Resource Allocation in Cloud Computing Using Hybrid Algorithm

resource allocation and scheduling in cloud computing policy and algorithm and resource allocation in cloud computing model and algorithm
Dr.JohnGates Profile Pic
Published Date:09-11-2017
Your Website URL(Optional)
I.J. Intelligent Systems and Applications, 2015, 08, 59-64 Published Online July 2015 in MECS ( DOI: 10.5815/ijisa.2015.08.08 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm V.Suresh Kumar Research Scholar, M S University Tirunelveli, Tamilnadu, India E-mail: M. Aramudhan Department of Information Technology, Perunthalaivar Kamarajar Engineering College, Pondicherry, India Abstract— Cloud computing is experiencing rapid advancement to cloud environment to resources so that total response in academia and industry. This technology offers distributed, time in makespan, is reduced 3. Task scheduling is virtualized and elastic resources as utilities for end users and allocating one or more time intervals to one or more can support full recognition of “computing as a utility” in the resources. Scheduling is a problem of scheduling future. Scheduling distributes resources among parties which submitted tasks set from different users on computing simultaneously and asynchronously seek it. Scheduling resources to reduce a specific job’s completion time or algorithms are meant for scheduling and they reduce resource system makespan. Many parameters are factors for starvation ensuring fairness among those using resources. Most scheduling problems like system throughput, load Task-scheduling cloud computing procedures consider task resource requirements for CPU and memory, and not bandwidth. balancing, service cost, service reliability, and system use. This study suggests optimizing scheduling with BAT-Harmony search hybrid algorithm. Application Index Terms— Cloud Computing, Task Scheduling, BAT Algorithm, Harmony Search Platform I. INTRODUCTION Cloud computing uses central remote servers and internet for data and applications maintenance. It permits Unified Resource consumers to use applications sans installation and access personal files at a computer having internet access. This ensures more efficient computing through centralizing memory, storage, processing and bandwidth 1. Cloud Fabric computing is “a type of parallel and distributed system in a collection of inter-connected and virtualized computers Fig. 1. Cloud Architecture dynamically provisioned and accessed as one or more unified computing resources established on Service Level Scheduling is a set of policies controlling order of Agreement (SLA), via negotiation between service work a computer system has to perform. Various provider and consumer”. scheduling algorithm exist in distributed computing, and Due to benefits like elastic and scalable on-demand job scheduling is one. The advantage of job scheduling resources, Cloud service users explore ability of scalable algorithm is achieving high performance computing and platforms for efficient and cost-effective execution of best system throughput. Scheduling manages CPU applications like e-commerce, High Performance memory availability. A good scheduling policy ensures Computing (HPC), social network and web applications. maximum resource use 4. Job grouping based For successful Cloud resources use, applications should scheduling is dynamic scheduling strategy maximizing adapt to the new environment and new scheduling resources use, processing capabilities and reducing solutions should be developed to ensure good overhead time and cost to execute jobs. performance. So also, Cloud providers should determine Job scheduling considers: (i) processing requirements proper configurations and scheduling policies for proper for a job, (ii) jobs grouping mechanism, called job use of computational, networks and storage resources like grouping, according to resources processing capabilities, different applications that are executed both concurrently and (iii) job grouping transmission to correct resource 5. and in isolation 2. The scheduler orders jobs so that balance between To ensure that cloud services are effective as provider improving quality of services and simultaneously infrastructure, task scheduling algorithm is a major maintaining jobs efficiency and fairness is