The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


Balanced Workload Clusters for Distributed Object Oriented Software

When clustering objects to be allocated on a numbe r of nodes, most researches focus only on either the communication cost between clusters or the balancin g of the workload on the nodes. Load balancing is a technique to distribute workload evenly across two or more compu ters, network links, CPUs, hard drives or other resources, in order to, get optimal resource utilization, maximize throughp ut, minimize response time and avoid overload. In this paper, we introduce three clustering algorithms that obtain balanced cl usters for homogeneous clustered with minimized com munication cost. 


[1] Abdel5Raouf A., Fergany T., Ammar R., and Hamad S., Performance5Based Modeling for Distributed Object5Oriented Software, the Journal of Computational Methods in Sciences and Engineering Archive , vol. 6, no. 5, pp. 7695 773 , 2006.

[2] Abella J. and Gonzlez A., Inherently Workload5 Balanced Clustered Microarchitecture, in Proceedings of the 19 th International Parallel and Distributed Processing Symposium , Denver, Colorado, pp. 20, 2005.

[3] Abu Abass O., Comparisions between Data Clustering Algorithms, the International Arab Journal of Information Technology , vol. 5, no. 3, pp. 3205325, 2008.

[4] Appavoo J., Clustered Objects, A PhD Thesis, Department of Computer Science , University of Toronto, 2005.

[5] Babnik T., Aggarwal R., and Moorep,. Principal Component and Hierarchical Cluster Analyses as Applied to Transformer Partial Discharge Data With Particular Reference to Transformer Condition Monitoring, IEEE Transactions on Power Delivery , vol. 23, no. 4, pp. 200852016, 2008.

[6] Banerjee A. and Ghosh J., Scalable Clustering Algorithms with Balancing Constraints, Data Mining and Knowledge Discovery Journal , vol. 13, no. 3, pp 3655395, 2006.

[7] Banerjee A., Chandola V., and Kumar V., Anomaly Detection: A Survey, ACM Computing Surveys Journal , vol. 41, no. 3, pp. 15 72, 2009.

[8] Bereson A. and Lobbia R., Efficient Track5to5 Track Assignment using Cluster Analysis, in Proceedings of the 9 th IEEE International Conference on Information Fusion , Florence, Italy, pp. 158, 2006.

[9] Dash M., Liu H., Scheuermann P., and Tan K., Fast Hierarchical Clustering and its Validation, Data and Knowledge Engineering Journal , Elsevier , vol. 44, no. 1, pp. 1095138, 2003. Balanced Workload Clusters for Distributed Object Oriented Software 387

[10] Ding J., Ding T., and Meulen P., Throughput Analysis of Linear Cluster Tools, IEEE Transancations on Automatic Science Engineering , vol. 1, no. 1, pp. 1045109, 2005.

[11] Els sser R., L cking T., and Monien B., New Spectral Bounds on k5Partitioning of Graphs, in Proceedings of the 13 th Annual ACM Symposium on Parallel Algorithms and Architectures , New York, USA, pp. 2555262, 2001.

[12] Garama A., Gupta A., Karypis G., and Kumar V., Introduction to Parallel Computing , Addison5 Wesley, 2003.

[13] Gibson T., How Things Work: Standard Deviation as a Tool for Measuring Precision and Accuracy, available at: http://archives. profsurv.com/magazine/article.aspx?i=1826, last visited 2007.

[14] Grosu D. and Chronopoulos A., Algorithmic Mechanism Design for Load Balancing in Distrributed Systems, IEEE Transactions on Systems , Man and Cybernetics5Part B: Cybernetics , vol. 34, no. 1, pp. 77584, 2004.

[15] Guadalupe J., Basnet B., Andrew H., Sung S., and Bernardete M., Fuzzy Clustering and Data Analysis Toolbox for using with Matlab, available at: ftp://ftp.unicauca.edu.co/cuentas /fiet/docs/DEIC/Materias/computacion%20intelig ente/parte%20II/semana12/clustering/mfiles/Clus teringToolbox/FuzzyClusteringToolbox.pdf, last visited 2008.

[16] Hamad S., Fergany T., Ammar R., and Solit S., Mapping Distributed Object5Oriented Software to Architecture with Limited Number of Processors, in Proceedings of IEEE International Symposium on Signal Processing and Information Technology , Giza, Egypt, pp. 5315536, 2007.

[17] Hamad S., Fergany T., Ammar R., and Abd El5 Raouf A., A Double K5Clustering Approach for Restructuring Object5Oriented Software, in Proceedings of IEEE Symposium on Computers and Communications , Marrakech, pp. 1695174, 2008.

[18] Hamad S., Khalifa M., Ammar R., and Soleit E., Performance5Based Restructuring of Distributed Object5Oriented Computations for a Cluster of Multiprocessors, A PhD Thesis, Ain Shams University, 2008.

[19] Hongjin J., Zeng D., Yanxiang S., Yangang W., and Xisheng W., Semi5Hierarchical Correspondence Cluster Analysis and Regional Geochemical Pattern Recognition, the Journal of Geochemical Exploration , vol. 93, no. 2, pp. 1095119, 2007.

[20] H sel V. and Walcher S., Clustering Techniques: A Brief Survey, Technical Report, Insttitut fiir Biomathematik Und Biometrie GSF, Research Center, Germany, 2000.

[21] Huang C., Zhou G., Abdelzaher T., Son S., and Stankovic A., Load Balancing in Bounded5 Latency Content Distribution, in Proceedings of the 26 th IEEE International Symposium on Real5 Time Systems , Miami, USA, pp. 61573, 2005

[22] Jiang D., Tang C., and Zhang A., Cluster Analysis for Gene Expression Data: A Survey, IEEE Transactions on Knowledge and Engineering , vol. 16, no. 11, pp. 137051386, 2004.

