
communication costs.
In the future work, the dynamic storage systems are considered.
In this the number of nodes and the number of stored objects are
continuously changed. To reduce redundancy for such environment a
new scheme is needed.
IJTET©2015
REFERENCES
[1] D. P. Anderson (2004), ‗Boinc: a system for public-resource
computing and storage‘, Proceedings of the 5th
IEEE/ACM
International Workshop on Grid Computing
[2] C. Blake & R. Rodrigues (2003), ‗High availability, scalable
storage, dynamic peer networks‘, Proceedings of the 9th
Workshop on Hot Topics in Operating Systems (HOTOS)
[3] W. J. Bolosky , J. R. Douceur, D. Ely & M. Theimer (2000),
―Feasibility of a serverless distributed file system deployed on
an existing set of desktop pcs‖, proceedings of the
International Conference on Measurement and Modeling of
Computer Systems ACM SIGMETRICS
[4] R. Campbell, I. Gupta, M. Heath, S. Y. Ko, M. Kozuch, M.
Kunze, T. Kwan, K. Lai, H.Y. Lee, M. Lyons, D. Milojicic, D.
O‘Hallaron & Y. C. Soh (2009), ‗ Open cirrus cloud
computing testbed: federated data centers for open source
systems and services research‘, Proceedings of the Usenix
Workshop on Hot Topics on Cloud Computing (HotCloud)
[5] A. Chandra & J. Weissman (2009), ‗ Nebulas: Using
distributed voluntary resources to build clouds‘, Proceedings
of the Usenix Workshop on Hot Topics on Cloud Computing
(HotCloud)
[6] CleverSafe, 2010, Cleversafe, http://www.cleversafe.com
[7] Y. Deng & F. Wang (2007), ‗A heterogeneous storage grid
enabled by grid service‘, Proceedings on Small Interest Group
on Operating Systems review (SIGOPS) , vol. 41, no. 1, pp.
7–13
[8] A. Dimakis, P. Godfrey, M. Wainwright & K. Ramchandran
(2007), ‗Network coding for distributed storage systems‘,
Proceedings of the 26th
IEEE International Conference on
Computer Communications
[9] A. Duminuco & E. W. Biersack (2008), ‗Hierarchical codes:
how to make erasure codes attractive for peer-to-peer storage
systems‘, Proceedings of the 8th International Conference on
Peer-to-Peer Computing (P2P)
[10] B. Godfrey, Repository of availability
traces,2010,<http://www.cs.berkeley.edu/pbg/availability/>
[11] T. Gonsalves & A. Egashira (2013), ―Parallel Swarms
Oriented Particle Swarm Optimization‖, Proceedings of
Applied Computational Intelligence and Soft Computing 2013
[12] J. Kennedy & R. Eberhart (1995), ‗Particle swarm
optimization‘, Proceedings of the IEEE International
Conference on Neural Networks
[13] J. Kubiatowicz, D. Bindel, Y. Chen, S. Czerwinski, P. Eaton,
D. Geels, R. Gummad, S. Rhea, H. Weatherspoon, W.
Weimer, C. Wells & B. Zhao (2000), ‗Oceanstore: an
architecture for global-scale persistent storage‘, Proceedings of
the 9th
International Conference on Architectural Support for
Programming Languages and Operating Systems (ASPLOS)
77
INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY
VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303
[14] W. K. Lin, D. M. Chiu & Y. B. Lee (2004), ‗Erasure code
replication revisited‘, Proceedings of the 4th
International
Conference on Peer-to-Peer Computing (P2P)
[15] P. Lluis, G. Pedro, S. Marc & H. Blas (2011), ‗Towards the
design of optimal data redundancy schemes for heterogeneous
cloud storage infrastructures‘, Journal of Elsevier, vol. 55, no.
5, pp. 1100–1113
[16] L. Pamies-Juarez, P. García-López & M. Sánchez-Artigas, M
(2009), ‗Heterogeneity-aware erasure codes for peer-to-peer
storage systems‘, Proceedings of the 38th
IEEE International
Conference on Parallel Processing (ICPP)
[17] R. Rodrigues & B. Liskov (2005), ‗High availability in dhts:
erasure coding vs replication‘, Proceedings of the 4th
International Workshop on Peer-To-Peer Systems (IPTPS)
[18] Standford.edu, Folding@home: distributing computing
project, 2009, <http://folding.stanford.edu>
[19] J. Stribling , Planetlab all pairs ping, 2010,
<http://infospect.planetlab.org/pings>
[20] H. Weatherspoon & J. D. Kubiatowicz (2002),‘Erasure coding
vs. replication: a quantitative comparison‘, Proceedings of the
1st
International Workshop on Peer-To-Peer Systems (IPTPS)
[21] WuaLa, 2010, Wuala, <http://www.wuala.com>.
[22] F. Wu, T. Qiu, Y. Chen & G. Chen (2005), ‗Redundancy
schemes for high availability in dhts‘, Proceedings of the 3rd
International Symposium on Parallel and Distributed
Processing and Applications (ISPA)
[23] Z. Zhang & Q. Lian (2002), ‗Reperasure: replication protocol
using erasure code in peer-to-peer storage network‘,
Proceedings of the 21st
Symposium on Reliable Distributed
Systems (SRDS)
IJTET©2015
78

More Related Content

What's hot

ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGEADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
ijdpsjournal
 
Cloud computing – partitioning algorithm
Cloud computing – partitioning algorithmCloud computing – partitioning algorithm
Cloud computing – partitioning algorithm
ijcseit
 
Ed33777782
Ed33777782Ed33777782
Ed33777782
IJERA Editor
 
Mobile data gathering with load balanced
Mobile data gathering with load balancedMobile data gathering with load balanced
Mobile data gathering with load balanced
jpstudcorner
 
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
ijasuc
 
Data Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
Data Dissemination in Wireless Sensor Networks: A State-of-the Art SurveyData Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
Data Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
CSCJournals
 
Mobile elements scheduling for periodic sensor applications
Mobile elements scheduling for periodic sensor applicationsMobile elements scheduling for periodic sensor applications
Mobile elements scheduling for periodic sensor applications
ijwmn
 
Real time eventual consistency
Real time eventual consistencyReal time eventual consistency
Real time eventual consistency
ijfcstjournal
 
Data gathering in wireless sensor networks using intermediate nodes
Data gathering in wireless sensor networks using intermediate nodesData gathering in wireless sensor networks using intermediate nodes
Data gathering in wireless sensor networks using intermediate nodes
IJCNCJournal
 
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
CSCJournals
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
IJERD Editor
 
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER WR...
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER  WR...AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER  WR...
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER WR...
Vijay Prime
 
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor NetworkA QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
ijassn
 
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENTDYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
IJCNCJournal
 
Peer to peer cache resolution mechanism for mobile ad hoc networks
Peer to peer cache resolution mechanism for mobile ad hoc networksPeer to peer cache resolution mechanism for mobile ad hoc networks
Peer to peer cache resolution mechanism for mobile ad hoc networks
ijwmn
 
3 3 energy efficient topology
3 3 energy efficient topology3 3 energy efficient topology
3 3 energy efficient topology
IAEME Publication
 

What's hot (16)

ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGEADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
ADVANCED DIFFUSION APPROACH TO DYNAMIC LOAD-BALANCING FOR CLOUD STORAGE
 
Cloud computing – partitioning algorithm
Cloud computing – partitioning algorithmCloud computing – partitioning algorithm
Cloud computing – partitioning algorithm
 
Ed33777782
Ed33777782Ed33777782
Ed33777782
 
Mobile data gathering with load balanced
Mobile data gathering with load balancedMobile data gathering with load balanced
Mobile data gathering with load balanced
 
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
A COST EFFECTIVE COMPRESSIVE DATA AGGREGATION TECHNIQUE FOR WIRELESS SENSOR N...
 