maintained. So, requirement. They are responsible to map jobs submitted evaluating scheduling algorithms performance is crucial Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64 60 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm to realizing large-scale distributed systems. Despite Many-tasks workflow scheduling in a distributed various scheduling algorithms for cloud environment, no computing platform is a NP-hard problem which is even comprehensive performance study providing a unified more complex and challenging when virtualized clusters platform for comparing such algorithms exists 6. execute many tasks on a cloud computing platform. The As Cloud computing Systems users increased, tasks to difficulty is in satisfying multiple objectives that may be be scheduled also increased proportionally. So, better conflicting in nature. It is difficult to minimize many algorithms to schedule tasks on systems are required. tasks makespan, when reducing resource cost and Algorithms to schedule tasks are service oriented and preserving fault tolerance and/or Quality of Service (QoS) differ according to environments 7. Cloud computing simultaneously. Such requirements and goals are hard to Task Scheduling algorithms minimize tasks makespan optimize due to unknown runtime conditions, like with minimum resources. Cloud computing, uses low- resources availability and random workload distributions power hosts to ensure high usability. Cloud computing is 12. a class of systems and applications using distributed Usually, standard BA algorithm exploits search space, resources to function in a decentralized way. but sometime is trapped in local optima and so cannot Available resources must be used efficiently without perform global search well. For BA, search depends on affecting service parameters of cloud. Cloud scheduling random walks and hence fast convergence is not process service parameters are generalized in 3 stages guaranteed. This study proposes a hybrid algorithm for namely 8, BAT-Harmony search for scheduling optimization in 1. Resource discovering and filtering - Datacenter cloud computing. The rest of the study is as follows: Broker notices resources in network and gets their Section 2 reviews related works in literature. Section 3 status information. explains methods used in the proposed work; Section 4 2. Resource selection - Target resource selection is based discusses experiments and results and Section 5 on task and resource parameters. This is a deciding concludes the work. stage 3. Task submissions - Tasks are submitted to selected resources II. RELATED WORK Task scheduling is a famous combinatorial A service flow scheduling with various QoS optimization problem. The aim is determining a proper requirements in cloud computing was proposed by Liu et sequence during task execution while obeying some al., 13, adopting an Ant Colony Optimization (ACO) (transaction logic) constraints. As an optimization algorithm to improve service flow scheduling. In the new problem, getting an optimal packing (allocation) scheme model, default rate described radio of cloud service needs huge computation time. After a resource provider breaking SLA, and introduced SLA module to calculation algorithm determines mapping scenarios to monitor cloud services running state. satisfy QoS requirements, an actual resource allocation The relation between infrastructure components and algorithm maps task demands to available resources 9. power consumption of cloud computing environment was The target of scheduling is maximizing resource use studied by Luo et al., 14, who discussed task types and lowering tasks process time. An efficient job matching and component power adjustment methods. A scheduling strategy must yield less response time 10 to Cloud Computing resource scheduling algorithm built on ensure that jobs execution takes place in a stipulated time. energy efficient optimization methods was presented. Simultaneously there is an occurrence of in time resource Experiments proved that jobs that used hardware reallocation. Due to this, jobs take place and more jobs environment had energy consumption reduced by the new are submitted to cloud by clients which results in algorithm. accelerating cloud system’s business performance. Many An ACO based job scheduling algorithm, adapted to