Optimasi Cloud Task Scheduling Menggunakan Algoritma Self-Adaptive Jellyfish Search Optimizer (SAJSO) Dengan Opposition Based Learning (OBL) Pada Cloud Environment

Saniane, Sharira (2024) Optimasi Cloud Task Scheduling Menggunakan Algoritma Self-Adaptive Jellyfish Search Optimizer (SAJSO) Dengan Opposition Based Learning (OBL) Pada Cloud Environment. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5027201016-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (4MB) | Request a copy

Abstract

Cloud Computing memainkan peran penting dalam dunia teknologi saat ini dengan menyediakan akses mudah ke sumber daya TI melalui internet. Namun, tantangan dalam penjadwalan tugas cloud dapat menurunkan kinerja sistem. Jellyfish Search Optimizer (JSO), yang terinspirasi dari perilaku ubur-ubur, merupakan salah satu solusi efektif untuk penjadwalan tugas cloud. Dalam penelitian ini, JSO digabungkan dengan Opposition-Based Learning (OBL) untuk memanfaatkan informasi dari solusi berlawanan dan memilih solusi terbaik, serta diterapkan juga Self-Adaptive Jellyfish Search Optimizer (SAJSO) yang mampu secara dinamis menyesuaikan parameter. Evaluasi kinerja algoritma dilakukan terhadap berbagai parameter menggunakan cloud simulator dan Eclipse IDE. Hasil menunjukkan bahwa JSO unggul pada parameter makespan dan imbalance degree pada Dataset Stratified Random, sementara JSO OBL unggul pada parameter imbalance degree dengan dataset SDSC. SAJSO menunjukkan keunggulan pada parameter total energy consumption pada dataset SDSC, dan SAJSO OBL unggul pada resource utilization untuk seluruh dataset, makespan dan throughput untuk dataset SDSC, serta throughput pada dataset Stratified Random. Namun, JSO, JSO OBL, SAJSO, dan SAJSO OBL tidak unggul pada parameter average start time, average finish time, average execution time, total wait time, dan total scheduling length pada ketiga dataset. JSO direkomendasikan untuk parameter makespan, throughput, resource utilization, total energy consumption, dan imbalance degree pada dataset dengan kompleksitas sedang hingga tinggi.
=================================================================================================================================
Cloud Computing plays a crucial role in today's technology landscape by providing easy access to IT resources over the internet. However, challenges in cloud task scheduling can degrade system performance. The Jellyfish Search Optimizer (JSO), inspired by the behavior of jellyfish, is an effective solution for cloud task scheduling. In this study, JSO is combined with Opposition-Based Learning (OBL) to leverage information from opposite solutions and select the best solution. Additionally, the Self-Adaptive Jellyfish Search Optimizer (SAJSO) is implemented to dynamically adjust parameters during the optimization process. The performance evaluation of the algorithms was conducted on various parameters using a cloud simulator and Eclipse IDE. Results show that JSO excels in makespan and imbalance degree parameters on the Stratified Random dataset, while JSO OBL excels in the imbalance degree parameter with the SDSC dataset. SAJSO shows superiority in the total energy consumption parameter on the SDSC dataset, and SAJSO OBL excels in resource utilization across all datasets, makespan and throughput for the SDSC dataset, and throughput on the Stratified Random dataset. However, JSO, JSO OBL, SAJSO, and SAJSO OBL do not perform well on parameters such as average start time, average finish time, average execution time, total wait time, and total scheduling length across all three datasets, indicating that GA and PSO are superior in these aspects. JSO is recommended for makespan, throughput, resource utilization, total energy consumption, and imbalance degree parameters on datasets with moderate to high complexity.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Cloud computing, Cloud task scheduling, Jellyfish Search Optimizer (JSO), Cloudsim, IDE dan Opposition Based Learning (OBL), Task Scheduler
Subjects:	T Technology > T Technology (General)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis
Depositing User:	Sharira Saniane
Date Deposited:	18 Jul 2024 05:07
Last Modified:	18 Jul 2024 05:07
URI:	http://repository.its.ac.id/id/eprint/108433

Actions (login required)

View Item