Data Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
Data Dissemination in Wireless Sensor Networks: A State-of-the Art SurveyData Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
Data Dissemination in Wireless Sensor Networks: A State-of-the Art Survey
 
Mobile elements scheduling for periodic sensor applications
Mobile elements scheduling for periodic sensor applicationsMobile elements scheduling for periodic sensor applications
Mobile elements scheduling for periodic sensor applications
 
Real time eventual consistency
Real time eventual consistencyReal time eventual consistency
Real time eventual consistency
 
Data gathering in wireless sensor networks using intermediate nodes
Data gathering in wireless sensor networks using intermediate nodesData gathering in wireless sensor networks using intermediate nodes
Data gathering in wireless sensor networks using intermediate nodes
 
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
Efficient Tree-based Aggregation and Processing Time for Wireless Sensor Netw...
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER WR...
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER  WR...AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER  WR...
AN ENERGY EFFICIENT L2 CACHE ARCHITECTURE USING WAY TAG INFORMATION UNDER WR...
 
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor NetworkA QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
A QoI Based Energy Efficient Clustering for Dense Wireless Sensor Network
 
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENTDYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
DYNAMIC TASK SCHEDULING BASED ON BURST TIME REQUIREMENT FOR CLOUD ENVIRONMENT
 
Peer to peer cache resolution mechanism for mobile ad hoc networks
Peer to peer cache resolution mechanism for mobile ad hoc networksPeer to peer cache resolution mechanism for mobile ad hoc networks
Peer to peer cache resolution mechanism for mobile ad hoc networks
 
3 3 energy efficient topology
3 3 energy efficient topology3 3 energy efficient topology
3 3 energy efficient topology
 

Viewers also liked

Periodic Auditing of Data in Cloud Using Random Bits
Periodic Auditing of Data in Cloud Using Random BitsPeriodic Auditing of Data in Cloud Using Random Bits
Periodic Auditing of Data in Cloud Using Random Bits
IJTET Journal
 
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
IJTET Journal
 
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
IJTET Journal
 
Manu’s Employee Estimating Device
Manu’s Employee Estimating DeviceManu’s Employee Estimating Device
Manu’s Employee Estimating Device
IJTET Journal
 
Network Lifetime Enhancement by Node Deployment in WSN
Network Lifetime Enhancement by Node Deployment in WSNNetwork Lifetime Enhancement by Node Deployment in WSN
Network Lifetime Enhancement by Node Deployment in WSN
IJTET Journal
 
Time Reduction and Upgrading of Balancing Machine for Impeller
Time Reduction and Upgrading of Balancing Machine for ImpellerTime Reduction and Upgrading of Balancing Machine for Impeller
Time Reduction and Upgrading of Balancing Machine for Impeller
IJTET Journal
 
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
IJTET Journal
 
An Efficient VLSI Design for Extracting Local Binary Pattern
An Efficient VLSI Design for Extracting Local Binary PatternAn Efficient VLSI Design for Extracting Local Binary Pattern
An Efficient VLSI Design for Extracting Local Binary Pattern
IJTET Journal
 
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
IJTET Journal
 
Comparative Study on Watermarking & Image Encryption for Secure Communication
Comparative Study on Watermarking & Image Encryption for Secure CommunicationComparative Study on Watermarking & Image Encryption for Secure Communication
Comparative Study on Watermarking & Image Encryption for Secure Communication
IJTET Journal
 
Biometrics Authentication Using Raspberry Pi
Biometrics Authentication Using Raspberry PiBiometrics Authentication Using Raspberry Pi
Biometrics Authentication Using Raspberry Pi
IJTET Journal
 
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
IJTET Journal
 
Enhanced Secure E-Gateway using Hierarchical Visual Cryptography
Enhanced Secure E-Gateway using Hierarchical Visual CryptographyEnhanced Secure E-Gateway using Hierarchical Visual Cryptography
Enhanced Secure E-Gateway using Hierarchical Visual Cryptography
IJTET Journal
 
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase System
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase SystemHarmonic Mitigation Method for the DC-AC Converter in a Single Phase System
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase System
IJTET Journal
 
Quality Prediction in Fingerprint Compression
Quality Prediction in Fingerprint CompressionQuality Prediction in Fingerprint Compression
Quality Prediction in Fingerprint Compression
IJTET Journal
 
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
IJTET Journal
 
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
IJTET Journal
 

Viewers also liked (17)

Periodic Auditing of Data in Cloud Using Random Bits
Periodic Auditing of Data in Cloud Using Random BitsPeriodic Auditing of Data in Cloud Using Random Bits
Periodic Auditing of Data in Cloud Using Random Bits
 
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
A Secure Cloud Storage System with Data Forwarding using Proxy Re-encryption ...
 
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
Enhancing energy efficient dynamic load balanced clustering protocol using Dy...
 
Manu’s Employee Estimating Device
Manu’s Employee Estimating DeviceManu’s Employee Estimating Device
Manu’s Employee Estimating Device
 
Network Lifetime Enhancement by Node Deployment in WSN
Network Lifetime Enhancement by Node Deployment in WSNNetwork Lifetime Enhancement by Node Deployment in WSN
Network Lifetime Enhancement by Node Deployment in WSN
 
Time Reduction and Upgrading of Balancing Machine for Impeller
Time Reduction and Upgrading of Balancing Machine for ImpellerTime Reduction and Upgrading of Balancing Machine for Impeller
Time Reduction and Upgrading of Balancing Machine for Impeller
 
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
Adaptive Circumstance Knowledgeable Trusted System for Security Enhancement i...
 
An Efficient VLSI Design for Extracting Local Binary Pattern
An Efficient VLSI Design for Extracting Local Binary PatternAn Efficient VLSI Design for Extracting Local Binary Pattern
An Efficient VLSI Design for Extracting Local Binary Pattern
 
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
Experimental Evaluation of Electronic Port Fuel Injection System in Four Stro...
 
Comparative Study on Watermarking & Image Encryption for Secure Communication
Comparative Study on Watermarking & Image Encryption for Secure CommunicationComparative Study on Watermarking & Image Encryption for Secure Communication
Comparative Study on Watermarking & Image Encryption for Secure Communication
 
Biometrics Authentication Using Raspberry Pi
Biometrics Authentication Using Raspberry PiBiometrics Authentication Using Raspberry Pi
Biometrics Authentication Using Raspberry Pi
 
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
Area Delay Power Efficient and Implementation of Modified Square-Root Carry S...
 
