Sucipto, Halbianto Adi (2025) Penerapan Artificial Neural Network Clustering Untuk Pengaturan Under Frequency Load Shedding Guna Mencegah Kerugian Produksi Signifikan Di Perusahaan Hulu Minyak Dan Gas. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6022231019-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6022231019-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (9MB) | Request a copy |
Abstract
Perusahaan hulu minyak dan gas (upstream oil and gas companies) adalah perusahaan yang terlibat dalam proses awal rantai industri minyak dan gas. Penelitian ini berfokus kepada perusahaan minyak dan gas yang memiliki sistem listrik terisolasi sehingga desain skema Under frequency load shedding (UFLS) harus mengutamakan produksi sebagai elemen dalam pelepasan beban. Pendekatan konvensional kurang efektif dalam mencegah tingginya kerugian produksi. Penelitian ini mengusulkan pendekatan pengaturan UFLS berbasis Artificial Neural Network (ANN) Clustering untuk mengelompokkan beban berdasarkan konsumsi listrik, tingkat produksi, dan prioritas fasilitas. Metode clustering akan membagi beban menjadi kategori kritikal, esensial, dan non-esensial, sehingga pelepasan beban dapat dilakukan secara lebih selektif dan tepat sasaran ketika terjadi penurunan frekuensi sistem. Hasil penelitian menunjukkan bahwa penerapan metode ini mampu secara signifikan mengurangi potensi kerugian produksi, dengan estimasi penghematan sebesar 18.661,26 barel minyak (setara IDR 1.009.143.475 pada 2022) dan 25.956 barel minyak (setara IDR 2.604.520.000 pada 2024). Penerapan UFLS berbasis ANN Clustering terbukti efektif dalam menjaga keberlangsungan produksi serta meningkatkan efisiensi teknis dan ekonomi pada operasi hulu minyak dan gas.
=====================================================================================================================================
Upstream oil and gas companies are entities involved in the initial stages of the oil and gas industry value chain. This study focuses on oil and gas companies with isolated power systems, where the design of the Under Frequency Load Shedding (UFLS) scheme must prioritize production as a key element in load shedding decisions. Conventional approaches are less effective in preventing high production losses. This research proposes a UFLS regulation approach based on Artificial Neural Network (ANN) Clustering to classify loads according to electricity consumption, production levels, and facility priority. The clustering method categorizes loads into critical, essential, and non-essential groups, allowing load shedding to be performed more selectively and accurately during system frequency drops. The results show that this method can significantly reduce potential production losses, with estimated savings of 18,661.26 barrels of oil (equivalent to IDR 1,009,143,475 in 2022) and 25,956 barrels of oil (equivalent to IDR 2,604,520,000 in 2024). The implementation of ANN Clustering-based UFLS has proven effective in ensuring production continuity and enhancing both technical and economic efficiency in upstream oil and gas operations.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Perusahaan minyak & gas, Under Frequency Load Shedding (UFLS), Artificial Neural Network (ANN) Clustering, Mencegah |
| Subjects: | T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.84 Heuristic algorithms. T Technology > T Technology (General) > T58.8 Productivity. Efficiency |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | Halbianto Adi Sucipto |
| Date Deposited: | 23 Jul 2025 01:23 |
| Last Modified: | 23 Jul 2025 01:23 |
| URI: | http://repository.its.ac.id/id/eprint/120607 |
Actions (login required)
 |
View Item |