Implementasi Algoritma Improvised Prioritized Deadline Scheduling Algorithm (IPDSA) pada Grid Environment Menggunakan PVM3

Resource Scheduling is one of the most challenging parts of grid computing. A number of algorithms have been designed and developed to create effective resource scheduling. In this research, the algorithms that have been used are the improvised prioritized deadline scheduling algorithm (IPDSA), and the parallel virtual machine version 3 (PVM3) has been used for efficient task execution, with a deadline limit for each task. PVM3 is a software library that optimizes resources flexibly and heterogeneously on a computer. These resources have been connected to various architectures in parallel, so that they can complete tasks well, even though they are very large and complex. This research has implemented the IPDSA resource scheduling algorithm to optimize scheduling and Grid resources in a computer laboratory as a grid environment, where the computers (hosts) are the Grid resource. This research has also developed an IPDSA resource scheduling algorithm by giving priority to each task and implemented using PVM3. The IPDSA resource scheduling algorithm has been successfully implemented using PVM3, with average Tardiness showing a stable value and getting a Non-Delayed Task value above 97.3%, because the resources and tasks that are carried out can be distributed evenly according to the number of hosts used.

Investigations on RELAP5-3D to RELAP5-3D Coupling Methodology by PVMEXEC

In the framework of a BEPU (Best Estimate Plus Uncertainty) approach within the licensing process of a nuclear power plant, the need to extend the resources of nuclear system thermal-hydraulics codes, such as RELAP5-3D, arises to allow more detailed simulations of the complex 3D reality of Nuclear Power Plants (NPPs), either under normal steady-state or during various accident scenarios. Currently, it is not possible to achieve the same degree of detail for a whole nuclear system when it is simulated with RELAP5-3D and this is due to the inherent limitations in the number of components and volumes to be used for the analysis. For this reason, it is of extreme interest the use of tools for codes coupling that enable the use of different codes for the simulation of different portions of a system in a unified analysis. In this paper the attention will be focused on the decomposition of the thermal-hydraulic domain of a system into subsystems to be simulated by different instances of the same code (e.g. RELAP5-3D) coupled together by means of PVMEXEC program and parallel virtual machine (PVM) technology. Explicit and semi-implicit solution algorithms were used for the analyses. Among the analyzed cases, the following will be discussed in detail with the aim to provide additional guidelines for the use of the PVMEXEC tool: (i) the Edward’s pipe blowdown test, (ii) a simplified countercurrent heat exchanger, (iii) different hydraulics and heat structure coupling schemes for a shell-tube heat exchanger and (iv) a three-task coupled model of a simplified BWR model.

METODE CONJUGATE GRADIENT PARAREL UNTUK MENYELESAIKAN SISTEM PERSAMAAN LINEAR DALAM SCILAB

<p>Komputasi paralel merupakan salah satu alternatif untuk meningkatkan kinerja komputasi. Komputasi paralel bertujuan menyelesaikan masalah komputasi yang besar dan mempercepat waktu eksekusinya. Komputasi paralel yang dilakukan dalam percobaan menggunakan beberapa komputer dalam satu jaringan. <em>Software </em>yang digunakan dalam percobaan adalah SCILAB dan <em>Parallel Virtual Machine </em>(PVM). Masalah komputasi yang akan diselesaikan adalah penyelesaian sistem persamaan linear dengan menggunakan metode <em>Conjugate Gradient </em>(CG). Algoritma parallel dari metode <em>Conjugate Gradient </em>dibuat agar metode ini dapat diterapkan secara paralel. Waktu eksekusi metode <em>Conjugate</em> <em>Gradient </em>baik secara sekuensial maupun paralel untuk menyelesaikan sistem persamaan linear yang sama dalam percobaan diamati. Percobaan dilakukan terhadap 3 buah sistem persamaan linear dengan matrik koefisien <em>A </em>yang berbeda. Percobaan metode <em>Conjugate Gradient </em>paralel untuk sistem persamaan linear dengan matriks nos3 dan matriks ex13 berhasil mencapai <em>speedup </em>yang dicapai pada percobaan paralel untuk matriks ex13_30_30 sangat kecil, artinya waktu eksekusinya cenderung sama atau lebih lambat dari pada waktu eksekusinya. <em>Speedup </em>yang dicapai pada setiap percobaan paralel selalu bertambah seiring bertambahnya jumlah komputer yang digunakan. <em>Speedup </em>yang dicapai pada setiap percobaan metode <em>Conjugate Gradient </em>paralel untuk nilai toleransi 10^-10 lebih besar dibandingkan pada percobaan untuk toleransi 10^-5.</p>