Cloud Task Scheduling Menggunakan Chimp Optimization Algorithm (ChOA) Dengan Opposition Based Learning (OBL) Pada Cloud Environment

Yumna, Muhamad Ilham (2025) Cloud Task Scheduling Menggunakan Chimp Optimization Algorithm (ChOA) Dengan Opposition Based Learning (OBL) Pada Cloud Environment. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5027211024-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Penjadwalan tugas merupakan aspek krusial dalam cloud computing karena memengaruhi efisiensi pemanfaatan sumber daya dan kinerja sistem secara keseluruhan. Salah satu algoritma metaheuristik yang digunakan untuk mengatasi permasalahan ini adalah Chimp Optimization Algorithm (ChOA), algoritma ini memiliki keterbatasan dalam hal eksplorasi global dan kecenderungan terjebak pada solusi lokal. Untuk mengatasi hal tersebut, penelitian ini mengusulkan penggabungan ChOA dengan pendekatan Opposition-Based Learning (OBL) pada tahap inisialisasi populasi guna meningkatkan keberagaman solusi awal dan kemampuan eksplorasi. Evaluasi dilakukan menggunakan tiga dataset simulasi (Simple Random, Stratified Random, dan SDSC) serta satu skenario Real Environment. Hasil penelitian menunjukkan bahwa ChOA-OBL cukup efektif dalam menyelesaikan masalah task scheduling, khususnya pada skenario dengan distribusi tugas yang homogen atau moderat. Hal ini ditunjukkan oleh dominasi performa ChOA-OBL pada hampir seluruh parameter evaluasi di dataset Simple Random dan Real Environment, seperti Total Wait Time sebesar 28.438.864,11 dan Makespan 13.266,42 pada Simple Random, serta Total Wait Time 127.871.964,60 dan Makespan 256,94 pada Real Environment. Namun, pada dataset dengan distribusi nilai tersegmentasi atau kompleks seperti Stratified Random dan SDSC, efektivitas algoritma menurun akibat solusi oposisi yang tidak kontekstual sehingga dapat mengganggu arah pencarian ChOA.
=======================================================================================================================================
Task scheduling is a crucial aspect of cloud computing, as it affects the efficiency of resource utilization and the overall system performance. One of the metaheuristic algorithms used to address this problem is the Chimp Optimization Algorithm (ChOA), although this algorithm has limitations in global exploration and a tendency to get trapped in local optima. To overcome these issues, this study proposes combining ChOA with the Opposition-Based Learning (OBL) approach during the initial population phase to improve the diversity of initial solutions and exploration capabilities. The evaluation was conducted using three simulated datasets (Simple Random, Stratified Random, and SDSC) and one Real Environment scenario. The results indicate that ChOA-OBL is quite effective in solving the task scheduling problem, especially in scenarios with homogeneous or moderate task distributions. This is demonstrated by the dominance of ChOA-OBL performance across almost all evaluation parameters on the Simple Random and Real Environment datasets, such as a Total Wait Time of 28,438,864.11 and Makespan of 13,266.42 on Simple Random, as well as a Total Wait Time of 127,871,964.60 and Makespan of 256.94 on Real Environment. However, on datasets with segmented or complex value distributions such as Stratified Random and SDSC, the algorithm's effectiveness decreased due to non-contextual opposition solutions that could disrupt the ChOA search direction. Nevertheless, overall, ChOA-OBL remained adaptive and superior in maintaining scheduling system efficiency in cloud environments.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Chimp Optimization Algorithm (ChOA), Cloud Computing, Opposition-Based Learning (OBL), Penjadwalan Tugas, Chimp Optimization Algorithm (ChOA), Cloud Computing, Opposition-Based Learning (OBL), Task Scheduling
Subjects:	Q Science > QA Mathematics > QA76.585 Cloud computing. Mobile computing.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis
Depositing User:	Muhamad Ilham Yumna
Date Deposited:	30 Jul 2025 08:59
Last Modified:	30 Jul 2025 08:59
URI:	http://repository.its.ac.id/id/eprint/123780

Actions (login required)

View Item