SlideShare ist ein Scribd-Unternehmen logo
1 von 7
Downloaden Sie, um offline zu lesen
ISSN: 2277 – 9043
          International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                         Volume 1, Issue 5, July 2012



                    Grid Scheduling Using PSO with SPV Rule
                                          Kuldeep Kaur
                                          M.TECH(CSE)
                         Department of Computer Science and Engineering
                                  Baby2impressive@yahoo.co.in
                           Lovely Professional University, Punjab, India

                                  Mr. Sudhanshu Prakash Tiwari
                         Department of Computer Science and Engineering
                           Lovely Professional University, Punjab, India


Abstract                                                     1. Its ability to make more cost-effective
Grid computing can be defined as applying                        use of a given amount of computer
the resources of many computers in a network                     resources.
to a problem which requires a great number of                2. It is a way to solve problems that can't
computer processing cycles or access to large                    be approached without an enormous
amounts of data. However, in the field of grid                   amount of computing power.
computing scheduling of tasks is a big                       3. Because it suggests that the resources
challenge. The task scheduling problem is the                    of    many      computers     can be
problem of assigning the tasks in the system                     cooperatively and perhaps
in a manner that will optimize the overall               Synergistically harnessed and managed as
performance of the application, while                    collaboration toward a common objective.
assuring the correctness of the result. Each             Grid computing can be used to compute large
day new algorithms are proposed for                      number of tasks on the resources which are
assigning tasks to the resources. This is also a         geographically remotely located. Task
boon for the grid computing. In this paper we            scheduling is a challenging problem in grid
use the technique of Particle Swarm                      computing environment. Many parallel
Optimization (PSO) with SPV (Shortest                    applications consist of multiple computational
position value) rule to solve the task                   components. While the execution of some of
scheduling problem in grid computing. The                these components or tasks depends on the
aim of using this technique is use the given             completion of other tasks, others can be
resources optimally and assign the task to the           executed at the same time, which increases
resources efficiently. The simulated results             parallelism of the problem.
show that PSO with SPV rule proves to be a               Abraham et al and Braun et al [1] address the
better algorithm when applied to resource                dynamic scheduling of jobs to the
allocation and disk scheduling in grid                   geographically       distributed     computing
computing.                                               resources. They provide an introduction of
                                                         computational grids followed by a brief
Keywords: Grid scheduling; PSO with SPV
                                                         description of the three nature’s heuristics
rule; SPV Rule; Tasks; Resources
                                                         namely Genetic Algorithm (GA), Simulated
                                                         Annealing (SA) and Tabu Search (TS).
    I.   INTRODUCTION                                    Yang gao et al [2] proposed two algorithms
                                                         that use the predictive models to schedule
Grid computing is a network that is not in               jobs at both system level and application
the same place but distributed resources such            level.
as    computers,    peripherals,    switches,            M Aggrawal et al [3] presented a Genetic
instruments, and data. Grid computing                    Algorithm based scheduler. The proposed
appears to be a promising trend for three                scheduler used in both the intra-grid of a large
reasons:                                                 organization and in a research grid consisting

                                                                                                      20
                                    All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
          International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                         Volume 1, Issue 5, July 2012


of large clusters, connected through a high                because now inefficient resource allocation
bandwidth dedicated network.                               can greatly hamper the efficiency and
Shanshan Song et al[4] proposed a new                      throughput of the scheduler.
Space-Time Genetic Algorithm (STGA) for                    To formulate the problem, define Ta
trusted job scheduling in which they consider              a={1,2,3,…X } as x independent tasks
three security-driven heuristic modes: secure,             permutation and Rb b={1,2,3,…y } as y
risky and f -risky.                                        computing resources. Suppose that the
Lee Wang et al [5] developed a heuristic                   processing time Pa,b for task a computing on
based approach to matching and scheduling in               b resource is known. The completion time
heterogeneous computing environment.                       F(x) represents the total cost time of
Lin Jian Ning et al [6] scheduling-algorithm               completion.
based on genetic algorithm (GA) is addressed.                 The objective is to find an permutation
    In this paper simulated results prove that             matrix m = (Mab) , with Mab =1 if resource
PSO with SPV rule proves to be better when                 a performs task b and if otherwise, Mab=0,
it is applied for resource allocation in the field         which minimizes the total costs.
of grid computing. This paper is organized as
follows. In section 2 the issues related to task           F(x)=ΣΣPa,b * Mab      (1)
scheduling is discussed. In section 3 particle
swarm algorithm is introduced. In section 4                Subject to
we implement PSO with SPV rule for grid                    Σ Mab=1,∀ b∈ T ,       (2)
task scheduling problem. In section 5 we see
the simulation result of work done in section              Mab∈ { 0,1}, ∀ a∈ R, b∈ T      (3)
4.                                                            The minimal F(x) represents the length of
                                                           schedule whole tasks working on available
 II.   TASK SCHEDULING ISSUES IN                           resources. The scheduling constraints (2)
       GRID COMPUTING                                      guarantee that each task is assigned to exactly
                                                           one resource.
   Computational grid can be combination of
hardware and software that can be used to                   III.   PARTICLE   SWARM
solve complex computational problems. The                           OPTIMIZATION
resource in a computational grid can be
anything which can be used to solve the given              The particle swarm optimization algorithm,
problem. For example a set of printers which               originally introduced in terms of social and
are used for printing a set a documents. The               cognitive behavior by Kennedy and Eberhart
overall objective of task scheduling is to                 (1995), solves problems in many fields,
minimize the completion time and to utilize                especially engineering and computer science.
the resources effectively and usually it is easy           The individuals, called particles henceforth,
to get the information about the ability to                are flown through the multi-dimensional
process data of the available resource.                    search space with each particle representing a
   The problem of task scheduling arises in a              possible solution to the multi-dimensional
situation where there are more tasks than the              optimization problem. Each solution's fitness
available resources. Consider a scenario                   is based on a performance function related to
wherein there are x, x={1,2,3,4,........X} tasks           the optimization problem being solved. The
to be done and there are y, y={1,2,3,4.......Y}            movement of the particles is influenced by
resources available. With the condition that               two factors using information from iteration-
the task is not allowed to be migrated between             to-iteration as well as particle-to-particle. As
resources.                                                 a result of iteration-to- iteration information,
   In such a situation if we have y>x then                 the particle stores in its memory the best
there is no reason for developing new                      solution visited so far, called pbest , and
algorithms for task scheduling because then                experiences an attraction towards this solution
resources can be allocated to the tasks on first           as it traverses through the solution search
come first serve basis.But if y<x then we need             space. As a result of the particle-to-particle
to develop new algorithms for task scheduling              interaction, the particle stores in its memory
                                                                                                        21
                                      All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
           International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                          Volume 1, Issue 5, July 2012


