Optimasi Load Balancing Menggunakan Algoritma Simulated Annealing dan Harmony Search di Cloud Environment

Maye, Aqil Sulthan Yuki (2025) Optimasi Load Balancing Menggunakan Algoritma Simulated Annealing dan Harmony Search di Cloud Environment. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5027211007-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Cloud computing merupakan fondasi utama dalam penyediaan layanan teknologi informasi modern, namun dinamika volume permintaan pengguna menuntut solusi penyeimbangan beban (load balancing) yang optimal agar sistem tetap efisien dan responsif. Penelitian ini mengusulkan dan menganalisis Hybrid Simulated Annealing–Harmony Search (Hybrid SA–HS) sebagai algoritma optimasi load balancing di lingkungan cloud. Kinerja Hybrid SA–HS dievaluasi secara komprehensif, baik melalui simulasi menggunakan CloudSim dengan tiga jenis dataset (Simple Random, Stratified Random, dan SDSC Blue Horizon Log), maupun pada implementasi real environment (IRE) berbasis Docker. Efektivitas Hybrid SA–HS dibandingkan dengan Simulated Annealing (SA), Harmony Search (HS), serta algoritma pembanding Particle Swarm Optimization (PSO) dan Genetic Algorithm (GA). Hasil eksperimen menunjukkan Hybrid SA–HS secara konsisten unggul pada parameter Imbalance Degree, dengan rata-rata 0,012 pada Simple Random, 0,297 pada Stratified Random, 0,079 pada SDSC, dan 0,058 pada real environment, yang lebih rendah daripada SA dan HS. Hybrid SA–HS juga menunjukkan hasil terbaik pada Makespan (SDSC: 83.355,74 ms; IRE: 142.838,40 ms), Average Finish Time (Stratified Random: 18.123,98 ms; IRE: 68.283,37 ms), dan Average Execution Time pada real environment (11.235,36 ms). Penelitian ini menunjukkan bahwa Hybrid SA–HS merupakan solusi optimasi load balancing yang efektif, khususnya dalam mengatasi tantangan Imbalance Degree. Selain itu, algoritma ini juga terbukti efektif dalam menurunkan nilai Makespan, Average Finish Time, dan Average Execution Time pada lingkungan cloud yang kompleks dan dinamis.

=========================================================================================================================================

Cloud computing serves as a fundamental platform for delivering modern information technology services; however, the dynamic volume of user demands necessitates optimal load balancing solutions to ensure system efficiency and responsiveness. This research proposes and analyzes the Hybrid Simulated Annealing–Harmony Search (Hybrid SA–HS) algorithm as an optimization approach for load balancing in cloud environments. The performance of Hybrid SA–HS is comprehensively evaluated, both through simulations using CloudSim with three types of datasets (Simple Random, Stratified Random, and SDSC Blue Horizon Log), and through implementation in a real environment (IRE) based on Docker. The effectiveness of Hybrid SA–HS is compared to Simulated Annealing (SA), Harmony Search (HS), as well as benchmark algorithms Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Experimental results demonstrate that Hybrid SA–HS consistently outperforms other methods in the Imbalance Degree parameter, with average values of 0.012 on Simple Random, 0.297 on Stratified Random, 0.079 on SDSC, and 0.058 on the real environment, all lower than those of SA and HS. Hybrid SA–HS also achieves the best results for Makespan (SDSC: 83,355.74 ms; IRE: 142,838.40 ms), Average Finish Time (Stratified Random: 18,123.98 ms; IRE: 68,283.37 ms), and Average Execution Time in the real environment (11,235.36 ms). This study demonstrates that Hybrid SA–HS is an effective load balancing optimization solution, particularly in addressing Imbalance Degree challenges. In addition, this algorithm proves to be effective in reducing Makespan, Average Finish Time, and Average Execution Time in complex and dynamic cloud environments.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Load Balancing, Cloud Computing, Hybrid SA–HS, Simulated Annealing, Harmony Search, Load Balancing, Cloud Computing, Hybrid SA–HS, Simulated Annealing, Harmony Search.
Subjects:	Q Science > QA Mathematics > QA76.585 Cloud computing. Mobile computing. Q Science > QA Mathematics > QA76.9 Computer algorithms. Virtual Reality. Computer simulation.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information Technology > 59201-(S1) Undergraduate Thesis
Depositing User:	Aqil Sulthan Yuki Maye
Date Deposited:	22 Jul 2025 08:18
Last Modified:	22 Jul 2025 08:18
URI:	http://repository.its.ac.id/id/eprint/120635

Actions (login required)

View Item