|Gobalakrishnan Natesan||Research Scholar, Sathyabama Institute of Science and Technology, Department of Information Technology, St.Joseph’s College of Engineering, Chennai, Tamil nadu 600119, India|
|Arun Chokkalingam||R.M.K College of Engineering & Technology, Chennai, Tamil nadu 601206, India|
Cloud computing is one of the emerging areas in computing platforms, supporting heterogeneous, parallel and distributed environments. An important challenging issue in cloud computing is task scheduling, which directly influences system performance and its efficiency. The primary objective of task scheduling involves scheduling tasks related to resources and minimizing the time span of the schedule. In this study, we propose a Modified Mean Grey Wolf Optimization (MGWO) algorithm to enhance system performance, and consequently reduce scheduling issues. The main objective of this method is focused upon minimizing the makespan (execution time) and energy consumption. These two objective functions are elaborated in the algorithm in order to suitably regulate the quality of results based on response, in order to achieve a near optimal solution. The implementation results of the proposed algorithm are evaluated using the CloudSim toolkit for standard workloads (normal and uniform). The advantage of the proposed method is evident from the simulation results, which show a comprehensive reduction in makespan and energy consumption. The outcomes of these results show that the proposed Mean GWO algorithm achieves a 8.85% makespan improvement compared to the PSO algorithm, and 3.09% compared to the standard GWO algorithm for the normal dataset. In addition, the proposed algorithm achieves 9.05% and 9.2% improvement in energy conservation compared to the PSO and standard GWO algorithms for the uniform dataset, respectively.
Cloud computing; Energy; Grey Wolf Optimization; Makespan; Optimization
Cloud computing is one of the most aggressively competent technologies in the field of computing. It enables companies to maximize their productivity potential, pushing them towards the excellence of providing a unified service for their respective customers. Each of the fortune 500 listed companies is transferring their infrastructure in to the cloud domain. Cloud computing requires internet connection through which any user can store their data remotely and access the same form somewhere else. (Buyya et al., 2009). One of the core reasons why cloud computing is as popular as it is, is that it is scalable, reliable and allows end users to focus on the product, rather than worrying about how to deploy the service, which now is often managed by third party companies. The following are the services that are currently being offered under the cloud domain: Software as a Service (SaaS), Platform as a Service (PaaS),and Infrastructure as a Service (IaaS). Virtualized applications are developed for offering such services through the Internet. (Zhang et al., 2010; Pradeep & Jacob, 2018; Jennings & Stadler, 2015; Mustafa et al., 2015).
The unique selling point of cloud services is that they are flexible, dynamic and most importantly reduce the possibilities of degradation in performance. This is the main focus of various researchers around the world, with active fields including security, task scheduling, privacy concerns, cloud performance and deployment (Ma et al., 2014; Kumar & Sharma, 2017). As users are using shared resources in the cloud environment, it is important that task scheduling is performed in an efficient manner. User requirements are fulfilled by mapping their need with required resources with appropriate algorithms. Efficient solutions are provided to users by making use of more complex efficient scheduling algorithms (Dong et al., 2015). Problems could be a few or more, depending upon the complexity nature of applications. More complex applications require efficient algorithms to manage the data centers.
As the mapping of user tasks to the cloud resource is a complex problem, it is important to make use of optimization techniques to find near optimal solutions. Solutions for problems falling under NP-hard category can be obtained through enumeration techniques, heuristic or approximation method. The enumeration approach is usually not preferred because of its time consuming nature as it involves the building of all possible task schedulers that are needed and subsequently comparing each of them to arrive at the best solution (Gobalakrishnan & Arun, 2016). This leads us towards the next available option of heuristic and meta-heuristic techniques. Heuristic search techniques generate feasible solutions at a high operating cost, so these can be safely ignored (Shi et al., 2017; Natesan & Chokkalingam, 2018; Pradeep & Jacob, 2018). Therefore the only realistic possible solution could be obtained by adopting the meta-heuristic algorithm approach, such as the Genetic Algorithm (GA) (Gutierrez-Garcia & Sim, 2012), Particle Swarm Optimization (PSO) (Poli et al., 2007), or Grey Wolf Optimization (GWO) (Mirjalili et al., 2014), which employ a pool of candidate solutions to traverse the available solution space. It is also understood that GWO falls under the category of swarm intelligence (Pacini et al., 2014; Ghomi et al., 2017; Singh & Chana, 2016). In addition, factors such as adaptive exploratory behavior, little controlling parameter have motivated the use of GWO in this research work. In the paper, we propose a cloud task scheduling algorithm based on a metaheuristic Mean Grey Wolf Algorithm to minimize energy consumption and the execution time of the task in the cloud. Execution of the proposed algorithm is carried out in the CloudSim environment, for common workloads in simulated data centers.