Enhanced Secure E-Gateway using Hierarchical Visual Cryptography
Enhanced Secure E-Gateway using Hierarchical Visual CryptographyEnhanced Secure E-Gateway using Hierarchical Visual Cryptography
Enhanced Secure E-Gateway using Hierarchical Visual Cryptography
 
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase System
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase SystemHarmonic Mitigation Method for the DC-AC Converter in a Single Phase System
Harmonic Mitigation Method for the DC-AC Converter in a Single Phase System
 
Quality Prediction in Fingerprint Compression
Quality Prediction in Fingerprint CompressionQuality Prediction in Fingerprint Compression
Quality Prediction in Fingerprint Compression
 
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
Efficient Design of Higher Order Variable Digital Filter for Multi Modulated ...
 
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
Flow Control Using Variable Frequency Drive In Water Treatment Process of Dei...
 

Similar to ICICCE0298

Ax34298305
Ax34298305Ax34298305
Ax34298305
IJERA Editor
 
IRJET- Improving Data Availability by using VPC Strategy in Cloud Environ...
IRJET-  	  Improving Data Availability by using VPC Strategy in Cloud Environ...IRJET-  	  Improving Data Availability by using VPC Strategy in Cloud Environ...
IRJET- Improving Data Availability by using VPC Strategy in Cloud Environ...
IRJET Journal
 
P2P Cache Resolution System for MANET
P2P Cache Resolution System for MANETP2P Cache Resolution System for MANET
P2P Cache Resolution System for MANET
IJCSIS Research Publications
 
A Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid SystemsA Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid Systems
Editor IJCATR
 
Ijcatr04071003
Ijcatr04071003Ijcatr04071003
Ijcatr04071003
Editor IJCATR
 
A Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid SystemsA Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid Systems
Editor IJCATR
 
Scalable and adaptive data replica placement for geo distributed cloud storages
Scalable and adaptive data replica placement for geo distributed cloud storagesScalable and adaptive data replica placement for geo distributed cloud storages
Scalable and adaptive data replica placement for geo distributed cloud storages
Venkat Projects
 
A novel cache resolution technique for cooperative caching in wireless mobile...
A novel cache resolution technique for cooperative caching in wireless mobile...A novel cache resolution technique for cooperative caching in wireless mobile...
A novel cache resolution technique for cooperative caching in wireless mobile...
csandit
 
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
cscpconf
 
Analyse the performance of mobile peer to Peer network using ant colony optim...
Analyse the performance of mobile peer to Peer network using ant colony optim...Analyse the performance of mobile peer to Peer network using ant colony optim...
Analyse the performance of mobile peer to Peer network using ant colony optim...
IJCI JOURNAL
 
E045026031
E045026031E045026031
E045026031
researchinventy
 
Data Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big DataData Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big Data
neirew J
 
Data Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big DataData Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big Data
ijccsa
 
Dynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy managementDynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy management
eSAT Publishing House
 
Dynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy managementDynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy management
eSAT Journals
 
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
acijjournal
 
Use of genetic algorithm for
Use of genetic algorithm forUse of genetic algorithm for
Use of genetic algorithm for
ijitjournal
 
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHMCLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
ijcseit
 
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHMCLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
ijcseit
 
Hm2413291336
Hm2413291336Hm2413291336
Hm2413291336
IJERA Editor
 

Similar to ICICCE0298 (20)

Ax34298305
Ax34298305Ax34298305
Ax34298305
 
IRJET- Improving Data Availability by using VPC Strategy in Cloud Environ...
IRJET-  	  Improving Data Availability by using VPC Strategy in Cloud Environ...IRJET-  	  Improving Data Availability by using VPC Strategy in Cloud Environ...
IRJET- Improving Data Availability by using VPC Strategy in Cloud Environ...
 
P2P Cache Resolution System for MANET
P2P Cache Resolution System for MANETP2P Cache Resolution System for MANET
P2P Cache Resolution System for MANET
 
A Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid SystemsA Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid Systems
 
Ijcatr04071003
Ijcatr04071003Ijcatr04071003
Ijcatr04071003
 
A Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid SystemsA Survey of File Replication Techniques In Grid Systems
A Survey of File Replication Techniques In Grid Systems
 
Scalable and adaptive data replica placement for geo distributed cloud storages
Scalable and adaptive data replica placement for geo distributed cloud storagesScalable and adaptive data replica placement for geo distributed cloud storages
Scalable and adaptive data replica placement for geo distributed cloud storages
 
A novel cache resolution technique for cooperative caching in wireless mobile...
A novel cache resolution technique for cooperative caching in wireless mobile...A novel cache resolution technique for cooperative caching in wireless mobile...
A novel cache resolution technique for cooperative caching in wireless mobile...
 
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
A NOVEL CACHE RESOLUTION TECHNIQUE FOR COOPERATIVE CACHING IN WIRELESS MOBILE...
 
Analyse the performance of mobile peer to Peer network using ant colony optim...
Analyse the performance of mobile peer to Peer network using ant colony optim...Analyse the performance of mobile peer to Peer network using ant colony optim...
Analyse the performance of mobile peer to Peer network using ant colony optim...
 
E045026031
E045026031E045026031
E045026031
 
Data Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big DataData Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big Data
 
Data Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big DataData Distribution Handling on Cloud for Deployment of Big Data
Data Distribution Handling on Cloud for Deployment of Big Data
 
Dynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy managementDynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy management
 
Dynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy managementDynamic selection of cluster head in in networks for energy management
Dynamic selection of cluster head in in networks for energy management
 
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
MAP/REDUCE DESIGN AND IMPLEMENTATION OF APRIORIALGORITHM FOR HANDLING VOLUMIN...
 
Use of genetic algorithm for
Use of genetic algorithm forUse of genetic algorithm for
Use of genetic algorithm for
 
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHMCLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
 
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHMCLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
CLOUD COMPUTING – PARTITIONING ALGORITHM AND LOAD BALANCING ALGORITHM
 
Hm2413291336
Hm2413291336Hm2413291336
Hm2413291336
 

More from IJTET Journal

Beaglebone Black Webcam Server For Security
Beaglebone Black Webcam Server For SecurityBeaglebone Black Webcam Server For Security
Beaglebone Black Webcam Server For Security
IJTET Journal
 
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc NetworksConceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
IJTET Journal
 
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
IJTET Journal
 
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy MethodPrevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
IJTET Journal
 
Effective Pipeline Monitoring Technology in Wireless Sensor Networks
Effective Pipeline Monitoring Technology in Wireless Sensor NetworksEffective Pipeline Monitoring Technology in Wireless Sensor Networks
Effective Pipeline Monitoring Technology in Wireless Sensor Networks
IJTET Journal
 
Raspberry Pi Based Client-Server Synchronization Using GPRS
Raspberry Pi Based Client-Server Synchronization Using GPRSRaspberry Pi Based Client-Server Synchronization Using GPRS
Raspberry Pi Based Client-Server Synchronization Using GPRS
IJTET Journal
 