the best solution visited by any particle, and                Eberhart, 1998). The resulting velocity update
experiences an attraction towards this                        equation becomes:
solution, called gbest , as well. The first and
second factors are called cognitive and social
components, respectively. After each                          vid = w * vid + c1 r1( pid - xid) + c2r2( pgd -xid)
iteration, the pbest and gbest are updated for
each particle if a better or more dominating                  (6)
solution (in terms of fitness) is found. This
process continues, iteratively, until either the                 Eberhart and Shi (2000) indicate that the
desired result is converged upon, or it is                    optimal strategy is to initially set w to 0.9 and
determined that an acceptable solution cannot                 reduce it linearly to 0.4, allowing initial
be found within computational limits. For an                  exploration followed by acceleration toward
n-dimensional search space, the ith particle of               an improved global optimum.
the swarm is represented by an n-dimensional
vector, Xi= (xi1 ,xi2 .....xin )T . The velocity of              IV. PROPOSED METHODOLOGY
this particle is represented by another n-
dimensional vector Vi = (vi1; vi2...... vin )T .              In this paper we have proposed a solution for
The previously best visited position of the ith               grid scheduling using PSO with SPV rule. For
particle is denoted as Pi = (pi1, pi2,........pin )T .        solving any optimization problem we have to
`g' is the index of the best particle in the                  first formulate the problem according to
swarm. The velocity of the ith particle is                    optimization problem. In this case first we
updated using the velocity update equation                    formulate the grid scheduling problem
given by                                                      according to PSO algorithm. Next subsection
                                                              describes how we formulate the grid
                                                              scheduling problem.
vid = vid +c1r1( pid - xid) + c2r2( pgd -xid)
                                                                    V. REPRESENTATION
(4)
                                                              To solve the problem, representation of the
                                                              individual and fitness value is required. PSO
and the position is updated using
                                                              with SPV rule algorithm is based on
                                                              population (candidate solution) and each
xid= xid + vid                                                population have its own fitness value
                                                              according to which it is compared from
(5)                                                           others, so we have to first represent the grid
                                                              scheduling problem in terms of PSO with
   where d = 1, 2....n ; i = 1; 2....S , where S              SPV rule.In grid scheduling, we have a set of
is the size of the swarm; c1 and c2 are                       tasks and a set of resources as input and a
constants, called cognitive and social scaling                sequence, which informs that which task is to
parameters respectively (usually, c1 = c2 ; r1 ,              be operated on which resource and in which
r2 are random numbers, uniformly distributed                  order as output. PSO with SPV rule is based
in [0, 1]). Equations (4) and (5) are the initial             on population concept and each individual in
version of PSO algorithm. A constant, Vmax, is                population represents a solution, in case of
used to arbitrarily limit the velocities of the               grid scheduling problem, solution is a
particles and improve the resolution of the                   sequence of tasks which are to be performed.
search. Further, the concept of an inertia                    So we have to first formulate each individual
weight was developed to better control                        of PSO with SPV rule.
exploration and exploitation. The motivation                  Grid task scheduling problem is a discrete
was to be able to eliminate the need for Vmax .               optimization problem. In the proposed
The inclusion of an inertia weight (w) in the                 solution continuous version of PSO is used
particle swarm optimization algorithm was                     instead of discrete version. To change the
first reported in the literature in 1998 (Shi and             continuous version to real version for grid
                                                              task scheduling problem SPV rule is used.
                                                                                                              22
                                         All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
          International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                         Volume 1, Issue 5, July 2012


Using the SPV (shortest position value) rule              Table1: Values of position vector, sequence
continuous position generated by PSO is                   and set of resources.
converted to discrete value.                                 Dimension       Xid       Sid       Rlm
    We represent dimension as a number of                    0               7.83      9         4
task and value as an initial sequence from the
possible set of sequences to find optimal                    1               -0.65     0         0
sequence. Position vector Xid={x1,x2,x3,......xd}            2               2.90      4         4
where i is the particular individual and d                   3               5.46      7         2
represents the dimension index, is calculated                  4              1.25       3          3
using PSO. The position vector of each
particle makes transformation about the                        5              4.87       6          1
continuous position. Smallest position value                   6              -0.48      1          1
i.e. SPV rule is used to find a permutation                    7              0.39       2          2
corresponding position Xid. The position                       8              6.0        8          3
vector Xid has continuous values. By using the                 9              3.28       5          0
SPV rule this continuous position value can
be converted to discrete value permutation                    VI.     FITNESS FUNCTION
Sid=[si1, si2,…….sid].Sidis the sequence of task
of i particle in the processing order with                After representation of each individual we
respect to the d dimension.                               have to calculate fitness value of each
    Set of resources is represented by                    individual. On the basis of fitness value we
Rlm={r1,r2,r3......ry}, where l represents a              determine the optimal solution. In case of grid
particle/ sequence and m represents the tasks             scheduling problem optimal solution is the
which are assigned to a resource. After Sid, set          minimization the value of equation.
of resources is calculated using equation (7).            Our main objective is to minimize the fitness
                                                          value, an individual who have the minimum
       Rlm=Sid mod M         (7)                          fitness value is considered as the optimal
                                                          solution.
 i.e. value of task set mod Total resources
                                                                    VII. ALGORITHM
Resource id is given to each resource so that
they can be easily differentiated from one                Grid scheduling using PSO with SPV Rule
other. Such as r1 is the resource id of first
resource. For e.g. if we have 10 tasks which              To solve the grid scheduling problem we have
are to be performed on 5 available resources              used the Particle Swarm Optimization (PSO)
then we have dimension value as 10.Based on               with SPV rule. We set an initial population by
SPV rules, the continuous position convert to             selecting random starting sequences from the
a permutation of sequences Sid, which is a                set of x! Sequences; where x is the total
sequence of task simplified by the particle Xid.          number of tasks. After getting the initial
   Position vector Xid is calculated using PSO            particle we calculate fitness value of each
is={4.83,-0.55,1.90,3.46,1.05,2.87,-                      particle, according to equation. After that we
0.28,0.19,4.0,2.28}                                       calculate best among the entire particle and
   Then using SPV rule transformation of                  set it as an initial global best.
position vector Xid to Sid, we have Sid value as             PSO update equation is used to update old
{9,0, 4, 7,3,6,1,2,8,5}.                                  population and generate new sequences and
Equation (7) is then used to determine the                then their resources are calculated. This
associated resources for the calculated tasks             sequence, along with its resource is then used
in the sequence. We can calculate the                     to find the fitness value of each individual of
resource set as {4, 0, 4, 2, 3, 1, 1, 2, 3, 0}            each particle of the population. Algorithm 1 is
The table1 represents the dimension values of             the proposed algorithm for the grid
position vector Xid , sequence Sid and Set of             scheduling problem.
resource Rlm.