scheduling algorithms are available and the most popular dynamic cloud computing characteristics that integrated are discussed below. specific ACO advantages in NP-hard problems was FCFS is First Come First Serve algorithm where first proposed by Song et al., 15. It aimed to reduce job data reaching queue first is executed first. The round completion time based on pheromone. Experiments robin algorithm has an advantage over FCFS algorithm. showed that ACO algorithm is promising for job It allocates a process or task with a time slot and after this, scheduling in cloud computing environments. the job is changed and the next job comes to execution. System service cost and task scheduling algorithms of Priority scheduling algorithm discards FCFS and round optimizing resource was studied by Wng et al., 16. robin algorithm’s disadvantages. In this algorithm each Besides, it also proposed a mathematical model of job’s priority is decided based on tasks properties 11. Dynamic Service-quality Cost (DSC) which in real-time Hybrid algorithm uses FCFS and priority algorithm synthetically measures service cost and node's service where a job queue has only one algorithm to be done, performance in cloud computing. Further, it also when it goes for FCFS algorithm but when the next presented a complexity-aware optimization task algorithm reaches the queue, it checks jobs priority and scheduling algorithm. Finally, experiments proved the reschedules tasks accordingly. A hybrid approach is proposed algorithm’s reasonability and effectiveness. It always better than a single approach. achieved not only reduced service cost but also increased service quality by reasonably assigning tasks to nodes for Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm 61 calculation in cloud computing. And results were scheduling problem, and hence it used the unused free consistent with theoretical analysis. space economically. A PSO based heuristic to schedule applications to A Period ACO (PACO) based scheduling algorithm, to cloud resources that considered computation cost and solve task scheduling problems in cloud computing was data transmission cost was presented by Pandey et al., proposed by Sun et al., 23. PACO used ACO algorithm 17. A workflow application was experimented on in cloud computing, with first proposed scheduling period varying computation and communication cost. Cost strategy and improvement of pheromone intensity savings when using PSO was compared with Best updated strategy. Experiment showed that PACO ensured Resource Selection (BRS) algorithm. Results revealed good performance in makespan and load balance of the that PSO achieved: (a) three times more cost savings total cloud cluster. compared to BRS, and (b) also resulted in good workload A new framework built combining computing distribution. resources on Cloud computing and computing Use of working scheduling models to improve resource components in local systems was presented by Man and allocation in cloud computing was suggested by Chen Huh 24. The framework’s main component is cost with and Tseng 18. However, cloud computing and resources finish time-based scheduling algorithm that balanced distribution is more responsive with applications needing application schedule performance and mandatory cost for to be more time and resources optimal oriented. Authors use of Cloud resources. Experiments and comparison analog users in accordance with demand work category with the other scheduling approaches proved benefits of parameters, and scheduling parameters to access Internet the new algorithm. usage or take single time to work the parameter, by An architecture based on collaboration between thin- queuing theory for scheduling models like demand, thick clients and clouds that provided effective task scheduling parameters to model, generating reference scheduling which boosted processing time in mobile data, through data analysis to compare various scheduling cloud platform was proposed by Hung et al., 25 while characteristics. Cloud computing systems future is a considering network bandwidth and cost for cloud service frame of reference to build own cloud computing models. usage. Experiments showed improved efficiency of task A new method to solve problem by applying stochastic scheduling in ensuring desired processing