In infrastructure layer, cloud computing technology provides the possibility of using computing and storage resources as a service according to the type of requirements. Moreover, it makes dynamic resource management feasible through generating an abstract layer on whole physical resources by virtualization. The goal of current research is to present intelligent water drop algorithm to achieve a method for optimal installation of virtual machines on physical machines embedded in data center in order to reduce power consumption and consequently reducing the number of active physical servers as well as decreasing waste amount of resources. In fact, presenting this algorithm results in reducing costs of maintenance and infrastructure’s service providers since the biggest part of maintenance cost is related to energy consumption. Therefore, the most benefit will be achieved by service provider once it can make energy consumption the least. CloudSim simulator has been used to simulate all IWD, GA, PSO, and MBFD algorithms with the purpose of resource management in cloud computing. Outcome results show that among current methods of intelligent water drop algorithm, using MAD algorithm as overload detection algorithm and MMT algorithm as virtual machine selection algorithm can provide the most optimal answer for physical resources’ management in cloud computing.
Majid Abdous : Department of Computer Engineering, Electronic Branch, Islamic Azad University
Tehran, Iran
Touraj Banirostam : Department of Computer Engineering, Islamic Azad University, Central Tehran Branch
Tehran, Iran
Cloud Computing, Resource Management, Water Drop Algorithm, Intelligent Water Drop
Considering the large number of users and resources in cloud computing, using evolutionary algorithms for physical resource management seems to be a suitable method.
Investigating results of separate simulation of all IWD, GA, PSO, and MBFD algorithms based on different policies of physical and virtual machines’ selection of the proposed method, as well as MAD algorithm as overhead detection algorithm and MMT algorithm as virtual machine selection algorithm; shows the least amount of energy consumption of 43 W/H. The proposed model reduces energy consumption 9% more than MBDF algorithm, 21% more than PSO algorithm, and 38% than GA algorithm. As demonstrated in table and Fig 2, energy consumption of algorithms have been surveyed through using IQR and MMT algorithms when IQR algorithms which have a good performance in large search spaces are used for physical host overhead detection and MMT algorithms which is used to minimize migration rate; the average of 10 optimal answers of IWD algorithm shows less energy consumption in comparison to the other three proposed method. However investigating energy consumption based on MMT and IQR algorithms for IWD algorithm is equal to 53 W/H which is a higher than the result of MAD and MMT algorithms.
[1] A. K. Chandan Banerjeea, and R. Dattaguptac, “Customized 3-tier Service Suite Conceptualization in Cloud Computing”, Procedia Technology, 4 . 2012 , pp 561 – 565. [2] B. Mondal, K. Dasgupta, P. Dutta, “Load Balancing in Cloud Computing using Stochastic Hill Climbing-A Soft Computing Approach”, Procedia Technology 4, 2012, pp 783 – 789.
[3] A. Beloglazov, & R. Buyya, “Optimal online deterministic algorithms and adaptive heuristics for energy and performance efficient dynamic consolidation of virtual machines in cloud data centers”, Concurrency and Computation: Practice and Experience, 24(13), 2012, pp 1397-1420.
[4] A. Yongqiang, A, Haibing. “multi-objective ant colony system algorithm for virtual machine placement in cloud computing”, Journal of Computer and System Sciences, 79(8): 2013, pp1230–1242.
[5] S. Wang, Z. Liu, Z. Zheng, Q. Sun, F. Yan, “ Particle Swarm Optimization for Energy-Aware Virtual Machine Placement Optimization in Virtualized Data Centers”, International Conference Parallel and Distributed Systems (ICPADS), South Korea: Seoul,23. 2013, PP:102-109.
[6] V. Vignesh, Ks. Sendhil Kumar, N. Jaisankar, “Resource Management and Scheduling in Clod Environment”, International Journal of Scientific and Research Publications, Volume 3, Issue 6, 2013, pp 2250-3153.
[7] D. PALANIKKUMAR, E. GOWSALYA, B. RITHU, P. ANBUSELVEN, “AN INTELLIGENT WATER DROPS ALGORITHM BASED SERVICE SELECTION AND COMPOSITION IN SERVICE ORIENTED ARCHITECTURE”, Journal of Theoretical and Applied Information Technology, Vol. 39 No.1, 2012.
[8] O. Basem, L-P. W. Alijla, A. T, K. Chee Peng Lim, “ A modified Intelligent Water Drops algorithm and its application to optimization problems”, Expert Systems with Applications, Expert Systems with Applications 41, 2014, pp 6555–6569.
[9] R. Buyya, A. Beloglazov, & J. Abawajy,”Energyefficient management of data center resources for cloud computing: A vision, architectural elements, and open challenges”, arXiv preprint arXiv:2010, pp1006.0308.