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
IJTET Journal
 
An Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
An Efficient Decoding Algorithm for Concatenated Turbo-Crc CodesAn Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
An Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
IJTET Journal
 
Improved Trans-Z-source Inverter for Automobile Application
Improved Trans-Z-source Inverter for Automobile ApplicationImproved Trans-Z-source Inverter for Automobile Application
Improved Trans-Z-source Inverter for Automobile Application
IJTET Journal
 
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
IJTET Journal
 
Comprehensive Path Quality Measurement in Wireless Sensor Networks
Comprehensive Path Quality Measurement in Wireless Sensor NetworksComprehensive Path Quality Measurement in Wireless Sensor Networks
Comprehensive Path Quality Measurement in Wireless Sensor Networks
IJTET Journal
 
Optimizing Data Confidentiality using Integrated Multi Query Services
Optimizing Data Confidentiality using Integrated Multi Query ServicesOptimizing Data Confidentiality using Integrated Multi Query Services
Optimizing Data Confidentiality using Integrated Multi Query Services
IJTET Journal
 
Foliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing TechniquesFoliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing Techniques
IJTET Journal
 
Comparative Study on NDCT with Different Shell Supporting Structures
Comparative Study on NDCT with Different Shell Supporting StructuresComparative Study on NDCT with Different Shell Supporting Structures
Comparative Study on NDCT with Different Shell Supporting Structures
IJTET Journal
 
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
IJTET Journal
 
A Five – Level Integrated AC – DC Converter
A Five – Level Integrated AC – DC ConverterA Five – Level Integrated AC – DC Converter
A Five – Level Integrated AC – DC Converter
IJTET Journal
 
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
IJTET Journal
 
Study of Eccentrically Braced Outrigger Frame under Seismic Exitation
Study of Eccentrically Braced Outrigger Frame under Seismic ExitationStudy of Eccentrically Braced Outrigger Frame under Seismic Exitation
Study of Eccentrically Braced Outrigger Frame under Seismic Exitation
IJTET Journal
 
Enhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
Enhanced Hashing Approach For Image Forgery Detection With Feature Level FusionEnhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
Enhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
IJTET Journal
 
An Efficient Image Encomp Process Using LFSR
An Efficient Image Encomp Process Using LFSRAn Efficient Image Encomp Process Using LFSR
An Efficient Image Encomp Process Using LFSR
IJTET Journal
 

More from IJTET Journal (20)

Beaglebone Black Webcam Server For Security
Beaglebone Black Webcam Server For SecurityBeaglebone Black Webcam Server For Security
Beaglebone Black Webcam Server For Security
 
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc NetworksConceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
Conceal Traffic Pattern Discovery from Revealing Form of Ad Hoc Networks
 
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
Node Failure Prevention by Using Energy Efficient Routing In Wireless Sensor ...
 
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy MethodPrevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
Prevention of Malicious Nodes and Attacks in Manets Using Trust worthy Method
 
Effective Pipeline Monitoring Technology in Wireless Sensor Networks
Effective Pipeline Monitoring Technology in Wireless Sensor NetworksEffective Pipeline Monitoring Technology in Wireless Sensor Networks
Effective Pipeline Monitoring Technology in Wireless Sensor Networks
 
Raspberry Pi Based Client-Server Synchronization Using GPRS
Raspberry Pi Based Client-Server Synchronization Using GPRSRaspberry Pi Based Client-Server Synchronization Using GPRS
Raspberry Pi Based Client-Server Synchronization Using GPRS
 
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
ECG Steganography and Hash Function Based Privacy Protection of Patients Medi...
 
An Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
An Efficient Decoding Algorithm for Concatenated Turbo-Crc CodesAn Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
An Efficient Decoding Algorithm for Concatenated Turbo-Crc Codes
 
Improved Trans-Z-source Inverter for Automobile Application
Improved Trans-Z-source Inverter for Automobile ApplicationImproved Trans-Z-source Inverter for Automobile Application
Improved Trans-Z-source Inverter for Automobile Application
 
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
Wind Energy Conversion System Using PMSG with T-Source Three Phase Matrix Con...
 
Comprehensive Path Quality Measurement in Wireless Sensor Networks
Comprehensive Path Quality Measurement in Wireless Sensor NetworksComprehensive Path Quality Measurement in Wireless Sensor Networks
Comprehensive Path Quality Measurement in Wireless Sensor Networks
 
Optimizing Data Confidentiality using Integrated Multi Query Services
Optimizing Data Confidentiality using Integrated Multi Query ServicesOptimizing Data Confidentiality using Integrated Multi Query Services
Optimizing Data Confidentiality using Integrated Multi Query Services
 
Foliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing TechniquesFoliage Measurement Using Image Processing Techniques
Foliage Measurement Using Image Processing Techniques
 
Comparative Study on NDCT with Different Shell Supporting Structures
Comparative Study on NDCT with Different Shell Supporting StructuresComparative Study on NDCT with Different Shell Supporting Structures
Comparative Study on NDCT with Different Shell Supporting Structures
 
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
Experimental Investigation of Lateral Pressure on Vertical Formwork Systems u...
 
A Five – Level Integrated AC – DC Converter
A Five – Level Integrated AC – DC ConverterA Five – Level Integrated AC – DC Converter
A Five – Level Integrated AC – DC Converter
 
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
A Comprehensive Approach for Multi Biometric Recognition Using Sclera Vein an...
 
Study of Eccentrically Braced Outrigger Frame under Seismic Exitation
Study of Eccentrically Braced Outrigger Frame under Seismic ExitationStudy of Eccentrically Braced Outrigger Frame under Seismic Exitation
Study of Eccentrically Braced Outrigger Frame under Seismic Exitation
 
Enhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
Enhanced Hashing Approach For Image Forgery Detection With Feature Level FusionEnhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
Enhanced Hashing Approach For Image Forgery Detection With Feature Level Fusion
 
An Efficient Image Encomp Process Using LFSR
An Efficient Image Encomp Process Using LFSRAn Efficient Image Encomp Process Using LFSR
An Efficient Image Encomp Process Using LFSR
 

Recently uploaded

The Cruelty of Animal Testing in the Industry.pdf
The Cruelty of Animal Testing in the Industry.pdfThe Cruelty of Animal Testing in the Industry.pdf
The Cruelty of Animal Testing in the Industry.pdf
luzmilaglez334
 
Node JS Interview Question PDF By ScholarHat
Node JS Interview Question PDF By ScholarHatNode JS Interview Question PDF By ScholarHat
Node JS Interview Question PDF By ScholarHat
Scholarhat
 
How to Manage Line Discount in Odoo 17 POS
How to Manage Line Discount in Odoo 17 POSHow to Manage Line Discount in Odoo 17 POS
How to Manage Line Discount in Odoo 17 POS
Celine George
 
Genetics Teaching Plan: Dr.Kshirsagar R.V.
Genetics Teaching Plan: Dr.Kshirsagar R.V.Genetics Teaching Plan: Dr.Kshirsagar R.V.
Genetics Teaching Plan: Dr.Kshirsagar R.V.
DrRavindrakshirsagar1
 
