Publications

Vahid Salmani, Mahmoud Naghibzadeh, Amirali Habibi, Hossein Deldari, Quantitative Comparison of Job-level Dynamic Scheduling Policies in Parallel Real-time Systems, In Proceedings of IEEE TENCON 2006, Hong Kong, November 2006.

Scheduling algorithms play an important role in design of real-time systems. Due to high processing power and low price of multiprocessors, real-time scheduling in such systems is more interesting; however, more complicated. Earliest Deadline First (EDF) and Least Laxity First (LLF) are two well-known and extensively applied dynamic scheduling algorithms on which many researches have already been done. However, to the best of our knowledge, the efficiency of aforementioned algorithms has not been compared under similar conditions. Perhaps the main reason is that LLF algorithm is fully dynamic and impractical to implement. In this research, we have used a job-level dynamic and practical version of LLF which is called Modified Least Laxity First (MLLF) algorithm instead of the traditional LLF and have compared its performance with EDF algorithm from many different aspects. The success ratio has been chosen as the key factor for evaluation of the algorithms.

Hamed Vahdat Nejad, and Hossein Deldari, A Parallel Quadtree Approach for Image Compression using Wavelets, Enformatika Transactions on Engineering, Computing and Technology, Vol. 14, August 2006, ISSN 1305-5313, Pages 396-399.

Wavelet transforms are multiresolution decompositions that can be used to analyze signals and images. Image compression is one of major applications of wavelet transforms in image processing. It is considered as one of the most powerful methods that provides a high compression ratio. However, its implementation is very time-consuming. At the other hand, parallel computing technologies are an efficient method for image compression using wavelets. In this paper, we propose a parallel wavelet compression algorithm based on quadtrees. We implement the algorithm using MatlabMPI (a parallel, message passing version of Matlab), and compute its isoefficiency function, and show that it is scalable. Our experimental results confirm the efficiency of the algorithm also.

Ebrahim Bagheri, Hossein Deldari, Dejong Function Optimization by Means of a Parallel Approach to Fuzzified Genetic Algorithm, IEEE Symposium on Computers and Communications (ISCC'06), June 26-29, Pula-Cagliari, Sardinia, Italy, Pages 675-680.

Genetic Algorithms are very powerful search methods that are used in different optimization problems. Parallel versions of genetic algorithms are easily implemented and usually increase algorithm performance. Fuzzy control as another optimization solution along with genetic algorithms can significantly increase algorithm performance. Two variations for genetic algorithm and fuzzy system composition exist. In the first approach Genetic algorithms are used to optimize and model the structure of fuzzy systems through knowledge base or membership function design while the second approach exploits fuzzy to dynamically supervise genetic algorithm performance by speedily reaching an optimal solution. In this paper we propose a new method for fuzzy parallel genetic algorithms, in which a parallel client-server single population fuzzy genetic algorithm is configured to optimize the performance of the first three Dejong functions in order to reach a global solution in the least possible iterations. Simulations show much improvement in genetic algorithm performance evaluation.

Mohsen Amini Salehi, Hossain Deldari, A Novel Load Balancing Method in an Agent-based Grid, IEEE International Conference on Computing and Informatics (ICOCI 2006), June 6-8, 2006, Kuala Lumpur, Malaysia.

A computational grid is a widespread computing environment which provides huge computational power for large-scale distributed applications. One of the most important issues in such an environment is resource management. Load balancing which is a part of resource manager, has a considerable effect on resources’ performance. There are several factors which affect the stability of the load balancing in the grid. Among these factors, accurate criterion for estimating the workload, considering the workload transmission cost, validity of the information about other nodes and the overhead imposed by the method are more effective. In this paper we propose a novel method for load balancing which tries to satisfy these factors. The proposed method is implemented on an agent-based resource management system, called ARMS. There are several simulations which indicate that the proposed method outperforms than similar methods.

Mohsen Amini Salehi, Hossain Deldari, Grid Load Balancing using an Echo System of Intelligent Ants, In Proceedings of the IASTED International Conference on Parallel and distributed Computing and Networks, Pages 47-52, Feruary 2006, Innsbruck, Austria.

