Comparison of Fine Grained and Coarse Grained Parallel Models in Particle Swarm Optimization Algorithm

Date

2011-11-23

Author

Baştürk, Alper
Akay, Rüştü
Kalınlı, Adem

Metadata

Show full item record

Item Usage Stats

110
views

0
downloads

Many optimization problems are generally complex and required to be solved in parallel architectures due to theircomputational costs. The main issue about the parallelism is that the parallel architectures may affect the performancebecause the original models are constructed based upon the sequential architectures. Therefore, the parallelizationapproaches should consider the efficiency in addition to reducing computational cost. The objective of this paper is two-fold.First goal is presenting a parallelization approaches and investigating the performance efficiency of the parallel models.Second purpose is implementing the models in parallel programming environments and examining the time efficiency. In thisstudy, two parallel models are developed for Particle Swarm Optimization (PSO) algorithm: fine-grained and coarse-grainedmodels. The models are tested on some benchmark problems. Results demonstrate that the parallel models considered canbe efficiently used for improving both performance and speed-up.

Subject Keywords

Parallel approaches, Fine-grained, Coarse-grained, Particle swarm optimization

URI

https://hdl.handle.net/11511/72077
http://archives.un-pub.eu/index.php/P-ITCS/issue/view/53/showToc

Conference Name

2nd World Conference on Information Technology WCIT-2011, (23 - 27 Kasım 2011)

Collections

Other, Conference / Seminar

Suggestions

OpenMETU
Core

Efficient solution of optimization problems with constraints and/or cost functions expensive to evaluate Kurtdere, Ahmet Gökhan; Leblebicioğlu, Mehmet Kemal; Department of Electrical and Electronics Engineering (2009) There are many optimization problems motivated by engineering applications, whose constraints and/or cost functions are computationally expensive to evaluate. What is more derivative information is usually not available or available at a considerable cost. For that reason, classical optimization methods, based on derivatives, are not applicable. This study presents a framework based on available methods in literature to overcome this important problem. First, a penalized model is constructed where the viola...
Comparative study on explicit integration algorithms for structural dynamics Çakır, Dilara; Kurç, Özgür; Department of Civil Engineering (2022-8) Conventional explicit integration algorithms used to solve structural dynamic problems may require too small time increments to satisfy the stability requirements in the presence of high-frequency modes. The requirement to have a too small time increment can cause extending the solution time above the tolerable limit. In this study, three different explicit integration algorithms found in the literature are compared in terms of stability, accuracy, and run-time. The examined integration methods are a two-st...
Data-parallel programming on Helios, Parallel environment and PVM Sener, C; Paker, Y; Kiper, A (1996-09-27) Parallel computing, increasingly used for computationally intensive problems, requires considerable expertise and time, limiting then widespread use. This article presents a data-parallel programming tool to simplify the task of developing parallel programs based on data-parallel type. It has been originally developed for the Hellos operating system running on a network of Transputers, and then ported to the IBM SP/2 system executing two parallel programming environments. With its interface to the C languag...
Parallel Scalable PDE Constrained Optimization Antenna Identification in Hyperthermia Cancer Treatment Planning SCHENK, Olaf; Manguoğlu, Murat; CHRİSTEN, Matthias; SATHE, Madan (Springer Science and Business Media LLC, 2009-01-01) We present a PDE-constrained optimization algorithm which is designed for parallel scalability on distributed-memory architectures with thousands of cores. The method is based on a line-search interior-point algorithm for large-scale continuous optimization, it is matrix-free in that it does not require the factorization of derivative matrices. Instead, it uses a new parallel and robust iterative linear solver on distributed-memory architectures. We will show almost linear parallel scalability results for t...
Parallel solution of sparse linear systems to find the shortest path in large scale graphs Arslan, Hilal; Manguoğlu, Murat (2018-06-29) Solving the shortest path problem on large scale networks is crucial for many applications. As parallelism became more common with the advent of multi-core architectures as well as large and complex networks have begun to emerge in many settings, it is inevitable to come up with algorithms that take advantage of the current architectures. One alternative to solve the shortest path problem is to use one of the classical or improved parallel variations of the Dijkstra’s algorithm. However, when the size of th...

Citation Formats

A. Baştürk, R. Akay, and A. Kalınlı, “Comparison of Fine Grained and Coarse Grained Parallel Models in Particle Swarm Optimization Algorithm,” Antalya, Türkiye, 2011, p. 751, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/72077.