How to Add a Filter in the Odoo 17 - Odoo 17 Slides
How to Add a Filter in the Odoo 17 - Odoo 17 SlidesHow to Add a Filter in the Odoo 17 - Odoo 17 Slides
How to Add a Filter in the Odoo 17 - Odoo 17 Slides
Celine George
 
E-learning Odoo 17 New features - Odoo 17 Slides
E-learning Odoo 17  New features - Odoo 17 SlidesE-learning Odoo 17  New features - Odoo 17 Slides
E-learning Odoo 17 New features - Odoo 17 Slides
Celine George
 
1. Importance_of_reducing_postharvest_loss.pptx
1. Importance_of_reducing_postharvest_loss.pptx1. Importance_of_reducing_postharvest_loss.pptx
1. Importance_of_reducing_postharvest_loss.pptx
UmeshTimilsina1
 
Our Guide to the July 2024 USPS® Rate Change
Our Guide to the July 2024 USPS® Rate ChangeOur Guide to the July 2024 USPS® Rate Change
Our Guide to the July 2024 USPS® Rate Change
Postal Advocate Inc.
 
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
SSRCreations
 
JavaScript Interview Questions PDF By ScholarHat
JavaScript Interview  Questions PDF By ScholarHatJavaScript Interview  Questions PDF By ScholarHat
JavaScript Interview Questions PDF By ScholarHat
Scholarhat
 
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
Dr. Nasir Mustafa
 
Allopathic M1 Srudent Orientation Powerpoint
Allopathic M1 Srudent Orientation PowerpointAllopathic M1 Srudent Orientation Powerpoint
Allopathic M1 Srudent Orientation Powerpoint
Julie Sarpy
 
Introduction to Google Productivity Tools for Office and Personal Use
Introduction to Google Productivity Tools for Office and Personal UseIntroduction to Google Productivity Tools for Office and Personal Use
Introduction to Google Productivity Tools for Office and Personal Use
Excellence Foundation for South Sudan
 
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
Alvaro Barbosa
 
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
Nguyen Thanh Tu Collection
 
New Features in Odoo 17 Sign - Odoo 17 Slides
New Features in Odoo 17 Sign - Odoo 17 SlidesNew Features in Odoo 17 Sign - Odoo 17 Slides
New Features in Odoo 17 Sign - Odoo 17 Slides
Celine George
 
How to Manage Shipping Connectors & Shipping Methods in Odoo 17
How to Manage Shipping Connectors & Shipping Methods in Odoo 17How to Manage Shipping Connectors & Shipping Methods in Odoo 17
How to Manage Shipping Connectors & Shipping Methods in Odoo 17
Celine George
 
C# Interview Questions PDF By ScholarHat.pdf
C# Interview Questions PDF By ScholarHat.pdfC# Interview Questions PDF By ScholarHat.pdf
C# Interview Questions PDF By ScholarHat.pdf
Scholarhat
 
Odoo 17 Events - Attendees List Scanning
Odoo 17 Events - Attendees List ScanningOdoo 17 Events - Attendees List Scanning
Odoo 17 Events - Attendees List Scanning
Celine George
 
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
Nguyen Thanh Tu Collection
 

Recently uploaded (20)

The Cruelty of Animal Testing in the Industry.pdf
The Cruelty of Animal Testing in the Industry.pdfThe Cruelty of Animal Testing in the Industry.pdf
The Cruelty of Animal Testing in the Industry.pdf
 
Node JS Interview Question PDF By ScholarHat
Node JS Interview Question PDF By ScholarHatNode JS Interview Question PDF By ScholarHat
Node JS Interview Question PDF By ScholarHat
 
How to Manage Line Discount in Odoo 17 POS
How to Manage Line Discount in Odoo 17 POSHow to Manage Line Discount in Odoo 17 POS
How to Manage Line Discount in Odoo 17 POS
 
Genetics Teaching Plan: Dr.Kshirsagar R.V.
Genetics Teaching Plan: Dr.Kshirsagar R.V.Genetics Teaching Plan: Dr.Kshirsagar R.V.
Genetics Teaching Plan: Dr.Kshirsagar R.V.
 
How to Add a Filter in the Odoo 17 - Odoo 17 Slides
How to Add a Filter in the Odoo 17 - Odoo 17 SlidesHow to Add a Filter in the Odoo 17 - Odoo 17 Slides
How to Add a Filter in the Odoo 17 - Odoo 17 Slides
 
E-learning Odoo 17 New features - Odoo 17 Slides
E-learning Odoo 17  New features - Odoo 17 SlidesE-learning Odoo 17  New features - Odoo 17 Slides
E-learning Odoo 17 New features - Odoo 17 Slides
 
1. Importance_of_reducing_postharvest_loss.pptx
1. Importance_of_reducing_postharvest_loss.pptx1. Importance_of_reducing_postharvest_loss.pptx
1. Importance_of_reducing_postharvest_loss.pptx
 
Our Guide to the July 2024 USPS® Rate Change
Our Guide to the July 2024 USPS® Rate ChangeOur Guide to the July 2024 USPS® Rate Change
Our Guide to the July 2024 USPS® Rate Change
 
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
10th Social Studies Enrichment Material (Abhyasa Deepika) EM.pdf
 
JavaScript Interview Questions PDF By ScholarHat
JavaScript Interview  Questions PDF By ScholarHatJavaScript Interview  Questions PDF By ScholarHat
JavaScript Interview Questions PDF By ScholarHat
 
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
Dr. Nasir Mustafa CERTIFICATE OF APPRECIATION "NEUROANATOMY"
 
Allopathic M1 Srudent Orientation Powerpoint
Allopathic M1 Srudent Orientation PowerpointAllopathic M1 Srudent Orientation Powerpoint
Allopathic M1 Srudent Orientation Powerpoint
 
Introduction to Google Productivity Tools for Office and Personal Use
Introduction to Google Productivity Tools for Office and Personal UseIntroduction to Google Productivity Tools for Office and Personal Use
Introduction to Google Productivity Tools for Office and Personal Use
 
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
Benchmarking Sustainability: Neurosciences and AI Tech Research in Macau - Ke...
 
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
BÀI TẬP BỔ TRỢ 4 KỸ NĂNG TIẾNG ANH LỚP 12 - GLOBAL SUCCESS - FORM MỚI 2025 - ...
 
New Features in Odoo 17 Sign - Odoo 17 Slides
New Features in Odoo 17 Sign - Odoo 17 SlidesNew Features in Odoo 17 Sign - Odoo 17 Slides
New Features in Odoo 17 Sign - Odoo 17 Slides
 
How to Manage Shipping Connectors & Shipping Methods in Odoo 17
How to Manage Shipping Connectors & Shipping Methods in Odoo 17How to Manage Shipping Connectors & Shipping Methods in Odoo 17
How to Manage Shipping Connectors & Shipping Methods in Odoo 17
 
C# Interview Questions PDF By ScholarHat.pdf
C# Interview Questions PDF By ScholarHat.pdfC# Interview Questions PDF By ScholarHat.pdf
C# Interview Questions PDF By ScholarHat.pdf
 
Odoo 17 Events - Attendees List Scanning
Odoo 17 Events - Attendees List ScanningOdoo 17 Events - Attendees List Scanning
Odoo 17 Events - Attendees List Scanning
 
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
BỘ ĐỀ THI HỌC SINH GIỎI CÁC TỈNH MÔN TIẾNG ANH LỚP 9 NĂM HỌC 2023-2024 (CÓ FI...
 