time that integer programming for ideal resource scheduling in corresponded to customer’s money. cloud computing was proposed by Li and Guo 19. An optimization model for task scheduling for Applying Grobner bases theory to solve stochastic integer reducing energy consumption in cloud-computing data programming problem and experimental results of centers was presented by Liu et al., 26. The new implementation are presented. approach was formulated as an integer programming A Least Languages First Min-Min (LLFMM), problem to lower cloud-computing data center energy algorithm based scheduling algorithm, suitable to consumption by scheduling tasks to a minimum servers multilingual information resources to improve while keeping task response time constraints. information resources scheduling performance in cloud Additionally, the most efficient server first task- computing was proposed by Han and Luo 20. scheduling scheme to minimize energy expenditure as a Concurrent Scheduling Marking Graph (CSMG) of practical scheduling scheme was formulated. Simulation Colored Dynamic Timed Petri nets (CDTdPN) was show that new task-scheduling scheme reduced server defined and algorithm for constructing CSMG of energy consumption on average over 70 times compared CDTdPN was given. CSMG represented concurrent to energy consumed under a (not-optimized) random- relation of transitions in Petri nets and reduced graph size based task-scheduling scheme. Energy savings were to be constructed to some extent. Finally, example and achieved by reducing allocated servers. simulation revealed that the new scheduling algorithm reduced makespan and that the new modeling and analyzing techniques were convenient to analyze III. METHODOLOGY scheduling system performance. This study proposed a hybrid method using BAT A QoS guided task scheduling model, composed of algorithm and Harmony search algorithm for scheduling scheduling strategies and QoS guided scheduling optimization in cloud computing. Sufferage-min heuristic algorithm was presented by Han et al., 21. Experiment revealed that make span value A. BAT algorithm was successfully shortened. Xin-She Yang in 2010 27 developed BAT algorithm A Multi Queue Scheduling (MQS) algorithm to reduce which exploits the bats echolocation. Bats use sonar cost of reservation and on-demand plans using global echoes to detect/avoid obstacles. Sound pulses are scheduler was proposed by Karthick et al., 22. transformed to a frequency that reflects from obstacles. Scheduling is an important and complex part in cloud Bats use time delay from emission to reflection and use it computing. The new methodology depicted the clustering to navigate. They emit short loud, sound impulses and the concept for jobs based on burst time. The new method pulse rate is defined as 10 to 20 times /sec. After hitting overcame problems and reduced starvation in the process. and reflecting, bats transform own pulse to advantageous The new MQS method gave more importance to job information to measure how far away the prey is. Bats selection dynamically to achieve optimum cloud Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64 62 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm use wavelengths that vary from in range 0.7, 17 mm or Step 2: Evaluate the quality 𝑓 for each bat in 𝑃 inbound frequencies 20,500 kHz. determined by the objective function (𝑥 ). BAT algorithm is based on idealizing bats’ Step 3: While the termination criterion is not satisfied echolocation characteristics which follow approximate or or 𝑡 MaxGeneration do idealized rules 28: Sort the population of bats 𝑃 from best to worst by (1) Bats use echolocation to sense distance, and “know” order of quality 𝑓 for each bat. surroundings in some magical way. Store the KEEP best bats as KEEPBAT. (2) Bats fly randomly with velocity vi and a fixed for 𝑖 = 1:NP (all bats) do frequency fmin at position xi, varying wavelength λ, t t1 t v v() v xQ i i i and loudness A0 to hunt. They spontaneously t t1 t accommodate wavelength (or frequency) of emitted x x v i i i pulses and adjust pulse rate emission r ∈ 0, 1, if (rand 𝑟 ) then depending on target’s proximity. tt xx  u (3) Though loudness changes in different ways, it is supposed that loudness varies from a minimum end if constant (positive) Amin to a large A0. for 𝑗 = 1:𝐷 (all elements) do //Mutate if (rand HMCR) then B. Harmony search r  NP rand  1 Harmony Search (HS) is a music-based meta-heuristic optimization algorithm inspired by observation that music x ( j) x ( j) where r (1,2,...,HMS) vr 1 1 aims to search for a perfect state of harmony. The if (rand PAR) then harmony in music is analogous to finding optimality in x (j) x (j)bw(2  rand1) optimization. Optimization search process is compared to vv a jazz musician’s improvisation process. On one hand, endif perfectly pleasing harmony is determined by audio else aesthetic standards. A musician intends to produce music x ( j)  x rand(x x ) v min,j max,j minj with perfect harmony. Alternatively, an optimal solution endif to an optimization problem is best solution to a problem endfor 𝑗 under given objectives and limited by constraints. Both t t t processes produce best or optimum 29. Evaluate the fitness for the offsprings x,, x x u i v HS algorithm initializes Harmony Memory (HM) with t Select the offspring x with the best fitness k random generated solutions. The solutions stored in HM t t t are defined by Harmony Memory Size (HMS). Then a among the offsprings x,, x x u i v new solution is created as follows iteratively. Every if (rand 𝐴 ) then decision variable is generated on memory consideration tt xx and a possible additional modification, or through rk 1 random selection. Parameters used in generation of a new end if solution are called Harmony Memory Considering Rate Replace the KEEP worst bats with the KEEP (HMCR) and Pitch Adjusting Rate (PAR). Each decision best bats KEEPBAT stored. variable is set to value of corresponding variable of one end for 𝑖 solution in HM with a HMCR probability. Further 𝑡 = 𝑡 + 1; modification of this value is done with a PAR probability Step 4: end while 30. Otherwise (with a probability of 1−HMCR), Step 5: Post-processing the results and visualization; decision variable is set to random value. After a new End solution is generated, it is evaluated and compared to worst HM solution. If its value is better than that of worst Generally Trust establishes/maintains relationship solution, it replaces worst solution in HM. This is between 2 entities for long. Applying trust models to repeated, till a termination criterion is fulfilled. The scheduling decreases failure ratio and reassigns cloud hybrid HS/BA meta-heuristic algorithm is as follows 31: environments. Combining communication trust and data trust locates a component/resource/service’s overall trust Begin when scheduling. Data trust decides resources list to Step 1: Initialization. Set the generation counter 𝑡 = 1; calculate trust and threshold levels to separate trustful and initialize the population of NP bats 𝑃 randomly and untrusted nodes. Communication trust is calculated on each bat corresponding to a potential solution to the client’s bandwidth availability and resource centers. given problem; Bayesian model is used for data fusion and define loudness 𝐴 ; set frequency 𝑄 , the initial communication trusts. Reputation ratings are calculated velocities V, and pulse rate 𝑟 ; by probability density functions based beta reputation set the harmony memory consideration rate HMCR, given by 32, the pitch adjustment rate PAR and bandwidth bw; set maximum of elite individuals retained KEEP. Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm 63 ()    11 f ( p  , ) p (1 p)  ( ) ( ) (1) Where α represents jobs completed and β represents unsuccessful jobs. R is reputation for resource n ij i observed from neighborhood resources n . j R Beta(1,1) ij ij ij (2) Trust value is then calculated using expected reputation value. T E(R ) E Beta(1,1)  ij ij ij ij Fig. 3. Best Fitness achieved. (1) ij V. CONCLUSION  (3) ( 2) ij ij Cloud computing is a paradigm sharing computing and storage infrastructure over scalable resources network. In today’s world, data is scattered across different data IV. EXPEREIMENTAL RESULTS centers and applications are stored in remote servers. Cloud technology brings scattered data and remote The experiments are conducted with BAT and HS applications to user’s laptop virtually. The idea is to algorithms separately and with the hybrid algorithm. The make computing and storage infrastructure available to proposed scheduling mechanism was implemented. cloud users