                                                                                                        23
                                     All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
         International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                        Volume 1, Issue 5, July 2012


Algorithm for Grid Scheduling using PSO                 maximum function evaluation, which is
                                                        20,000 in our experiment. The fourth control
with SPV Rule                                           parameter is Dimension and it depends upon
                                                        the number of tasks. The next control
                                                        parameter is the value of c1 & c2 which we
[Initialsation Phase]                                   have taken as 1.14. And w (Inertia weight) is
 For s=0 to Swarm size do                               also a control parameter and we have taken its
    For d=0 to dimension size do                        value as 0.7.
    Randomly initialize particle
    Using SPV rule a task sequence is
    Compute         resource       for   that             IX.    EXPERIMENTAL RESULTS
    particle/sequence generated
    End for d                                           In this section we analyze the result obtained
Compute fitness of initialized particle                 by our algorithm. To test the efficiency of our
Compute global best                                     algorithm results of PSO with SPV rule is
End for s                                               compared with Genetic algorithm (GA)
[Update Phase]                                          results. In a grid scheduling task we already
Repeat                                                  have the information about the number of
For s=0 to each swarm size do                           resources, number of tasks, and the amount of
      For d=0 to problem dimension do                   time that will be taken by a resource to
Update particles using PSO update equation              complete a task. We just need to find the
A new sequence is generated using SPV rule              sequence which will provide us the optimal
    Compute resources for that sequence                 results. We conducted the experiment by
     end for d                                          varying the number of resources as well as
Compute fitness of updated particle                     varying the number of tasks and then we
if needed update historical information for             compared our results with that of GA. In
global best(Pg)                                         particular, we have taken three cases in which
endfor s                                                we have taken different number of resources
untill(stopping criteria is not met)                    and tasks.

                                                        Experiment 1: Here, we are assuming there
                                                        are 5 resources and 17 tasks. Following are
 VIII. EXPERIMENTAL SETUP
                                                        the execution time (in units) taken by PSO
                                                        with SPV and GA.
For every algorithm there are some control
parameters which are used for its efficient             Table2: Execution time calculated by GA and
working. Hence, there are some controls                 PSO with SPV rule for17 tasks by 5 resources
parameters for PSO with SPV rule also. We
did an extensive literature survey and carried                Genetic         Particle    Swarm
out our own experiments for determining the                   Algorithm       Optimization with
values of these control parameters. From this                 (GA)            Shortest   Position
we found that the values which we have taken                                  Value (PSO with
in this experiment are standard values and                                    SPV)
they are also suitable for this experiment.                   3078.0          3074.0
   The first control Parameter is Maximum
function evaluation and the value of this
parameter we have taken in our experiment as            The sequence generated by GA is: 14, 8, 0,
20,000. The next parameter in our experiment            16, 4, 13, 6, 1, 3, 9, 11, 15, 12, 10, 5, 7, 2.
is maximum number of population and we
have taken its value to be 40. Another control          The sequence generated by our proposed PSO
parameter is number of runs and we have                 with SPV rule is: 4, 12, 7, 14, 2, 13, 6, 8, 10,
taken its value in our experiment as 30. It             15, 1, 0, 9, 3, 5, 16, 11.
must be noted that each run contains
                                                                                                     24
                                   All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
          International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                         Volume 1, Issue 5, July 2012


Experiment 2: Here, we are assuming there                  From the table 2, table 3, table 4, it is clear
are 10 resources and 27 tasks. The execution               that PSO with SPV rule takes less execution
time (in units) taken by GA and PSO with                   time than the GA algorithm.
SPV rule are:
                                                                 X.     CONCLUSION
Table3: Execution time calculated by GA and
PSO with SPV rule for27 tasks by 10                        It can be concluded from the results that
resources                                                  proposed PSO with SPV rule performs better
                                                           than the GA algorithm. The procedure
                                                           followed in grid scheduling consists of the
 Genetic              Particle      Swarm                  generation of the population according to the
 Algorithm (GA)       Optimization     with                algorithm, then the task sequence and
                      Shortest     Position                resources associated with the task sequence
                      Value (PSO with SPV)                 are generated and the positions, task sequence
 5365.0               5357.0                               and resource set are updated and then the
                                                           globally best position or sequence is
                                                           calculated. It is repeated again and again till
The      sequence      generated       by     GA           the maximum number of function evaluation.
is:24,9,7,2,26,0,8,13,3, 18, 10, 1, 23, 5, 17,             As future work we have the intention to apply
14, 4, 15, 12, 6, 16, 20, 11, 22, 25, 19, 21.              other types of nature inspired algorithms to
                                                           the grid scheduling problem, comparing their
The sequence generated by our proposed PSO                 results with the ones accomplished by the
with SPV rule is: 14, 19, 1, 9, 0, 7, 24, 6, 8,            PSO with SPV rule.
10, 15, 5, 13, 12, 26, 4, 11, 2, 22, 18, 17, 3,                  XI. REFERENCES
16, 21, 23, 20, 25.
                                                           [1] Foster and C. Kesselman (editors), The
Experiment 3: Here, we are assuming there                      Grid: Blueprint for a Future Computing
are 12 resources and 30 tasks. The execution
                                                               Infrastructure,    Morgan     Kaufman
time (in units) taken by GA and PSO with
                                                               Publishers, USA, 1999.
SPV rule are:
                                                           [2] Abraham, R. Buyya and B. Nath, Nature's
Table4: Execution time calculated by GA and                    Heuristics for Scheduling Jobs on
PSO with SPV rule for 30 tasks by 12                           Computational Grids, The 8th IEEE
resources                                                      International Conference on Advanced
                                                               Computing                          and
   Genetic             Particle      Swarm                     Communications(ADCOM 2000), pp. 45-
   Algorithm           Optimization    with                    52, December 2000.
   (GA)                Shortest     Position
                       Value (PSO with                     [3] Y. Gao, H.Q Rong and J.Z. Huang,
                       SPV)                                    Adaptive grid job scheduling with genetic
   6081.0              5834.0                                  algorithms,
                                                           [4] Future Generation Computer Systems
                                                               Elsevier, pp.151-161,2005.
The sequence generated by GA is: 28, 14, 20,
25, 10, 7, 17, 4, 9, 22, 6, 11, 24, 18, 0, 29, 15,         [5] M. Aggarwal, R.D. Kent and A. Ngom,
1, 26, 12, 13, 19, 29, 5, 3, 27, 2, 21, 16, 8.                 Genetic Algorithm Based Scheduler for
                                                               Computational Grids, in Proc. of the 19th
The sequence generated by our proposed PSO                     Annual International Symposium on High
with SPV rule is: 11, 22, 0, 29, 1, 25, 24, 17,                Performance Computing Systems and
26, 9, 2, 15, 6, 4, 19, 21, 7, 18, 28, 8, 10, 3,               Application (HPCS’05),pp.209-215, May
13, 27, 23, 5, 16, 14, 20, 12.                                 2005.