ICICCE0298

  • 1. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 Parallel Particle Swarm Optimization for Reducing Data Redundancy in Heterogeneous Cloud Storage M.Vidhya1 Mr.N.Sadhasivam2 , 1 Department of Computer Science and Engineering, 2 Department of Computer Science and Engineering, Bannari Amman Institute of Technology, Bannari Amman Institute of Technology, Sathyamangalam . Sathyamangalam. vidhyam284@gmail.com sadhasivamn82@gmail.com Abstract— Cloud storage is usually distributed infrastructure, where data is not stored in a single device but is spread to several storage nodes which are located in different areas. To ensure data availability some amount of redundancy has to be maintained. But introduction of data redundancy leads to additional costs such as extra storage space and communication bandwidth which required for restoring data blocks. In the existing system, the storage infrastructure is considered as homogeneous where all nodes in the system have same online availability which leads to efficiency losses. The proposed system considers that distributed storage system is heterogeneous where each node exhibit different online availability. Monte Carlo Sampling is used to measure the online availability of storage nodes. The parallel version of Particle Swarm Optimization is used to assign redundant data blocks according to their online availability. The optimal data assignment policy reduces the redundancy and their associated cost. Index Terms— cloud storage, data redundancy, online availability, optimal data assignment, particle swarm optimization ——————————  —————————— 1 INTRODUCTION LOUD storage systems are built upon storage resources from different computers or different dedicated storage devices to build a large storage service which provides more reliable, scalable and efficient storage service. The cloud storage services such as Amsazon, Facebook, Gmail use distributed storage systems. The cloud service providers render small capacity of storage for free and additional storage capacity for pay on monthly or annual basis. The cloud service providers and the users agreed upon the service level agreement which provide the quality of service measures such as response time, data availability, data reliability and reasonable costs. The amount of data that is replicated depends on the service level a customer chooses. In the storage system the redundancy is maintained to ensure data availability. The two mechanisms to maintain data redundancy are replication and erasure coding. In replication mechanism, the entire file is stored multiple times in different storage nodes which increases the storage space for which the user have to pay additional costs. When the storage node fails, the entire file has to be transmitted to restore the lost data over the communication links which cause additional communication costs. Another mechanism is erasure coding in which the data file is divided into fixed number of data blocks which are further encoded into number of redundant blocks. The cloud storage system uses the (k, n) erasure code where the file is divided into k data blocks which are encoded into n redundant blocks. At any time k redundant blocks are enough to construct original file. IJTET©2015 The storage system consists of set of storage nodes N. At any time the set of nodes M is chosen from N which is a random sample of N to store data blocks. In the set of nodes M, there may be some nodes available and some may not be available. By monitoring every node in the system for longer period of time, the mean node availability is calculated which is based on how much time the node active on the network. The data assignment function is used to assign redundant data blocks to set of storage nodes based on their online availability. the number of possible combinations to assign redundant data blocks is computationally hard for large scale storage systems. to solve such large scale combinatorial problems, the heuristic algorithms are used. The optimization algorithm works by defining the search space and to maximize the specified function. There are numerous algorithms available but particle swarm optimization is proved to have better performance for distributed environment. The computational speed of particle swarm optimization algorithm is faster compared to other evolutionary techniques such as genetic algorithm. The PSO algorithm is easy to implement because it has few parameters and convergence speed is faster. The particle swarm optimization algorithm may suffer from premature convergence that is the chance of falling into local optimum is higher. The algorithm falls into local optimum due to loss of diversity in population because each particle updates and follows the single global best particle. If the particle falls into local optimum, then the algorithm can‘t overcome from the local best 73 C
  • 2. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 solution. So to overcome such problems the parallel version of particle swarm optimization algorithm is used. In this the entire population is divided into subgroups and each subgroup performs independently for some time. After some time interval, the best of each swarm is chosen to find the best particle which has maximum value. Based on that value, all particles update their position. Here the convergence rate of the algorithm is improved because the particles moved towards the global best particle which is the best of all the sub swarms. But when the convergence rate is reduced, the algorithm‘s computational speed also gets reduced. Here all the sub swarms are independent. So they are executed in parallel on different machines which improve the computational time. The optimal data redundancy is the minimum amount of redundancy required to the data availability for accessing data at any time. The redundancy ratio decides how many times the data blocks are replicated. The value of redundancy ratio should be low to keep minimum redundancy. 2 RELATED WORK Cloud storage services have obtained importance in the recent years [1, 6, 7, 23]. These services allow users to store data outside of their storage infrastructure. To store large amounts of data from millions of users, cloud storage systems build their services over distributed storage infrastructures that are more scalable and reliable than centralized storage systems. Different works have proposed distributed data storage infrastructures, some of which built on grid infrastructures [1, 7], and some others built on P2P networks [20]. To achieve the required data availability, all the storage systems need to store data with redundancy. But the use of redundancy also increases storage and communication costs. To maintain the storage system accessible, the redundancy has to be reduced. The peer-to-peer (P2P) storage system such as Wuala [21] allows users to share part of their hard drives to obtain a reliable and online storage capacity. Chandra and Weissman [5] proposed the idea of letting users to contribute their unused storage resources to satisfy the storage requirements of these research projects. A similar approach was advocated by the developers of Open Cirrus [4] to aggregate unused resources from different small and heterogeneous datacenters. The existing storage solutions treat all nodes in the system are equal and they have same online availability. But the nodes in distributed storage infrastructure are heterogeneous. They exhibit different online availabilities. So the proposed system uses heterogeneity to calculate data availability, the Particle Swarm Optimization algorithm is used to place redundant data blocks according to node‘s availability and minimum data redundancy is obtained that satisfies the targeted availability. By reducing redundancy, distributed storage systems can reduce storage and communication costs. In [2], Blakes and Fodrigues described a limit beyond which communication costs cannot be reduced without increasing storage costs and the reverse is also true. The