The proposed approach fulfills the main objective of task scheduling by optimizing the execution time and energy consumed while executing the tasks in the cloud environment. A Mean-GWO technique has been proposed in this work to achieve this objective. The proposed technique has been evaluated with two datasets (normal and uniform distribution). The results obtained from the simulation carried out using the proposed mean-GWO technique clearly shows an improvement in the performance of task scheduling process when compared with the existing PSO and standard GWO techniques. In future, task scheduling can be attained in federated data centers based on the bio-inspired technique (Pacini et al., 2016; Aruna & Aramudhan, 2016). In addition, apart from QoS parameters such as execution time and energy, other parameters such as reliability, load imbalance and security can also be integrated with the Mean-GWO technique and implemented in the real cloud environment.
Abdullahi, M., Ngadi, M.A., Abdulhamid, S.M., 2016. Symbiotic Organism Search Optimization Based Task Scheduling in Cloud Computing Environment. Future Generation Computer Systems, Volume 56, pp. 640–650
Aruna, L., Aramudhan, M., 2016. Framework for Ranking Service Providers of Federated Cloud Architecture using Fuzzy Sets. International Journal of Technology, Volume 7(4), pp. 643–653
Buyya, R., Yeo, C.S., Venugopal, S., Broberg, J., Brandic, I., 2009. Cloud Computing and Emerging IT Platforms: Vision, Hype, and Reality for Delivering Computing as the 5th Utility. Future Generation Computer Systems, Volume 25(6), pp. 599–616
Dong, Z., Liu, N., Rojas-Cessa, R., 2015. Greedy Scheduling of Tasks with Time Constraints for Energy-efficient Cloud-computing Data Centers. Journal of Cloud Computing, Volume 4(1), pp. 1–14
Duan, R., Prodan, R., Li, X., 2014. Multi-objective Game Theoretic Scheduling of Bag-of-tasks Workflows on Hybrid Clouds. IEEE Transactions on Cloud Computing, Volume 2(1), pp. 29–42
Gobalakrishnan, N., Arun, C., 2016. SIS: A scheme for dynamic independent task scheduling in a cloud environment. International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT-2016), pp. 272-279,
Ghomi, E.J., Rahmani, A.M., Qader, N.N., 2017. Load-balancing Algorithms in Cloud Computing: A Survey. Journal of Network and Computer Applications, Volume 88, pp. 50–71
Gutierrez-Garcia, J.O., Sim, K.M., 2012. GA-based Cloud Resource Estimation for Agent-based Execution of Bag-of-tasks Applications. Information Systems Frontiers, Volume 14(4), pp. 925–951
Jennings, B., Stadler, R., 2015. Resource Management in Clouds: Survey and Research Challenges. Journal of Network and Systems Management, Volume 23(3), pp. 567–619
Kaur, T., Chana, I., 2016. Energy Aware Scheduling of Deadline-constrained Tasks in Cloud Computing. Cluster Computing, Volume 19(2), pp. 679–698
Khalili, A., Babamir, S.M., 2017. Optimal Scheduling Workflows in Cloud Computing Environment using Pareto?based Grey Wolf Optimizer. Concurrency and Computation: Practice and Experience, Volume 29(11), pp. 1–15
Kumar, M., Sharma, S.C., 2017. Dynamic Load Balancing Algorithm to Minimize the Makespan Time and Utilize the Resources Effectively in Cloud Environment. International Journal of Computers and Applications, Volume 39, pp. 1–10
Ma, T., Chu, Y., Zhao, L., Ankhbayar, O., 2014. Resource allocation and scheduling in cloud computing: policy and algorithm. IETE Technical review, Volume 31(1), pp. 4–16