                                                                                                       25
                                      All Rights Reserved © 2012 IJARCSEE
ISSN: 2277 – 9043
         International Journal of Advanced Research in Computer Science and Electronics Engineering
                                                                        Volume 1, Issue 5, July 2012


[6] S. Song, Y. Kwok, and K. Hwang,                         Computation,   Piscataway,   pp.   69-73,
    Security-Driven Heuristics and A Fast                   1998.
    Genetic Algorithm for Trusted Grid Job             [14] R. C. Eberhart and Y. Shi, Comparing
    Scheduling, in Proc. of 19th IEEE                      inertia weights and constriction factors in
    International Parallel and Distributed
                                                           particle swarm optimization Congress on
    Processing Symposium (IPDPS’05),                       Evolutionary Computing, vol. 1, pp. 84-
    pp.65-74, April 2005.                                  88, 2000.
[7] Lee Wang, Howard Jay Siegel, Vwani P.
    Roychowdhury,     and     Anthony     A.
    Maciejewski, Task Matching and
    Scheduling in Heterogeneous Computing                 Kuldeep Kaur received her Msc(IT)
    Environments Using a GeneticAlgorithm                Degree from Guru Nanak Dav University,
    Based Approach, Journal of Parallel and              Amritsar and M.TECH(CSE) Degree from
    Distributed Computing , Citeseer47, pp.8-            Lovely Professional University in 2010 and
    22, 1997                                             2012 respectively. Her Research Interests
[8] Zhang, L.; Chen, Y.; Sun, R.; Jing, S. &             include      Grid     Computing,      Soft
    Yang, B. A task scheduling algorithm                 Computing,Software     Engineering     and
    based on pso for grid computing                      wireless network,etc.
    International Journal of Computational
    Intelligence Research, 4, 37-43, 2008.
[9] Nath B, Lim S, Bignall R J, A Genetic
    Algorithm For Scheduling Independent
    Jobs OnUniform Machines With Multiple
    Objectives,   Proceedings      of    the
    International     Conference          on
    Computational     Intelligence      and
    Multimedia Applications, Australia, pp.               Mr.Sudhanshu Prakash Tiwari has done
    67-74, 1998.                                          M.TECH(CSE).He is assistant professor of
[10] J. Kennedy and R. Eberhart, “Particle                Department of Computer Science and
    swarm optimization”, in Proc. IEEE                    Engineering in Lovely Professional
    International      Conference      Neural             University.
    Networks, vol. 4, pp. 1942 – 1948, 1995.
[11] Lin JianNing and Wu HuiZhong
    ,Scheduling   in   Grid     Computing
    Environment Based onGenetic Algorithm,
    Journal of Computer Research and
    Development,pp.2195-2199,Vol.
    4,No.12,Dec 2004.
[12] Wright, A. Genetic Algorithms for Real
    Parameter Optimization, Foun-dations of
    Genetic Algorithms, G. Rswlins(Ed.),
    Morgen Kaufmann publishers, CA,
    pp.205-218, 1991.
[13] Y. Shi and R. C. Eberhart, “A modified
    particle swarm optimizer”, in Proc. IEEE
    International Conference on Evolutionary


                                                                                                   26
                                  All Rights Reserved © 2012 IJARCSEE

Weitere ähnliche Inhalte

Was ist angesagt?

SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYcsandit
 
4213ijaia02
4213ijaia024213ijaia02
4213ijaia02ijaia
 
Improved Max-Min Scheduling Algorithm
Improved Max-Min Scheduling AlgorithmImproved Max-Min Scheduling Algorithm
Improved Max-Min Scheduling Algorithmiosrjce
 
A PSO-Based Subtractive Data Clustering Algorithm
A PSO-Based Subtractive Data Clustering AlgorithmA PSO-Based Subtractive Data Clustering Algorithm
A PSO-Based Subtractive Data Clustering AlgorithmIJORCS
 
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing IJORCS
 
Extending network lifetime of wireless sensor
Extending network lifetime of wireless sensorExtending network lifetime of wireless sensor
Extending network lifetime of wireless sensorIJCNCJournal
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...AtakanAral
 
IRJET- Review of Existing Methods in K-Means Clustering Algorithm
IRJET- Review of Existing Methods in K-Means Clustering AlgorithmIRJET- Review of Existing Methods in K-Means Clustering Algorithm
IRJET- Review of Existing Methods in K-Means Clustering AlgorithmIRJET Journal
 
Qo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentQo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentAlexander Decker
 
A novel scheduling algorithm for cloud computing environment
A novel scheduling algorithm for cloud computing environmentA novel scheduling algorithm for cloud computing environment
A novel scheduling algorithm for cloud computing environmentSouvik Pal
 
Multiple dag applications
Multiple dag applicationsMultiple dag applications
Multiple dag applicationscsandit
 

Was ist angesagt? (19)

SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHYSPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
SPEED-UP IMPROVEMENT USING PARALLEL APPROACH IN IMAGE STEGANOGRAPHY
 
ME Synopsis
ME SynopsisME Synopsis
ME Synopsis
 
J41046368
J41046368J41046368
J41046368
 
4213ijaia02
4213ijaia024213ijaia02
4213ijaia02
 
Improved Max-Min Scheduling Algorithm
Improved Max-Min Scheduling AlgorithmImproved Max-Min Scheduling Algorithm
Improved Max-Min Scheduling Algorithm
 
P229 godfrey
P229 godfreyP229 godfrey
P229 godfrey
 
Bulk transfer scheduling and path reservations in research networks
Bulk transfer scheduling and path reservations in research networksBulk transfer scheduling and path reservations in research networks
Bulk transfer scheduling and path reservations in research networks
 
A PSO-Based Subtractive Data Clustering Algorithm
A PSO-Based Subtractive Data Clustering AlgorithmA PSO-Based Subtractive Data Clustering Algorithm
A PSO-Based Subtractive Data Clustering Algorithm
 
A0360109
A0360109A0360109
A0360109
 
B0330811
B0330811B0330811
B0330811
 
E01113138
E01113138E01113138
E01113138
 
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing
Max Min Fair Scheduling Algorithm using In Grid Scheduling with Load Balancing
 
C0312023
C0312023C0312023
C0312023
 
Extending network lifetime of wireless sensor
Extending network lifetime of wireless sensorExtending network lifetime of wireless sensor
Extending network lifetime of wireless sensor
 
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
Modeling and Optimization of Resource Allocation in Cloud [PhD Thesis Progres...
 
