Mennde, Gennaro Fajar (2024) Penggunaan Whale Optimization Algorithm (WOA) dan Opposition-Based Learning (OBL) sebagai Task Scheduler dalam Cloud Environment. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5027201061-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5027201061-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (5MB) | Request a copy |
Abstract
Di era informasi yang berkembang cepat, cloud computing menjadi solusi penting untuk memenuhi kebutuhan komputasi yang kompleks dan meningkatkan efisiensi sumber daya. Dalam lingkungan ini, penjadwalan tugas yang efisien sangat krusial untuk mengoptimalkan alokasi sumber daya dan meminimalisir waktu eksekusi untuk meningkatkan kinerja sistem. Whale Optimization Algorithm (WOA), sebuah algoritma meta-heuristik yang terinspirasi dari perilaku mencari makan paus, efektif dalam menjelajahi ruang pencarian dan bisa diterapkan untuk optimasi penjadwalan tugas. Untuk meningkatkan efektivitasnya, teknik Opposition-Based Learning (OBL) diintegrasikan, yang memanfaatkan konsep oposisi untuk mencapai solusi optimal dengan lebih cepat. Penggunaan Eclipse IDE dan Cloudsim dalam penelitian ini memungkinkan pengembangan dan pengujian model penjadwalan tugas yang lebih efisien. Penilaian kinerja algoritma ditentukan berdasarkan beberapa parameter penilaian Hasil penelitian ini, yang membandingkan penggunaan WOA dengan dan tanpa OBL, serta dengan Genetic Algorithm (GA) dan Particle Swarm Optimization (PSO), menunjukkan WOA-OBL unggul dalam makespan, average start time, average finish time, dan total energy consumption. Pada makespan, WOA-OBL 24,27% lebih unggul dibanding PSO. Pada average start time, WOA-OBL 9,34% lebih unggul dibanding GA. Pada average finish time, WOA-OBL 9,02% lebih unggul dibanding GA. Pada total energy consumption, WOA-OBL 15.16% lebih unggul dibanding GA.
=====================================================================================================================================
In the rapidly developing information era, cloud computing has become an important solution to meet complex computing needs and increase resource efficiency. In this environment, efficient task scheduling is crucial to optimize resource allocation and minimize execution time to improve system performance. Whale Optimization Algorithm (WOA), a meta-heuristic algorithm inspired by the foraging behavior of whales, is effective in exploring the search space and can be applied for task scheduling optimization. To increase its effectiveness, the Opposition-Based Learning (OBL) technique is integrated, which utilizes the concept of opposition to reach optimal solutions more quickly. The use of Eclipse IDE and Cloudsim in this research allows the development and testing of more efficient task scheduling models. Algorithm performance assessment is determined based on several assessment parameters. The results of this study, which compare the use of WOA with and without OBL, as well as with Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), show that WOA-OBL is superior in makespan, average start time, average finish time, and total energy consumption. In makespan, WOA-OBL is 24.27% superior to PSO. In average start time, WOA-OBL is 9.34% superior to GA. In average finish time, WOA-OBL is 9.02% superior to GA. In total energy consumption, WOA-OBL is 15.16% superior to GA.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Cloud Computing, Efesiensi, Opposition-Based Learning (OBL), Task scheduling, Whale Optimization Algorithm (WOA), Efficiency, |
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T57.62 Simulation T Technology > T Technology (General) > T57.84 Heuristic algorithms. |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis |
| Depositing User: | Gennaro Fajar Mennde |
| Date Deposited: | 25 Jul 2024 03:58 |
| Last Modified: | 25 Jul 2024 03:58 |
| URI: | http://repository.its.ac.id/id/eprint/108829 |
Actions (login required)
 |
View Item |