Analisis Cloud Task Scheduling Menggunakan Algoritma Squirrel Search and Opposition-Based Learning

Fauzan, Muhammad Nur (2023) Analisis Cloud Task Scheduling Menggunakan Algoritma Squirrel Search and Opposition-Based Learning. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05311940000035-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (2MB) | Request a copy

Abstract

Algoritma pencarian yang efisien dan efektif dalam alokasi sumber daya di lingkungan Cloud Computing memiliki peran penting dalam meningkatkan kinerja dan efisiensi sistem. Dalam penelitian ini, kami membandingkan Squirrel Search Algorithm (SSA) dengan Genetic Algorithm (GA) dalam konteks optimisasi alokasi sumber daya. Parameter penilaian yang digunakan meliputi Total Wait Time, Average Start Time, Average Execution Time, Average Finish Time, Throughput, Makespan, imbalance degree, total Scheduling Length, Resource Utilization, dan total Energy Consumption. Hasil eksperimen menunjukkan bahwa SSA memiliki kinerja yang lebih baik dibandingkan dengan GA dalam sebagian besar parameter penilaian yang digunakan. Dalam penggunaan simple dataset, SSA berhasil melampaui GA dalam hampir semua parameter, kecuali Average Execution Time. Dalam hal Resource Utilization, SSA mencapai peningkatan signifikan dari 56,02% (GA) menjadi 75,63%. Selain itu, total Energy Consumption juga mengalami penurunan yang signifikan dari 55,37 kWh (GA) menjadi 42,68 kWh (SSA). Penelitian ini memberikan wawasan yang lebih detail tentang keunggulan relatif dari SSA dan GA dalam konteks optimisasi alokasi sumber daya di lingkungan Cloud Computing. Hasil penelitian menunjukkan bahwa SSA mampu meningkatkan efisiensi penggunaan sumber daya dengan peningkatan Resource Utilization dan mengurangi konsumsi energi secara signifikan. Oleh karena itu, SSA dapat dianggap sebagai algoritma yang lebih unggul dalam hal efisiensi dan penghematan energi.
===============================================================================================================================
Efficient and effective resource allocation algorithms in Cloud Computing environments play a vital role in improving system performance and efficiency. In this research, we compare the Squirrel Search Algorithm (SSA) with the Genetic Algorithm (GA) in the context of resource allocation optimization. The evaluation parameters used include Total Wait Time, Average Start Time, Average Execution Time, Average Finish Time, Throughput, Makespan, imbalance degree, total Scheduling Length, Resource Utilization, and total Energy Consumption. The experimental results demonstrate that SSA outperforms GA in most of the evaluation parameters. In the case of a simple dataset, SSA surpasses GA in almost all parameters, except for Average Execution Time. Notably, SSA achieves a significant improvement in Resource Utilization, increasing it from 56.02% (GA) to 75.63%. Moreover, the total Energy Consumption also experiences a significant reduction, decreasing from 55.37 kWh (GA) to 42.68 kWh (SSA). This research provides detailed insights into the relative advantages of SSA and GA in the context of resource allocation optimization in Cloud Computing. The results highlight that SSA enhances Resource Utilization efficiency, leading to substantial improvements, while also reducing Energy Consumption significantly. Therefore, SSA can be considered a superior algorithm in terms of efficiency and energy savings.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Cloud Computing, Resource Utilization, Resource Allocation Optimization, Squirrel Search Algorithm, 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:	Muhammad Nur Fauzan
Date Deposited:	08 Sep 2023 04:55
Last Modified:	08 Sep 2023 04:55
URI:	http://repository.its.ac.id/id/eprint/103868

Actions (login required)

View Item