data redundancy schemes [17, 22, 23] provide better communication-storage trade-offs. Unfortunately, all these works have assumed homogeneous properties for all the storage nodes in the system. IJTET©2015 The main objective of this paper is to optimize distributed storage systems by considering the real heterogeneities present in cloud [4] systems, or any other existing distributed systems. In [7], Deng and Wang considered node heterogeneities in grid storage systems. However, they did not use such heterogeneities to reduce the amount of data redundancy required. In [15], Pamies-Juarez et al. describe heterogeneities using simple heuristic approaches to reduce data redundancy. In [16], Pamies-Juarez et al. provided the method to calculate data availability for any scale of storage system and use optimization method to assign data blocks to set of nodes. They provide the simple measure to find optimal data redundancy. In [11], Gonsalves & Egashira describes the parallel version of PSO algorithm without introducing any complexity. In this paper, the parallel version of algorithm is used to improve the data availability and to reduce the data redundancy of nodes compared to standard Particle Swarm Optimization algorithm. 3 PROBLEM DESCRIPTION In distributed storage system in order to maintain data availability some amount of redundancy has to be maintained .But introducing redundancy leads to additional storage and communication costs. So the need for effective redundancy scheme is required which balances the both data availability and its associated costs. In literature [9, 14, 17, 20], the erasure codes are proved to provide better redundancy for distributed storage systems. To improve data availability the data objects should be stored in high reliable nodes. To calculate node‘s availability for any scale Monte Carlo Sampling method is used. The existing system use Particle Swarm Optimization algorithm to assign data blocks to different nodes based on their availability. In original PSO, each particle updates its position based on its personal best and the global best. Here the global best is the best of entire swarm. All the particles in the swarm are moved towards on single position called global best. So the algorithm converges faster which is called premature convergence leads to poor performance. That is the algorithm fails to find a global optimal solution or even sometimes best local optimal solution. This has occurred due to decline of population diversity. When the algorithm parameters are not tuned properly there is a chance of falling in the local optima. In general, maintaining diversity will reduce convergence rate which is used to remove swarm stagnation in a poor local optimal solutions. To overcome such problems a parallel approach called Parallel Particle Swarm Optimization is used. 4 REDUCING DATA REDUNDANCY USING PARTICLE SWARM OPTIMIZATION 4.1 Monte Carlo method to measure data availability Data availability is referred as the degree to which data can be instantly accessed. The term is specified in service level agreements of cloud storage provider. In distributed storage infrastructure, data availability is defined as the possibility of detecting k blocks out of the n redundant blocks so that erasure codes construct original data object from k redundant blocks. In [14], Lluis et al. defined the data availability d, as a function D (k, n, g, N) which relies on erasure 74
  • 3. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 code parameters k and n, the data assignment function g and the set of nodes N. Monte Carlo Sampling technique is used to measure the data availability of storage system in heterogeneous distributed infrastructure. The distributed storage system consists of N nodes. So there are N 2 possible combinations to store n redundant blocks. The data assignment function g assigns n redundant blocks to storage nodes based on their online availability. 4.2 Steps to measure data availability a) The set VS of V samples is taken from N 2 (i.e. VS  N 2 ) randomly b) The set A is the combination which together store k or more redundant data blocks is selected from VS samples (i.e. A VS ) based on individual node‘s availability c) The data availability Vd is measured by average of number of samples together store k or more redundant blocks to number of samples taken from N 2 i.e.        V A dV 4.3 Data assignment using particle swarm optimization The data assignment function is used to assign redundant data blocks to set of storage nodes based on their online availability. The number of possible combinations to assign redundant data blocks is computationally hard for large scale storage systems. To solve best assignment of redundant blocks to storage nodes which maximizes the data availability, the Particle Swarm Optimization algorithm is used. The PSO is proved to be very efficient in distributed environment for performance. Optimization algorithms work by defining the workspace and to maximize the specified function. The search space is the set of possible combinations of storage nodes and the function to be maximized is data availability. 4.4 Algorithm for PSO a) Initialize the swarm from the solution space that is randomly distributing n redundant blocks to set of storage nodes N b) Evaluate the fitness function data availability d=(D, n, k, g) c) Update individual and global bests d) Update velocity and position of particles The velocity is given by )(11 1 t ii t i t i XlbestrcwVV  )(22 t iXgbestrc  (1) Here w is the inertia weight, 1r and 2r are random variables IJTET©2015 between [0, 1] and 1c , 2c are acceleration constants. The position is given by 11   t i t i t i VXX (2) e) The step b is performed until the minimum data availability is met. 4.5 Finding optimal data redundancy The optimal data redundancy is minimum data redundancy that is required to satisfy required data availability dˆ . The required data availability is taken as some nine‘s such as 0.9, 0.99, 0.9999 etc. The redundancy ratio r = n k which satisfies the minimum data availability is the optimal data redundancy. To find optimal redundancy r, the n value is fixed (i.e. n=|N|. β for large β) and the k value is changed from k=n to 1. 4.6 Algorithm for finding r a) Set k=|N| b) Calculate data availability D(n, k, g, N) c) while D(n ,k, g, N) < dˆ and k≠0 d) k=k-1 e) end while 5 PARALLEL PARTICLE SWARM OPTIMIZATION ALGORITHM FOR DATA ASSIGNMENT FUNCTION The existing system uses PSO algorithm for data assignment function but the original PSO algorithm suffers from premature convergence and it can‘t suitable for parallel operation. The parallel version of particle swarm optimization algorithm divides the population into sub-population and applies the algorithm individually to these sub-populations to reduce computation time. 5.1 Algorithm for PPSO a) Divide the population into k independent swarms randomly and initialize the individual swarm b) The fitness function of each independent swarm is evaluated c) The particle best and the swarm best of individual swarm is determined d) The velocity and position of each particle in every swarm is updated e) The steps 2 through 4 is repeated for N iterations 75