A computational grid is a widespread computing environment that provides huge computational power for large-scale distributed applications. One of the most important issues in such an environment is resource management for which agent-based approaches are appropriate. Load balancing as a part of resource management, has a considerable effect on performance. Ant colony is a metaheuristic that can be instrumental for grid load balancing. This paper presents an echo system of intelligent, autonomous and cooperative ants. The ants in this environment can procreate and also may commit suicide depending on existing conditions. A new concept called Ant level load balancing is presented for improving the performance of the mechanism. A performance evaluation model is derived. Theoretical analyses and simulation results indicate that this new mechanism surpasses its predecessor.

Mojtaba Sabeghi, Hossein Deldari, Vahid Salmani, Malihe Bahekmat, Toktam Taghavi, A Fuzzy Algorithm for Real-Time Scheduling of Soft Periodic Tasks on Multiprocessor Systems, In Proceedings of IADIS International Conference on Applied Computing, February 25-28, 2006, San Sebastian, Spain, Pages 467-471.

Many scheduling algorithms have been studied to guarantee the time constraints of real-time processes. Scheduling decision of these algorithms is usually based on parameters which are assumed to be crisp. However, in many circumstances the values of these parameters are vague. The vagueness of parameters suggests that we make use of fuzzy logic to decide in what order the requests should be executed to better utilize the system and as a result reduce the chance of a request being missed. Our main contribution is proposing a fuzzy approach to multiprocessor real-time scheduling in which the scheduling parameters are treated as fuzzy variables. A simulation is also performed and the results are judged against each other. It is concluded that the proposed fuzzy approach is very promising and it has the potential to be considered for future research.

M. Sabeghi, H. Deldari, and S. Khajouei, A Fuzzy Algorithm for Scheduling Periodic Tasks on Multiprocessor Soft Real-Time Systems, International Journal of Computer Science and Network Security, Pages 88-97, March 30, 2006. Also appeared in the Proceedings of the 17th IASTED International Conference Modeling And Simulation Pages 436-442, May 2006 , Montreal, QC. Canada.

In this paper we consider the use of fuzzy logic in the scheduling of periodic tasks in soft real-time multiprocessor systems. Most researches concerning real-time system scheduling assumes scheduling constraint to be precise. However, in many circumstances the values of these parameters are vague. The vagueness of parameters suggests that we make use of fuzzy logic to decide in what order the requests should be executed to better utilize the system and as a result reduce the chance of a request being missed. Our main contribution is proposing a fuzzy approach to multiprocessor real-time scheduling in which the scheduling parameters are treated as fuzzy variables. A simulation is also performed and the results are judged against each other. It is concluded that the proposed fuzzy approach is very promising and it has the potential to be considered for future research.

Ebrahim Bagheri, Hossein Deldari, Fuzzy Genetic Algorithm Parallelization for Dejong Function Optimization, International Journal of Pure and Applied Mathematics, 2006, vol.26 no. 3, Pages 321-334.

Genetic Algorithms are very powerful search methods that are used in different optimization problems. Parallel versions of genetic algorithms are easily implemented and usually increase algorithm performance. Fuzzy control as another optimization solution along with genetic algorithms can significantly increase algorithm performance. Two variations for genetic algorithm and fuzzy system composition exist. In the first approach Genetic algorithms are used to optimize and model the structure of fuzzy systems through knowledge base or membership function design while the second approach exploits fuzzy to dynamically supervise genetic algorithm performance by speedily reaching an optimal solution. In this paper we propose a new method for fuzzy parallel genetic algorithms, in which a parallel client-server single population fuzzy genetic algorithm is configured to optimize the performance of the first three Dejong functions in order to reach a global solution in the least possible iterations. Simulations show much improvement in genetic algorithm performance evaluation.

Ebrahim Bagheri, Hossein Deldari, Designing a Fuzzy Parallel Genetic Algorithm, 10th International Annual Computer Conference of Iran Computer Society (CSICC’05), 2005, Tehran, Iran.

Roohollah Mafi, Hossein Deldari, Mojtaba Mazoochi, Alchemi+: An Agent-Based Approach to Grid Programming, Parallel Processing and Applied Mathematics, 6th International Conference, (PPAM 2005), Poznan, Poland, September 11-14, 2005, Pages 188-195.

