Identifikasi anomali pada komputasi awan dengan pendekatan process mining : inductive miner dan alpha miner = Identification of anomaly in cloud computing with process mining approach: inductive miner and alpha miner

NUGRAHA, ZHILLAN ADRIAN (2024) Identifikasi anomali pada komputasi awan dengan pendekatan process mining : inductive miner dan alpha miner = Identification of anomaly in cloud computing with process mining approach: inductive miner and alpha miner. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (338kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (597kB)
[thumbnail of ToC] Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chpater1] Text (Chpater1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (775kB)
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (916kB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (950kB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (780kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (621kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)

Abstract

Cloud computing systems play a vital role in large-scale data processing with high flexibility. However, their complexity causes challenges in detecting anomalies that may indicate system disruptions, security breaches, or process inefficiencies. Manual detection becomes ineffective due to the large volume of log data. Therefore, this study applies a Process Mining approach using Inductive Miner, Alpha Miner, and Conformance Analysis to identify anomalies in cloud system logs. This study begins with the collection of log data from open sources, followed by preprocessing to ensure compatibility with process mining techniques. A process model is then built using Inductive Miner and Alpha Miner to represent the system activity flow. Furthermore, Conformance Analysis is used to evaluate the model's suitability to actual execution, identifying deviation patterns that may be indicators of anomalies. The results show that the combination of these three methods provides an in-depth understanding of system activity patterns as well as anomaly detection based on process path deviations and abnormal time gaps. Inductive Miner is proven effective in visualizing process patterns comprehensively, while Alpha Miner is able to identify basic patterns despite being sensitive to noise. Conformance Analysis reveals deviations between the ideal model and actual execution, indicating bottlenecks and resource mismatches such as disk I/O utilization and network traffic. These findings confirm that process mining can be an effective tool in analyzing and optimizing cloud systems to improve operational efficiency. / Sistem komputasi awan memainkan peran penting dalam pemrosesan data berskala besar dengan fleksibilitas tinggi. Namun, kompleksitasnya menyebabkan tantangan dalam mendeteksi anomali yang dapat mengindikasikan gangguan sistem, pelanggaran keamanan, atau inefisiensi proses. Deteksi manual menjadi tidak efektif karena volume data log yang besar. Oleh karena itu, penelitian ini menerapkan pendekatan Process Mining menggunakan Inductive Miner, Alpha Miner, dan Conformance Analysis untuk mengidentifikasi anomali dalam log sistem cloud. Penelitian ini dimulai dengan pengumpulan data log dari sumber terbuka, diikuti oleh preprocessing untuk memastikan kompatibilitas dengan teknik process mining. Model proses kemudian dibangun menggunakan Inductive Miner dan Alpha Miner guna merepresentasikan alur aktivitas sistem. Selanjutnya, Conformance Analysis digunakan untuk mengevaluasi kesesuaian model dengan eksekusi aktual, mengidentifikasi pola penyimpangan yang dapat menjadi indikator anomali. Hasil penelitian menunjukkan bahwa kombinasi ketiga metode ini memberikan pemahaman mendalam tentang pola aktivitas sistem serta deteksi anomali berbasis penyimpangan jalur proses dan celah waktu yang tidak wajar. Inductive Miner terbukti efektif dalam memvisualisasikan pola proses secara komprehensif, sementara Alpha Miner mampu mengidentifikasi pola dasar meskipun sensitif terhadap noise. Conformance Analysis mengungkap deviasi antara model ideal dan eksekusi aktual, menunjukkan adanya bottleneck dan ketidaksesuaian sumber daya seperti disk I/O utilization dan network traffic. Temuan ini menegaskan bahwa process mining dapat menjadi alat yang efektif dalam analisis dan optimalisasi sistem cloud untuk meningkatkan efisiensi operasional.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
NUGRAHA, ZHILLAN ADRIAN
NIM01082210010
zhillanadrian88@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Contributor
Murwantara, I Made
NIDN0302057304
made.murwantara@uph.edu
Uncontrolled Keywords: Process Mining, Inductive Miner, Alpha Miner, Conformance Analysis, Identifikasi Anomali, Komputasi Awan.
Subjects: T Technology > T Technology (General)
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Informatics
Current > Faculty/School - UPH Karawaci > School of Information Science and Technology > Informatics
Depositing User: Magang Input
Date Deposited: 17 May 2025 02:15
Last Modified: 17 May 2025 02:15
URI: http://repository.uph.edu/id/eprint/68407

Actions (login required)

View Item
View Item