  • 4. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 f) The global best is determined by comparing the swarm best of all the swarms. The fitness function data availability should be maximized for the global best. It is specified by the following equation ,,max( 21 sbestsbestgbest  ),...,3 ksbestsbest (3) g) The independent swarms are interacted using gbest value. The velocities of particles are updated according to the following equation )1()( ,,  twvtv jiji ))1()1(( ,,11  txtprc jiji ))1()1(( ,,22  txtprc jijs (4) ))1()1(( ,,33  txtprc jijg where jix , is the position of ith particle in jth swarm, jiv , is the velocity of ith particle in jth swarm, jip , is the pbest of ith particle in jth swarm, jsp , is the swarm best of jth swarm, gp is the global best among all the sub- swarms, 1c , 2c , 3c are acceleration parameters and 1r , 2r , 3r are the random variables. h) The position of all the particles are updated according to the following equation )()1()( ,,, tvtxtx jijiji  (5) i) The steps 2 to 8 are repeated for M iterations and the output is the best optimal assignment of data blocks 6 EXPERIMENTAL RESULTS 6.1 Parameter Settings The number of particles is 120 and the maximum number of iterations is 50. The acceleration parameters for PSO is 1c , 2c =1 and the inertia weight parameter value for both PSO and PPSO is 0.7. The number of subgroups for parallel particle swarm optimization algorithm is 8. The acceleration parameters for parallel particle swarm optimization algorithm are 1c =1, 2c =1 and 3c =1. The fitness function is data availability d= (D, k, n, g) which must meet the minimum data availability dˆ = {0.9, 0.99, 0.999}. 6.2 Performance Metrics a) Speedup It is the measure used to compute the ratio between the average IJTET©2015 execution time on single processor ][ 1tA and the average execution time on multiple processors ][ ktA .The speedup due to k processors is defined by ][ ][ 1 k k tA tA S  (6) TABLE 1 COMPARISON OF EXECUTION TIMES OF BOTH PSO AND PPSO Here the k value chosen is 8. The execution times of both PSO and PPSO are shown in the table 1. The speedup of Parallel Particle Swarm Optimization is 3.2 times faster than original Particle Swarm Optimization. b) Efficiency The efficiency is defined as the percentage of speedup caused by k processors. It is given by %100* k S E k k  (7) From the experiments the Parallel Particle Swarm Optimization algorithm is 40% efficient than Particle Swarm Optimization algorithm. The results prove that the parallel version of particle swarm optimization algorithm is efficient for data assignment function in distributed cloud storage which reduces the computation time of data assignment function. 6.3 Redundancy savings Redundancy Saving Ratio (RSR) is the metric used to measure the redundancy savings caused by distributed heterogeneous environment instead of homogeneous environment. The data redundancies orhom and heteror are caused by 76
  • 5. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 homogeneous and heterogeneous storage systems. The Redundancy Saving Ratio is defined as 100*1 hom        hetero o r r RSR (8) TABLE 2 THE REDUNDANCY SAVING RATIOS OF REAL AVAILABILITY DATASETS The number of storage nodes is 100. The fixed value for redundant blocks is n=100.|N| (i.e. β=100). The homogeneous environment uses unitary assignment function that is each block gets exactly one block. The heterogeneous environment uses parallel particle swarm optimization algorithm to assign data blocks to nodes based on their online availabilities. The four real time availability datasets are used for the experiments. The availability datasets are Planetlab nodes [19], Skype super-nodes [10], Microsoft desktop PCs [3], and Seti@- Home‘s desktop grid nodes[18] The results from table 2 shows that the redundancy savings are high for highly heterogeneous environments 7 CONCLUSION AND FUTURE WORK The proposed system uses parallel version of particle swarm optimization which reduces the computation time of the algorithm. The parallel particle swarm optimization algorithm assigns data blocks according to their online availabilities. By considering heterogeneous environment where each node have different online availabilities, the data assignment function assigns data blocks according to them. The redundancy savings are high almost 75% of redundancies are removed which also reduce storage and communication costs. In the future work, the dynamic storage systems are considered. In this the number of nodes and the number of stored objects are continuously changed. To reduce redundancy for such environment a new scheme is needed. IJTET©2015 REFERENCES [1] D. P. Anderson (2004), ‗Boinc: a system for public-resource computing and storage‘, Proceedings of the 5th IEEE/ACM International Workshop on Grid Computing [2] C. Blake & R. Rodrigues (2003), ‗High availability, scalable storage, dynamic peer networks‘, Proceedings of the 9th Workshop on Hot Topics in Operating Systems (HOTOS) [3] W. J. Bolosky , J. R. Douceur, D. Ely & M. Theimer (2000), ―Feasibility of a serverless distributed file system deployed on an existing set of desktop pcs‖, proceedings of the International Conference on Measurement and Modeling of Computer Systems ACM SIGMETRICS [4] R. Campbell, I. Gupta, M. Heath, S. Y. Ko, M. Kozuch, M. Kunze, T. Kwan, K. Lai, H.Y. Lee, M. Lyons, D. Milojicic, D. O‘Hallaron & Y. C. Soh (2009), ‗ Open cirrus cloud computing testbed: federated data centers for open source systems and services research‘, Proceedings of the Usenix Workshop on Hot Topics on Cloud Computing (HotCloud) [5] A. Chandra & J. Weissman (2009), ‗ Nebulas: Using distributed voluntary resources to build clouds‘, Proceedings of the Usenix Workshop on Hot Topics on Cloud Computing (HotCloud) [6] CleverSafe, 2010, Cleversafe, http://www.cleversafe.com [7] Y. Deng & F. Wang (2007), ‗A heterogeneous storage grid enabled by grid service‘, Proceedings on Small Interest Group on Operating Systems review (SIGOPS) , vol. 41, no. 1, pp. 7–13 [8] A. Dimakis, P. Godfrey, M. Wainwright & K. Ramchandran (2007), ‗Network coding for distributed storage systems‘, Proceedings of the 26th IEEE International Conference on Computer Communications [9] A. Duminuco & E. W. Biersack (2008), ‗Hierarchical codes: how to make erasure codes attractive for peer-to-peer storage systems‘, Proceedings of the 8th International Conference on Peer-to-Peer Computing (P2P) [10] B. Godfrey, Repository of availability traces,2010,<http://www.cs.berkeley.edu/pbg/availability/> [11] T. Gonsalves & A. Egashira (2013), ―Parallel Swarms Oriented Particle Swarm Optimization‖, Proceedings of Applied Computational Intelligence and Soft Computing 2013 [12] J. Kennedy & R. Eberhart (1995), ‗Particle swarm optimization‘, Proceedings of the IEEE International Conference on Neural Networks [13] J. Kubiatowicz, D. Bindel, Y. Chen, S. Czerwinski, P. Eaton, D. Geels, R. Gummad, S. Rhea, H. Weatherspoon, W. Weimer, C. Wells & B. Zhao (2000), ‗Oceanstore: an architecture for global-scale persistent storage‘, Proceedings of the 9th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 77
  • 6. INTERNATIONAL JOURNAL FOR TRENDS IN ENGINEERING & TECHNOLOGY VOLUME 3 ISSUE 1 –JANUARY 2015 - ISSN: 2349 - 9303 [14] W. K. Lin, D. M. Chiu & Y. B. Lee (2004), ‗Erasure code replication revisited‘, Proceedings of the 4th International Conference on Peer-to-Peer Computing (P2P) [15] P. Lluis, G. Pedro, S. Marc & H. Blas (2011), ‗Towards the design of optimal data redundancy schemes for heterogeneous cloud storage infrastructures‘, Journal of Elsevier, vol. 55, no. 5, pp. 1100–1113 [16] L. Pamies-Juarez, P. García-López & M. Sánchez-Artigas, M (2009), ‗Heterogeneity-aware erasure codes for peer-to-peer storage systems‘, Proceedings of the 38th IEEE International Conference on Parallel Processing (ICPP) [17] R. Rodrigues & B. Liskov (2005), ‗High availability in dhts: erasure coding vs replication‘, Proceedings of the 4th International Workshop on Peer-To-Peer Systems (IPTPS) [18] Standford.edu, Folding@home: distributing computing project, 2009, <http://folding.stanford.edu> [19] J. Stribling , Planetlab all pairs ping, 2010, <http://infospect.planetlab.org/pings> [20] H. Weatherspoon & J. D. Kubiatowicz (2002),‘Erasure coding vs. replication: a quantitative comparison‘, Proceedings of the 1st International Workshop on Peer-To-Peer Systems (IPTPS) [21] WuaLa, 2010, Wuala, <http://www.wuala.com>. [22] F. Wu, T. Qiu, Y. Chen & G. Chen (2005), ‗Redundancy schemes for high availability in dhts‘, Proceedings of the 3rd International Symposium on Parallel and Distributed Processing and Applications (ISPA) [23] Z. Zhang & Q. Lian (2002), ‗Reperasure: replication protocol using erasure code in peer-to-peer storage network‘, Proceedings of the 21st Symposium on Reliable Distributed Systems (SRDS) IJTET©2015 78