IRJET- Review of Existing Methods in K-Means Clustering Algorithm
IRJET- Review of Existing Methods in K-Means Clustering AlgorithmIRJET- Review of Existing Methods in K-Means Clustering Algorithm
IRJET- Review of Existing Methods in K-Means Clustering Algorithm
 
Qo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentQo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environment
 
A novel scheduling algorithm for cloud computing environment
A novel scheduling algorithm for cloud computing environmentA novel scheduling algorithm for cloud computing environment
A novel scheduling algorithm for cloud computing environment
 
Multiple dag applications
Multiple dag applicationsMultiple dag applications
Multiple dag applications
 

Andere mochten auch (9)

16 18
16 1816 18
16 18
 
35 38
35 3835 38
35 38
 
109 115
109 115109 115
109 115
 
6 11
6 116 11
6 11
 
44 49
44 4944 49
44 49
 
41 45
41 4541 45
41 45
 
1 5
1 51 5
1 5
 
130 133
130 133130 133
130 133
 
116 121
116 121116 121
116 121
 

Ähnlich wie 20 26

RSDC (Reliable Scheduling Distributed in Cloud Computing)
RSDC (Reliable Scheduling Distributed in Cloud Computing)RSDC (Reliable Scheduling Distributed in Cloud Computing)
RSDC (Reliable Scheduling Distributed in Cloud Computing)IJCSEA Journal
 
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...csandit
 
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...Editor IJCATR
 
Independent tasks scheduling based on genetic
Independent tasks scheduling based on geneticIndependent tasks scheduling based on genetic
Independent tasks scheduling based on geneticambitlick
 
Use of genetic algorithm for
Use of genetic algorithm forUse of genetic algorithm for
Use of genetic algorithm forijitjournal
 
Task Scheduling using Hybrid Algorithm in Cloud Computing Environments
Task Scheduling using Hybrid Algorithm in Cloud Computing EnvironmentsTask Scheduling using Hybrid Algorithm in Cloud Computing Environments
Task Scheduling using Hybrid Algorithm in Cloud Computing Environmentsiosrjce
 
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...ijcsit
 
A bi objective workflow application
A bi objective workflow applicationA bi objective workflow application
A bi objective workflow applicationIJITE
 
Adaptive check-pointing and replication strategy to tolerate faults in comput...
Adaptive check-pointing and replication strategy to tolerate faults in comput...Adaptive check-pointing and replication strategy to tolerate faults in comput...
Adaptive check-pointing and replication strategy to tolerate faults in comput...IOSR Journals
 
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...ijgca
 
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...ijgca
 
Job Scheduling on the Grid Environment using Max-Min Firefly Algorithm
Job Scheduling on the Grid Environment using Max-Min  Firefly AlgorithmJob Scheduling on the Grid Environment using Max-Min  Firefly Algorithm
Job Scheduling on the Grid Environment using Max-Min Firefly AlgorithmEditor IJCATR
 
Sharing of cluster resources among multiple Workflow Applications
Sharing of cluster resources among multiple Workflow ApplicationsSharing of cluster resources among multiple Workflow Applications
Sharing of cluster resources among multiple Workflow Applicationsijcsit
 
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...Editor IJCATR
 
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...Editor IJCATR
 
Qo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentQo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentAlexander Decker
 

Ähnlich wie 20 26 (20)

RSDC (Reliable Scheduling Distributed in Cloud Computing)
RSDC (Reliable Scheduling Distributed in Cloud Computing)RSDC (Reliable Scheduling Distributed in Cloud Computing)
RSDC (Reliable Scheduling Distributed in Cloud Computing)
 
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...
Fault-Tolerance Aware Multi Objective Scheduling Algorithm for Task Schedulin...
 
Grid computing for load balancing strategies
Grid computing for load balancing strategiesGrid computing for load balancing strategies
Grid computing for load balancing strategies
 
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...
Propose a Method to Improve Performance in Grid Environment, Using Multi-Crit...
 
Independent tasks scheduling based on genetic
Independent tasks scheduling based on geneticIndependent tasks scheduling based on genetic
Independent tasks scheduling based on genetic
 
Use of genetic algorithm for
Use of genetic algorithm forUse of genetic algorithm for
Use of genetic algorithm for
 
Task Scheduling using Hybrid Algorithm in Cloud Computing Environments
Task Scheduling using Hybrid Algorithm in Cloud Computing EnvironmentsTask Scheduling using Hybrid Algorithm in Cloud Computing Environments
Task Scheduling using Hybrid Algorithm in Cloud Computing Environments
 
N0173696106
N0173696106N0173696106
N0173696106
 
ausgrid 2005
ausgrid 2005ausgrid 2005
ausgrid 2005
 
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...
AN ENTROPIC OPTIMIZATION TECHNIQUE IN HETEROGENEOUS GRID COMPUTING USING BION...
 
A bi objective workflow application
A bi objective workflow applicationA bi objective workflow application
A bi objective workflow application
 
Adaptive check-pointing and replication strategy to tolerate faults in comput...
Adaptive check-pointing and replication strategy to tolerate faults in comput...Adaptive check-pointing and replication strategy to tolerate faults in comput...
Adaptive check-pointing and replication strategy to tolerate faults in comput...
 
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
 
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
GROUPING BASED JOB SCHEDULING ALGORITHM USING PRIORITY QUEUE AND HYBRID ALGOR...
 
Job Scheduling on the Grid Environment using Max-Min Firefly Algorithm
Job Scheduling on the Grid Environment using Max-Min  Firefly AlgorithmJob Scheduling on the Grid Environment using Max-Min  Firefly Algorithm
Job Scheduling on the Grid Environment using Max-Min Firefly Algorithm
 
Sharing of cluster resources among multiple Workflow Applications
Sharing of cluster resources among multiple Workflow ApplicationsSharing of cluster resources among multiple Workflow Applications
Sharing of cluster resources among multiple Workflow Applications
 
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...
Efficient Resource Management Mechanism with Fault Tolerant Model for Computa...
 
genetic paper
genetic papergenetic paper
genetic paper
 
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...
Bragged Regression Tree Algorithm for Dynamic Distribution and Scheduling of ...
 
Qo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environmentQo s aware scientific application scheduling algorithm in cloud environment
Qo s aware scientific application scheduling algorithm in cloud environment
 

Mehr von Ijarcsee Journal (20)

122 129
122 129122 129
122 129
 
104 108
104 108104 108
104 108
 
99 103
99 10399 103
99 103
 
93 98
93 9893 98
93 98
 
88 92
88 9288 92
88 92
 
82 87
82 8782 87
82 87
 
78 81
78 8178 81
78 81
 
73 77
73 7773 77
73 77
 
65 72
65 7265 72
65 72
 
58 64
58 6458 64
58 64
 
52 57
52 5752 57
52 57
 
46 51
46 5146 51
46 51
 
36 40
36 4036 40
36 40
 
28 35
28 3528 35
28 35
 
24 27
24 2724 27
24 27
 
19 23
19 2319 23
19 23
 
12 15
12 1512 15
12 15
 
134 138
134 138134 138
134 138
 
125 131
125 131125 131
125 131
 
114 120
114 120114 120
114 120
 

Kürzlich hochgeladen

Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 

Kürzlich hochgeladen (20)

Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 

20 26

  • 1. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 Grid Scheduling Using PSO with SPV Rule Kuldeep Kaur M.TECH(CSE) Department of Computer Science and Engineering Baby2impressive@yahoo.co.in Lovely Professional University, Punjab, India Mr. Sudhanshu Prakash Tiwari Department of Computer Science and Engineering Lovely Professional University, Punjab, India Abstract 1. Its ability to make more cost-effective Grid computing can be defined as applying use of a given amount of computer the resources of many computers in a network resources. to a problem which requires a great number of 2. It is a way to solve problems that can't computer processing cycles or access to large be approached without an enormous amounts of data. However, in the field of grid amount of computing power. computing scheduling of tasks is a big 3. Because it suggests that the resources challenge. The task scheduling problem is the of many computers can be problem of assigning the tasks in the system cooperatively and perhaps in a manner that will optimize the overall Synergistically harnessed and managed as performance of the application, while collaboration toward a common objective. assuring the correctness of the result. Each Grid computing can be used to compute large day new algorithms are proposed for number of tasks on the resources which are assigning tasks to the resources. This is also a geographically remotely located. Task boon for the grid computing. In this paper we scheduling is a challenging problem in grid use the technique of Particle Swarm computing environment. Many parallel Optimization (PSO) with SPV (Shortest applications consist of multiple computational position value) rule to solve the task components. While the execution of some of scheduling problem in grid computing. The these components or tasks depends on the aim of using this technique is use the given completion of other tasks, others can be resources optimally and assign the task to the executed at the same time, which increases resources efficiently. The simulated results parallelism of the problem. show that PSO with SPV rule proves to be a Abraham et al and Braun et al [1] address the better algorithm when applied to resource dynamic scheduling of jobs to the allocation and disk scheduling in grid geographically distributed computing computing. resources. They provide an introduction of computational grids followed by a brief Keywords: Grid scheduling; PSO with SPV description of the three nature’s heuristics rule; SPV Rule; Tasks; Resources namely Genetic Algorithm (GA), Simulated Annealing (SA) and Tabu Search (TS). I. INTRODUCTION Yang gao et al [2] proposed two algorithms that use the predictive models to schedule Grid computing is a network that is not in jobs at both system level and application the same place but distributed resources such level. as computers, peripherals, switches, M Aggrawal et al [3] presented a Genetic instruments, and data. Grid computing Algorithm based scheduler. The proposed appears to be a promising trend for three scheduler used in both the intra-grid of a large reasons: organization and in a research grid consisting 20 All Rights Reserved © 2012 IJARCSEE
  • 2. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 of large clusters, connected through a high because now inefficient resource allocation bandwidth dedicated network. can greatly hamper the efficiency and Shanshan Song et al[4] proposed a new throughput of the scheduler. Space-Time Genetic Algorithm (STGA) for To formulate the problem, define Ta trusted job scheduling in which they consider a={1,2,3,…X } as x independent tasks three security-driven heuristic modes: secure, permutation and Rb b={1,2,3,…y } as y risky and f -risky. computing resources. Suppose that the Lee Wang et al [5] developed a heuristic processing time Pa,b for task a computing on based approach to matching and scheduling in b resource is known. The completion time heterogeneous computing environment. F(x) represents the total cost time of Lin Jian Ning et al [6] scheduling-algorithm completion. based on genetic algorithm (GA) is addressed. The objective is to find an permutation In this paper simulated results prove that matrix m = (Mab) , with Mab =1 if resource PSO with SPV rule proves to be better when a performs task b and if otherwise, Mab=0, it is applied for resource allocation in the field which minimizes the total costs. of grid computing. This paper is organized as follows. In section 2 the issues related to task F(x)=ΣΣPa,b * Mab (1) scheduling is discussed. In section 3 particle swarm algorithm is introduced. In section 4 Subject to we implement PSO with SPV rule for grid Σ Mab=1,∀ b∈ T , (2) task scheduling problem. In section 5 we see the simulation result of work done in section Mab∈ { 0,1}, ∀ a∈ R, b∈ T (3) 4. The minimal F(x) represents the length of schedule whole tasks working on available II. TASK SCHEDULING ISSUES IN resources. The scheduling constraints (2) GRID COMPUTING guarantee that each task is assigned to exactly one resource. Computational grid can be combination of hardware and software that can be used to III. PARTICLE SWARM solve complex computational problems. The OPTIMIZATION resource in a computational grid can be anything which can be used to solve the given The particle swarm optimization algorithm, problem. For example a set of printers which originally introduced in terms of social and are used for printing a set a documents. The cognitive behavior by Kennedy and Eberhart overall objective of task scheduling is to (1995), solves problems in many fields, minimize the completion time and to utilize especially engineering and computer science. the resources effectively and usually it is easy The individuals, called particles henceforth, to get the information about the ability to are flown through the multi-dimensional process data of the available resource. search space with each particle representing a The problem of task scheduling arises in a possible solution to the multi-dimensional situation where there are more tasks than the optimization problem. Each solution's fitness available resources. Consider a scenario is based on a performance function related to wherein there are x, x={1,2,3,4,........X} tasks the optimization problem being solved. The to be done and there are y, y={1,2,3,4.......Y} movement of the particles is influenced by resources available. With the condition that two factors using information from iteration- the task is not allowed to be migrated between to-iteration as well as particle-to-particle. As resources. a result of iteration-to- iteration information, In such a situation if we have y>x then the particle stores in its memory the best there is no reason for developing new solution visited so far, called pbest , and algorithms for task scheduling because then experiences an attraction towards this solution resources can be allocated to the tasks on first as it traverses through the solution search come first serve basis.But if y<x then we need space. As a result of the particle-to-particle to develop new algorithms for task scheduling interaction, the particle stores in its memory 21 All Rights Reserved © 2012 IJARCSEE