[23] Kim T. and Shin Y., Role5based Decomposition for Improving Concurrency in Distributed Object5Oriented Software Development Environments, in Proceedings of the 23 rd IEEE Conference on Computer Software and Applications , Arizona, USA, pp. 4105415, 1999.

[24] Kotsiantis S. and Pintelas P., Recent Advances in Clustering: A Brief Survey, WSEAS. Transactions on Information Science and Applications , vol. 1, no. 1, pp. 73581, 2004.

[25] Lee Y. and Antonsson E., Dynamic Partitional Clustering using Evolution Strategies, in Proceedings of the 26 th IEEE Annual Conference on Industrial Electronics Society , Nagoya, Japan, pp. 271652721, 2000.

[26] Lee Y. and Song Y., Selecting the Key Research Areas in Nano5Technology Field using Technology Cluster Analysis: A Case Study Based on National, Technovation, vol. 27, no. 1, pp. 57564, 2007.

[27] Macnab J., Miller L., and Polatajko H., The Search for Subtypes of DCD: Is Cluster Analysis The Answer?, Human Movement Science , vol. 20, no. 1, pp. 49572, 2001.

[28] Narayanan S., Ozturk O., Kandemir M., and Karakoy M., Workload Clustering for Increasing EnergySavings on Embedded MPSoCs, in Proceedings of the IEEE International Conference SOC , VA, USA, pp. 1555160, 2005.

[29] Roy S. and Chaudhary V., Strings: A High5 Performance Distributed Shared Memory for Symmetrical Multiprocessor Clusters, in Proceedings of the 7 th IEEE International Symposium on High Performance Distributed Computing , Chicago, USA, pp. 90597, 1998.

[30] Smith M. and Munro M., Runtime Visualisation of Object Oriented Software, in Proceedings of the 1 st IEEE International Workshop on Visualizing Software for Understanding and Analysis , Washington, USA, pp. 81589, 2002.

[31] Sneed H. and Dombovari T., Comprehending a Complex, Distributed, Object5Oriented Software System A Report from the Field, in Proceedings of the 7 th International Workshop on Program Comprehension , PA, USA, pp. 2185225, 1999. 388 The International Arab Journal of Informat ion Technology, Vol. 12, No. 4, July 2015

[32] Thain D., Coordinating Access to Computation and Data in Distributed Systems, available at: http://research.cs.wisc.edu/htcondor/doc/thain5 dissertation.pdf, last visited 2004.

[33] Todd C., Toth T., and Busa5Fekete R., GraphClus, a MATLAB Program for Cluster Analysis using Graph Theory, Computers and Geosciences , vol. 35, no. 6, pp. 120551213, 2009.

[34] Tsai S., Chiou J., and Jen H., Load Balance Facility in Distributed MINIX System, in Proceedings of the 20 th System Architecture and Integration Conference , Liverpool, UK, pp. 1625 169, 2002.

[35] Wang X., Yan Z., and Xue W., An Adaptive Clustering Algorithm with High Performance Computing Application to Power System Transient Stability Simulation, in Proceedings of the 3 rd International Conference on Electric Utility Deregulation and Restructuring and Power Technologies , Nanjuing, China, pp. 11375 1140, 2008.

[36] Wu X., Taylor V., and Sharkawi S., Performance Analysis and Optimization of Parallel Scientific Applications on CMP Cluster Systems, in Proceedings of International Conference on Parallel Processing , Washington, USA, pp. 1885195, 2008.

[37] Xing Z. and Stroulia E., Understanding Class Evolution in Object5Oriented Software, in Proceedings of the 12 th IEEE International Workshop on Program Comprehension , Washington, USA, pp. 34543, 2004.

[38] Zhang Q., Riska A., Sun W., and Smimi E., Ciardo G., Workload5Aware Load Balancing for Clustered Web Servers, Parallel and Distributed Systems , IEEE Transactions on Computer Society , vol. 16, no. 3, pp. 2195233, 2005. Heba Ragab received the BSc degree in 2000 and MSc in 2007, and PhD degree in 2014, in computer and automatic control from the Faculty of Engineering, Tanta University. She is working now as a Lecturer at Computers and Automatic Control Department., Tanta University., Egypt. Her interests are in the area of: Distribute d systems and computations, software restructuring an d neural networks. Amany Sarhan received the BSc degree in electronics engineering and MSc degree in computer science and automatic control from the Faculty of Engineering, Mansoura University, in 1990 and 1997, respectively. She awarded the PhD degree as a joint research between Tanta Universety , Egypt and University of Connecticut, USA. She is working now as an Associate Prof. at Computers and Automatic Control Department., Tanta University, Egypt. Her interests are in the area of: Distribute d systems and computations, software restructuring, schema matching, image and video processing. Al Sayed Sallam received his MSc and PhD degrees from Bremen in Germany on 1983 and 1987 respectively. He is working now as an Associate Prof. and Head of Computers and Automatic Control Department., Tanta University, Egypt. His interests are in the area of: Control, software restructuring, robotics and network. He is the CIO of Tanta University for the last 2 years. Reda Ammar received his PhD degree, University of Cyhhonnecticut, computer science, 1983. He worked as the head of Department at Computer Science and Engineering Department, UCONN, USA. His Research Interests are: Software performance engineering; parallel and distributed computing; real5time systems and cluste r and grid computing. He is IEEE (senior member), ACM, ISCA, Editor5in5Chief of the International Journal of Computers and Their Applications, Associate Editor in Computing Letters and Member of the Board of Directors of the International Society of Computers and Their Applications.