Mirjalili, S., Mirjalili, S.M., Lewis, A., 2014. Grey Wolf Optimizer. Advances in Engineering Software, Volume 69, pp. 46–61
Moon, Y.J., Yu, H., Gil, J.M., Lim, J.B., 2017. A Slave Ants Based Ant Colony Optimization Algorithm for Task Scheduling in Cloud Computing Environments. Human-centric Computing and Information Sciences, Volume 7(28), pp. 1–10
Mustafa, S., Nazir, B., Hayat, A., Khan, A.U.R., Madani, S.A., 2015. Resource Management in Cloud Computing: Taxonomy, Prospects, and Challenges. Computers & Electrical Engineering, Volume 47, pp. 186–203
Natesan, G., Chokkalingam, A., 2018. A New Multi-objective Optimal Programming Model for Task Scheduling using Genetic Gray Wolf Optimization in Cloud Computing. The Computer Journal, Volume 61(10), pp. 1523–1536
Natesan, G., Chokkalingam, A., 2017. Opposition Learning-based Grey Wolf Optimizer Algorithm for Parallel Machine Scheduling in Cloud Environment. International Journal of Intelligent Engineering and Systems, Volume 10(1), pp. 186–195
Pacini, E., Mateos, C., Garino, C.G., 2014. Distributed Job Scheduling based on Swarm Intelligence: A Survey. Computers & Electrical Engineering, Volume 40(1), pp. 252–269
Pacini, E., Mateos, C., Garino, C. G., 2015. Balancing Throughput and Response Time in Online Scientific Clouds via Ant Colony Optimization (SP2013/2013/00006). Advances in Engineering Software, Volume 84, pp. 31–47
Pacini, E., Mateos, C., Garino, C.G., Careglio, C., Mirasso, A., 2016. A Bio-inspired Scheduler for Minimizing Makespan and Flowtime of Computational Mechanics Applications on Federated Clouds. Journal of Intelligent & Fuzzy Systems, Volume 31(3), pp. 1731–1743
Poli, R., Kennedy, J., Blackwell, T., 2007. Particle Swarm Optimization. Swarm Intelligence, Volume 1(1), pp. 33–57
Pradeep, K., Jacob, T.P., 2017. CGSA Scheduler: A Multi-objective-based Hybrid Approach for Task Scheduling in Cloud Environment. Information Security Journal: A Global Perspective, Volume 27(2), pp. 77-91
Pradeep, K., Jacob, T.P., 2018. OCSA: Task Scheduling Algorithm in Cloud Computing Environment. International Journal of Intelligent Engineering and Systems, Volume 11(3), pp. 271-279
Pradeep, K., Jacob, T.P., 2018. A hybrid approach for task scheduling using the cuckoo and harmony search in cloud computing environment. Wireless Personal Communications, Volume 101(4), pp. 2287-2311.
Ramezani, F., Lu, J., Taheri, J., Hussain, F.K., 2015. Evolutionary Algorithm-based Multi-Objective Task Scheduling Optimization Model in Cloud Environments. World Wide Web, Volume 18(6), pp. 1737–1757
Sadhasivam, N., Thangaraj, P., 2017. Design of an Improved PSO Algorithm for Workflow Scheduling in Cloud Computing Environment. Intelligent Automation & Soft Computing, Volume 23(3), pp. 493–500
Singh, S., Chana, I., 2016. A Survey on Resource Scheduling in Cloud Computing: Issues and Challenges. Journal of Grid Computing, Volume 14(2), pp. 217–264
Shi, L., Zhang, Z., Robertazzi, T., 2017. Energy-aware Scheduling of Embarrassingly Parallel Jobs and Resource Allocation in Cloud. IEEE Transactions on Parallel and Distributed Systems, Volume 28(6), pp. 1607–1620
Zhang, Q., Cheng, L., Boutaba, R., 2010. Cloud Computing: State-of-the-art and Research Challenges. Journal of Internet Services and Applications, Volume 1(1), pp. 7–18
Zhou, J., Dong, S., 2018. Hybrid Glowworm Swarm Optimization for Task Scheduling in the Cloud Environment. Engineering Optimization, Volume 50(6), pp. 949–964