  • 3. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 the best solution visited by any particle, and Eberhart, 1998). The resulting velocity update experiences an attraction towards this equation becomes: solution, called gbest , as well. The first and second factors are called cognitive and social components, respectively. After each vid = w * vid + c1 r1( pid - xid) + c2r2( pgd -xid) iteration, the pbest and gbest are updated for each particle if a better or more dominating (6) solution (in terms of fitness) is found. This process continues, iteratively, until either the Eberhart and Shi (2000) indicate that the desired result is converged upon, or it is optimal strategy is to initially set w to 0.9 and determined that an acceptable solution cannot reduce it linearly to 0.4, allowing initial be found within computational limits. For an exploration followed by acceleration toward n-dimensional search space, the ith particle of an improved global optimum. the swarm is represented by an n-dimensional vector, Xi= (xi1 ,xi2 .....xin )T . The velocity of IV. PROPOSED METHODOLOGY this particle is represented by another n- dimensional vector Vi = (vi1; vi2...... vin )T . In this paper we have proposed a solution for The previously best visited position of the ith grid scheduling using PSO with SPV rule. For particle is denoted as Pi = (pi1, pi2,........pin )T . solving any optimization problem we have to `g' is the index of the best particle in the first formulate the problem according to swarm. The velocity of the ith particle is optimization problem. In this case first we updated using the velocity update equation formulate the grid scheduling problem given by according to PSO algorithm. Next subsection describes how we formulate the grid scheduling problem. vid = vid +c1r1( pid - xid) + c2r2( pgd -xid) V. REPRESENTATION (4) To solve the problem, representation of the individual and fitness value is required. PSO and the position is updated using with SPV rule algorithm is based on population (candidate solution) and each xid= xid + vid population have its own fitness value according to which it is compared from (5) others, so we have to first represent the grid scheduling problem in terms of PSO with where d = 1, 2....n ; i = 1; 2....S , where S SPV rule.In grid scheduling, we have a set of is the size of the swarm; c1 and c2 are tasks and a set of resources as input and a constants, called cognitive and social scaling sequence, which informs that which task is to parameters respectively (usually, c1 = c2 ; r1 , be operated on which resource and in which r2 are random numbers, uniformly distributed order as output. PSO with SPV rule is based in [0, 1]). Equations (4) and (5) are the initial on population concept and each individual in version of PSO algorithm. A constant, Vmax, is population represents a solution, in case of used to arbitrarily limit the velocities of the grid scheduling problem, solution is a particles and improve the resolution of the sequence of tasks which are to be performed. search. Further, the concept of an inertia So we have to first formulate each individual weight was developed to better control of PSO with SPV rule. exploration and exploitation. The motivation Grid task scheduling problem is a discrete was to be able to eliminate the need for Vmax . optimization problem. In the proposed The inclusion of an inertia weight (w) in the solution continuous version of PSO is used particle swarm optimization algorithm was instead of discrete version. To change the first reported in the literature in 1998 (Shi and continuous version to real version for grid task scheduling problem SPV rule is used. 22 All Rights Reserved © 2012 IJARCSEE
  • 4. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 Using the SPV (shortest position value) rule Table1: Values of position vector, sequence continuous position generated by PSO is and set of resources. converted to discrete value. Dimension Xid Sid Rlm We represent dimension as a number of 0 7.83 9 4 task and value as an initial sequence from the possible set of sequences to find optimal 1 -0.65 0 0 sequence. Position vector Xid={x1,x2,x3,......xd} 2 2.90 4 4 where i is the particular individual and d 3 5.46 7 2 represents the dimension index, is calculated 4 1.25 3 3 using PSO. The position vector of each particle makes transformation about the 5 4.87 6 1 continuous position. Smallest position value 6 -0.48 1 1 i.e. SPV rule is used to find a permutation 7 0.39 2 2 corresponding position Xid. The position 8 6.0 8 3 vector Xid has continuous values. By using the 9 3.28 5 0 SPV rule this continuous position value can be converted to discrete value permutation VI. FITNESS FUNCTION Sid=[si1, si2,…….sid].Sidis the sequence of task of i particle in the processing order with After representation of each individual we respect to the d dimension. have to calculate fitness value of each Set of resources is represented by individual. On the basis of fitness value we Rlm={r1,r2,r3......ry}, where l represents a determine the optimal solution. In case of grid particle/ sequence and m represents the tasks scheduling problem optimal solution is the which are assigned to a resource. After Sid, set minimization the value of equation. of resources is calculated using equation (7). Our main objective is to minimize the fitness value, an individual who have the minimum Rlm=Sid mod M (7) fitness value is considered as the optimal solution. i.e. value of task set mod Total resources VII. ALGORITHM Resource id is given to each resource so that they can be easily differentiated from one Grid scheduling using PSO with SPV Rule other. Such as r1 is the resource id of first resource. For e.g. if we have 10 tasks which To solve the grid scheduling problem we have are to be performed on 5 available resources used the Particle Swarm Optimization (PSO) then we have dimension value as 10.Based on with SPV rule. We set an initial population by SPV rules, the continuous position convert to selecting random starting sequences from the a permutation of sequences Sid, which is a set of x! Sequences; where x is the total sequence of task simplified by the particle Xid. number of tasks. After getting the initial Position vector Xid is calculated using PSO particle we calculate fitness value of each is={4.83,-0.55,1.90,3.46,1.05,2.87,- particle, according to equation. After that we 0.28,0.19,4.0,2.28} calculate best among the entire particle and Then using SPV rule transformation of set it as an initial global best. position vector Xid to Sid, we have Sid value as PSO update equation is used to update old {9,0, 4, 7,3,6,1,2,8,5}. population and generate new sequences and Equation (7) is then used to determine the then their resources are calculated. This associated resources for the calculated tasks sequence, along with its resource is then used in the sequence. We can calculate the to find the fitness value of each individual of resource set as {4, 0, 4, 2, 3, 1, 1, 2, 3, 0} each particle of the population. Algorithm 1 is The table1 represents the dimension values of the proposed algorithm for the grid position vector Xid , sequence Sid and Set of scheduling problem. resource Rlm. 23 All Rights Reserved © 2012 IJARCSEE