regardless of time and location. Trust has an important role in commercial cloud environments and Table 1. Time required to complete task trust management is an integral part of cloud Time required to complete all task Time (second) technology’s commercial aspects. This study proposed a Random resource selection with BAT trust based resource selection scheme using BAT-HS for 391.14 scheduling scheduling problem in Cloud computing. The new Trust Trust based resource selection with BAT based resource selection with BAT-HS scheduling 371.26 scheduling decreased time to complete tasks by 10.4148% compared Random resource selection with Harmony 384.02 to Random resource selection having BAT scheduling. Search scheduling Trust based resource selection with Harmony 378.11 Search scheduling REFERENCES Random resource selection with BAT-HS 366.71 scheduling 1 Bhatt, K., & Bundele, M. (2013). Review Paper on PSO in Trust based resource selection with BAT-HS workflow scheduling and Cloud Model enhancing Search 352.42 scheduling mechanism in Cloud Computing. IJIET-International Journal of innovations in engineering and technology, 2(3). Trust based resource selection with BAT-HS 2 Garg, S. K., & Buyya, R. (2011, December). CloudSim Estimation of a Simple Particle Swarm scheduling decreases the time essential to complete all AlgorithmInternational Journal of Advanced Research in tasks by 3.9742% when compared with Random resource Computer Science and Software Engineering, 3(8), (pp. selection with BAT-HS scheduling, by 8.5818% when 1279-1287). compared with Random resource selection with HS 3 Elzeki, O. M., Reshad, M. Z., & Elsoud, M. A. (2012). scheduling and by 10.4148% when compared with Improved Max-Min Algorithm in Cloud Computing. Random resource selection with BAT scheduling. International Journal of Computer Applications, 50(12), 22-27. 4 Agarwal, D., & Jain, S. (2014). Efficient Optimal Algorithm of Task Scheduling in Cloud Computing Environment. arXiv preprint arXiv:1404.2076. 5 Chawla, Y., & Bhonsle, M. Dynamically optimized cost based task scheduling in Cloud Computing. 6 Azawi Mohialdeen, I. (2013). Comparative study of scheduling al-gorithms in cloud computing environment. Journal of Computer Science, 9(2). 7 Vijayalakshmi A. Lepakshi & Prashanth C S R (2013). A Study on Task Scheduling Algorithms in Cloud Computing. International Journal of Engineering and Innovative Technology (IJEIT), 2(11), 119-125. Fig. 2. Time required to complete task Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64 64 Trust Based Resource Selection in Cloud Computing Using Hybrid Algorithm 8 Jangra, A., & Saini, T. (2013). Scheduling optimization in 23 Sun, W., Zhang, N., Wang, H., Yin, W., & Qiu, T. (2013, cloud computing. Int. J. Adv. Res. Comput. Sci. Softw. December). PACO: A Period ACO Based Scheduling Eng, 3, 62-65. Algorithm in Cloud Computing. In Cloud Computing and 9 Heger, D. A. (2010). Optimized Resource Allocation & Big Data (CloudCom-Asia), 2013 International Conference Task Scheduling Challenges in Cloud Computing on (pp. 482-486). IEEE. Environments. dheger dhtusa. com. 24 Man, N. D., & Huh, E. N. (2013, January). Cost and 10 Vijayalakshmi, M., & Muthusamy, K. An Efficient Study efficiency-based scheduling on a general framework of Job Scheduling Algorithms with ACO in Cloud combining between cloud computing and local thick Computing Environment. clients. In Computing, Management and 11 Princy Bathla., Sahil Vashist., Rajwinder Singh., & Telecommunications (ComManTel), 2013 International Gagandeep Singh., (2014). A Sophisticated Review of the Conference on (pp. 258-263). IEEE. Job Scheduling methods on Cloud Network. International 25 Hung, P. P., Bui, T. A., & Huh, E. N. (2013, December). A Journal of Latest Scientific Research and Technology Thin-Thick Client Collaboration for Optimizing Task (IJLSRT). Scheduling in Mobile Cloud Computing. In IT 12 Zhang, F., Cao, J., Li, K., Khan, S. U., & Hwang, K. Convergence and Security (ICITCS), 2013 International (2014). Multi-objective scheduling of many tasks in cloud Conference on (pp. 1-4). IEEE. platforms. Future Generation Computer Systems, 37, 309- 26 Liu, N., Dong, Z., & Rojas-Cessa, R. (2013, July). Task 320. Scheduling and Server Provisioning for Energy-Efficient 13 Liu, H., Xu, D., & Miao, H. (2011, December). Ant colony Cloud-Computing Data Centers. In Distributed Computing optimization based service flow scheduling with various Systems Workshops (ICDCSW), 2013 IEEE 33rd QoS requirements in cloud computing. In Software and International Conference on (pp. 226-231). IEEE. Network Engineering (SSNE), 2011 First ACIS 27 Fister Jr, I., Fister, D., & Yang, X. S. (2013). A hybrid bat International Symposium on (pp. 53-58). IEEE. algorithm. arXiv preprint arXiv:1303.6310. 