Computational grids have provided the usage of computational distributed resources for computation intensive applications. The development of programs that use these capabilities is one of the challenging issues for grid computing. In this article, an effort has been made to solve this problem by presenting mobile-agent-based parallel programming on the grid. The presentation of this model which has been realized by extending Alchemi^TM grid system with adding agent properties and navigational commands that let user to develop his program by using mobile agents. To evaluate the system, algorithms of matrix multiplication and convex hull have been implemented in the mentioned system.

H. Deldari and T. Ghafarian, Parallel Genetic Algorithm Using Algorithmic Skeleton, ESTEGHLAL Journal of Engineering Isfahan University of Technology, Volume 22, No 2, Pages 1-19, March 2004.

H. Deldari, Performance Modeling of Parallel Algorithmic Skeletons, In Proceeding of the third International Annual Computer Conference of the Computer Society of Iran, CSICC'97, Computer Engineering Department , Iran University of Science and technology , Tehran, Iran, December 23-25, 1997, pages 75-85.

Several authors have proposed the use of algorithmic skeletons as a high-level, machine-independent means of developing parallel programs. This paper addresses the question of modeling the performance of such skeletons. This model is a generic higher order complexity function. Instatiation of the skeleton with specific set of functional parameters enables the time complexity of the particular application to be derived. The approach is illustracted by case studies based on application-specifi languages for image processing. The computational model used in this study is BSP. Two different versions of algorithms have been designed and implementd and the performance model for both version have been derived.

H. Deldari, J.R. Davy, P.M. Dew, A Skeleton for Parallel CSG with a Performance Model, Technical report, School of computer studies research report series, University of Leeds, 1997.

We Describe a metholdology for modelling the performance of the parallel algorithmic skeletons and illustrate it using a new skeleton which supports set membership classification problems in Constructive Solid Geometry. These problems are characterised by potentially unbalances tree structures with data-dependent computations at the nodes. The skeleton achieves good parallel efficiency on the class of computations permitted, the methodology accurately predicts the asymptotic performance of specific CSG applications.

H. Deldari, J.R. Davy  and P. M. Dew, Parallel CSG, Skeletons and Performance Modeling, In Proceeding of the Second Annual Computer Conference (CSICC 96), pages 115 -122, Amirkabir University of technology, December 1996.

We describe an efficient implementation of a parallel algorithmic skeleton which supports set membership classification problems in constructive Solid Geometry. A performance modeling methodology is developed, which realistically predicts the asymptotic performance of specific CSG applications.

H. Deldari, A Performance Study for Parallel Algorithmic Skeletons, PhD thesis, University of Leeds, Division of Computer Science, 1996.

H. Deldari, John Davy, Peter Dew, The Performance of Parallel Algorithmic Skeletons, In Parallel Programming and Applications edited by Peter Fritzson and Leif Finmo Pages 65-74, IOS Press 1995.

Several authors have proposed the use of algorithmic skeletons as a high-level machine independent means of developing parallel programs.  This paper addresses the question of modeling the performance of such skeletons. The execution time for a skeleton is presented as a generic higher order complexity function. Instantiation of the skeleton with a specific set of functional parameters enables the time complexity of the particular application to be derived. The approach is illustrated by examples based on existing special purpose languages for image processing, and is extended to analyse the scalability of skeleton-based applications, using isoefficiency functions.

John Davy, Hossain Deldari, Peter M. Dew, Constructive Solid Geometry Using Algorithmic Skeletons, In Proceeding of the fifth Eurographics workshop on Programming Paradigms in Graphics, held in Maastricht, The Netherlands, September 2-3, 1995.

This paper presents a feasibility study in the use of parallel algorithmic skeletons to program applications of constructive solid geometry(CSG). The potential for such an approach arises from the frequent use of divide-and-conquer (D&C) methods in this domain, which are amenable to highly parallel implementation. A prototype Geometric Evaluation Library (GEL) is described, which captures the structure of these algorithms. GEL includes a small set of polymorphic high-order functions, which capture the fundamental algorithmic structures independently of underlying geometric domain. An efficient parallel implementation of one of these functions shows the potential to develop them as parallel algorithmic skeletons. The paper concludes with a discussion of the potential for further developments of this approach.

J. R. Davy, H. Deldari, and P. M. Dew, Constructive Solid Geometry Using Parallel Algorithmic Skeletons, In Proceedings 5th Eurographics Workshop on Programming Paradigms for Graphics, Springer, 1995.