  • 5. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 Algorithm for Grid Scheduling using PSO maximum function evaluation, which is 20,000 in our experiment. The fourth control with SPV Rule parameter is Dimension and it depends upon the number of tasks. The next control parameter is the value of c1 & c2 which we [Initialsation Phase] have taken as 1.14. And w (Inertia weight) is For s=0 to Swarm size do also a control parameter and we have taken its For d=0 to dimension size do value as 0.7. Randomly initialize particle Using SPV rule a task sequence is Compute resource for that IX. EXPERIMENTAL RESULTS particle/sequence generated End for d In this section we analyze the result obtained Compute fitness of initialized particle by our algorithm. To test the efficiency of our Compute global best algorithm results of PSO with SPV rule is End for s compared with Genetic algorithm (GA) [Update Phase] results. In a grid scheduling task we already Repeat have the information about the number of For s=0 to each swarm size do resources, number of tasks, and the amount of For d=0 to problem dimension do time that will be taken by a resource to Update particles using PSO update equation complete a task. We just need to find the A new sequence is generated using SPV rule sequence which will provide us the optimal Compute resources for that sequence results. We conducted the experiment by end for d varying the number of resources as well as Compute fitness of updated particle varying the number of tasks and then we if needed update historical information for compared our results with that of GA. In global best(Pg) particular, we have taken three cases in which endfor s we have taken different number of resources untill(stopping criteria is not met) and tasks. Experiment 1: Here, we are assuming there are 5 resources and 17 tasks. Following are VIII. EXPERIMENTAL SETUP the execution time (in units) taken by PSO with SPV and GA. For every algorithm there are some control parameters which are used for its efficient Table2: Execution time calculated by GA and working. Hence, there are some controls PSO with SPV rule for17 tasks by 5 resources parameters for PSO with SPV rule also. We did an extensive literature survey and carried Genetic Particle Swarm out our own experiments for determining the Algorithm Optimization with values of these control parameters. From this (GA) Shortest Position we found that the values which we have taken Value (PSO with in this experiment are standard values and SPV) they are also suitable for this experiment. 3078.0 3074.0 The first control Parameter is Maximum function evaluation and the value of this parameter we have taken in our experiment as The sequence generated by GA is: 14, 8, 0, 20,000. The next parameter in our experiment 16, 4, 13, 6, 1, 3, 9, 11, 15, 12, 10, 5, 7, 2. is maximum number of population and we have taken its value to be 40. Another control The sequence generated by our proposed PSO parameter is number of runs and we have with SPV rule is: 4, 12, 7, 14, 2, 13, 6, 8, 10, taken its value in our experiment as 30. It 15, 1, 0, 9, 3, 5, 16, 11. must be noted that each run contains 24 All Rights Reserved © 2012 IJARCSEE
  • 6. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 Experiment 2: Here, we are assuming there From the table 2, table 3, table 4, it is clear are 10 resources and 27 tasks. The execution that PSO with SPV rule takes less execution time (in units) taken by GA and PSO with time than the GA algorithm. SPV rule are: X. CONCLUSION Table3: Execution time calculated by GA and PSO with SPV rule for27 tasks by 10 It can be concluded from the results that resources proposed PSO with SPV rule performs better than the GA algorithm. The procedure followed in grid scheduling consists of the Genetic Particle Swarm generation of the population according to the Algorithm (GA) Optimization with algorithm, then the task sequence and Shortest Position resources associated with the task sequence Value (PSO with SPV) are generated and the positions, task sequence 5365.0 5357.0 and resource set are updated and then the globally best position or sequence is calculated. It is repeated again and again till The sequence generated by GA the maximum number of function evaluation. is:24,9,7,2,26,0,8,13,3, 18, 10, 1, 23, 5, 17, As future work we have the intention to apply 14, 4, 15, 12, 6, 16, 20, 11, 22, 25, 19, 21. other types of nature inspired algorithms to the grid scheduling problem, comparing their The sequence generated by our proposed PSO results with the ones accomplished by the with SPV rule is: 14, 19, 1, 9, 0, 7, 24, 6, 8, PSO with SPV rule. 10, 15, 5, 13, 12, 26, 4, 11, 2, 22, 18, 17, 3, XI. REFERENCES 16, 21, 23, 20, 25. [1] Foster and C. Kesselman (editors), The Experiment 3: Here, we are assuming there Grid: Blueprint for a Future Computing are 12 resources and 30 tasks. The execution Infrastructure, Morgan Kaufman time (in units) taken by GA and PSO with Publishers, USA, 1999. SPV rule are: [2] Abraham, R. Buyya and B. Nath, Nature's Table4: Execution time calculated by GA and Heuristics for Scheduling Jobs on PSO with SPV rule for 30 tasks by 12 Computational Grids, The 8th IEEE resources International Conference on Advanced Computing and Genetic Particle Swarm Communications(ADCOM 2000), pp. 45- Algorithm Optimization with 52, December 2000. (GA) Shortest Position Value (PSO with [3] Y. Gao, H.Q Rong and J.Z. Huang, SPV) Adaptive grid job scheduling with genetic 6081.0 5834.0 algorithms, [4] Future Generation Computer Systems Elsevier, pp.151-161,2005. The sequence generated by GA is: 28, 14, 20, 25, 10, 7, 17, 4, 9, 22, 6, 11, 24, 18, 0, 29, 15, [5] M. Aggarwal, R.D. Kent and A. Ngom, 1, 26, 12, 13, 19, 29, 5, 3, 27, 2, 21, 16, 8. Genetic Algorithm Based Scheduler for Computational Grids, in Proc. of the 19th The sequence generated by our proposed PSO Annual International Symposium on High with SPV rule is: 11, 22, 0, 29, 1, 25, 24, 17, Performance Computing Systems and 26, 9, 2, 15, 6, 4, 19, 21, 7, 18, 28, 8, 10, 3, Application (HPCS’05),pp.209-215, May 13, 27, 23, 5, 16, 14, 20, 12. 2005. 25 All Rights Reserved © 2012 IJARCSEE
  • 7. ISSN: 2277 – 9043 International Journal of Advanced Research in Computer Science and Electronics Engineering Volume 1, Issue 5, July 2012 [6] S. Song, Y. Kwok, and K. Hwang, Computation, Piscataway, pp. 69-73, Security-Driven Heuristics and A Fast 1998. Genetic Algorithm for Trusted Grid Job [14] R. C. Eberhart and Y. Shi, Comparing Scheduling, in Proc. of 19th IEEE inertia weights and constriction factors in International Parallel and Distributed particle swarm optimization Congress on Processing Symposium (IPDPS’05), Evolutionary Computing, vol. 1, pp. 84- pp.65-74, April 2005. 88, 2000. [7] Lee Wang, Howard Jay Siegel, Vwani P. Roychowdhury, and Anthony A. Maciejewski, Task Matching and Scheduling in Heterogeneous Computing  Kuldeep Kaur received her Msc(IT) Environments Using a GeneticAlgorithm Degree from Guru Nanak Dav University, Based Approach, Journal of Parallel and Amritsar and M.TECH(CSE) Degree from Distributed Computing , Citeseer47, pp.8- Lovely Professional University in 2010 and 22, 1997 2012 respectively. Her Research Interests [8] Zhang, L.; Chen, Y.; Sun, R.; Jing, S. & include Grid Computing, Soft Yang, B. A task scheduling algorithm Computing,Software Engineering and based on pso for grid computing wireless network,etc. International Journal of Computational Intelligence Research, 4, 37-43, 2008. [9] Nath B, Lim S, Bignall R J, A Genetic Algorithm For Scheduling Independent Jobs OnUniform Machines With Multiple Objectives, Proceedings of the International Conference on Computational Intelligence and Multimedia Applications, Australia, pp.  Mr.Sudhanshu Prakash Tiwari has done 67-74, 1998. M.TECH(CSE).He is assistant professor of [10] J. Kennedy and R. Eberhart, “Particle Department of Computer Science and swarm optimization”, in Proc. IEEE Engineering in Lovely Professional International Conference Neural University. Networks, vol. 4, pp. 1942 – 1948, 1995. [11] Lin JianNing and Wu HuiZhong ,Scheduling in Grid Computing Environment Based onGenetic Algorithm, Journal of Computer Research and Development,pp.2195-2199,Vol. 4,No.12,Dec 2004. [12] Wright, A. Genetic Algorithms for Real Parameter Optimization, Foun-dations of Genetic Algorithms, G. Rswlins(Ed.), Morgen Kaufmann publishers, CA, pp.205-218, 1991. [13] Y. Shi and R. C. Eberhart, “A modified particle swarm optimizer”, in Proc. IEEE International Conference on Evolutionary 26 All Rights Reserved © 2012 IJARCSEE