14 Luo, L., Wu, W., Di, D., Zhang, F., Yan, Y., & Mao, Y. 28 Wang, G., Guo, L., Duan, H., Liu, L., & Wang, H. (2012). (2012, June). A resource scheduling algorithm of cloud A bat algorithm with mutation for UCAV path planning. computing based on energy efficient optimization methods. The Scientific World Journal, 2012. In Green Computing Conference (IGCC), 2012 29 Yang, X. S. (2009). Harmony search as a metaheuristic International (pp. 1-6). IEEE. algorithm. In Music-inspired harmony search algorithm 15 Song, X., Gao, L., & Wang, J. (2011, June). Job scheduling (pp. 1-14). Springer Berlin Heidelberg. based on ant colony optimization in cloud computing. In 30 Weyland, D. (2010). A rigorous analysis of the harmony Computer Science and Service System (CSSS), 2011 search algorithm: How the research community can be International Conference on (pp. 3309-3312). IEEE. misled by a “novel” methodology. International Journal of 16 Wang, N., Yang, Y., Meng, K., Chen, Y., & Ding, H. Applied Metaheuristic Computing (IJAMC), 1(2), 50-60. (2013, August). A task scheduling algorithm based on qos 31 Wang, G., & Guo, L. (2013). A novel hybrid bat algorithm and complexity-aware optimization in cloud computing. In with harmony search for global numerical optimization. Information and Communications Technology 2013, Journal of Applied Mathematics, 2013. National Doctoral Academic Forum on (pp. 1-8). IET. 32 Kumar, V. S., & Aramudhan, M. (2014). Trust based 17 Pandey, S., Wu, L., Guru, S. M., & Buyya, R. (2010, resource selection and list scheduling in cloud computing. April). A particle swarm optimization-based heuristic for International Journal of Advances in Engineering & scheduling workflow applications in cloud computing Technology, 6(6). environments. In Advanced Information Networking and Applications (AINA), 2010 24th IEEE International Conference on (pp. 400-407). IEEE. Authors’ Profiles 18 Chen, C. Y., & Tseng, H. Y. (2012, March). An V.Suresh Kumar has completed his BE Exploration of the Optimization of Excutive Scheduling in Computer Science from Bharatidasan the Cloud Computing. In Advanced Information University, Tamilnadu, M.Tech in Networking and Applications Workshops (WAINA), 2012 Computer Engineering from SASTRA, 26th International Conference on (pp. 1316-1319). IEEE. Tamilnadu. He is doing PhD in Computer 19 Li, Q., & Guo, Y. (2010, September). Optimization of Science at Manonmanium Sundharanar Resource Scheduling in Cloud Computing. In SYNASC University , Tirunelveli . At present he is (pp. 315-320). working as Dean of Dept.of Engineering, 20 Han, Y., & Luo, X. (2013, December). An Effective SNGIST, N.Paravoor His area of interest Algorithm and Modeling for Information Resources is Data mining, Networking, and Cloud computing. Scheduling in Cloud Computing. In Advanced Cloud and Big Data (CBD), 2013 International Conference on (pp. 14-19). IEEE. M.ARAMUDHAN has completed his 21 Han, H., Deyui, Q., Zheng, W., & Bin, F. (2013, undergraduate and postgraduate degrees September). A Qos Guided task Scheduling Model in in Computer Science and Engineering cloud computing environment. In Emerging Intelligent from Bharathidasan University. He Data and Web Technologies (EIDWT), 2013 Fourth obtained his PhD degree from Anna International Conference on (pp. 72-76). IEEE. University, Chennai. At present, he is 22 Karthick, A. V., Ramaraj, E., & Subramanian, R. G. (2014, working as Associate Professor in February). An Efficient Multi Queue Job Scheduling for Department of Information Technology, Cloud Computing. In Computing and Communication PKIET, Karaikal, Nedungadu, INDIA. Technologies (WCCCT), 2014 World Congress on (pp. 164-166). IEEE. Copyright © 2015 MECS I.J. Intelligent Systems and Applications, 2015, 08, 59-64

Advise: Why You Wasting Money in Costly SEO Tools, Use World's Best Free SEO Tool Ubersuggest.