Analisis Kestabilan Tegangan Pada Sistem Kelistrikan Jawa-Bali 500 Kv Menggunakan Radial Base Function Neural Network (RBFNN)

Hasbullah, Maulana Riza (2018) Analisis Kestabilan Tegangan Pada Sistem Kelistrikan Jawa-Bali 500 Kv Menggunakan Radial Base Function Neural Network (RBFNN). Undergraduate thesis, Institute Teknologi Sepuluh Nopember.

[img] Text
07111645000042-Undergraduate_Theses.pdf - Published Version
Restricted to Repository staff only

Download (2MB) | Request a copy

Abstract

Kemajuan teknologi menyebabkan kebutuhan akan tenaga listrik semakin meningkat. Sehingga demi memberikan kualitas listrik yang baik diperlukan beberapa cara diantaranya adalah analisis kestabilan. Tugas akhir ini akan membahas mengenai kestabilan tegangan pada sistem kelistrikan Jawa-Bali 500 kV untuk menghindari permasalahan voltage collapse dan yang lebih buruknya adalah black-out sistem. Analisis dibantu dengan program ETAP yang digunakan untuk study load-flow dengan variabel yang dirubah adalah nilai pembebanan sehingga dapat diketahui daya maksimum pada salah satu bus agar tidak melebihi kondisi kestabilan tegangan. Nilai-nilai yang didapat dengan merubah kondisi pembebanan akan dicatat dan selanjutnya dijadikan masukan untuk proses training and learning pada arsitektur Radial Base Function Neural Network (RBFNN). Didapatkan hasil pengujian menggunakan RBFNN dengan 40 data training dan 5 data testing yaitu diperoleh error terbesar adalah 1,02% dan MSE bernilai 4,84748x10-5 < 5x10-5. Dengan error sebesar itu, maka tingkat kebenaran prediksi pada RBFNN mencapai 98,98%. ========================================================= Technological advances led to the requirements for electrical power is increasing. So in order to give a good quality electricity needed some way of which is the analysis of stability. This final project will discuss about the stability of the voltage on the Java-Bali electricity system of 500 kV to avoid voltage collapse problems and worse is the black-out system. The ETAP program assisted with the analysis that is used to study load-flow with variable value is changed so that the imposition of the maximum power can be found at one of the bus so as not to exceed the conditions of the stability of voltage. The values obtained by changing the conditions of imposition of will be recorded and later made an input to the process of training and learning on the architecture of the Radial Base Function Neural Network (RBFNN). Obtain results of testing using RBFNN with 40 data training and 5 testing data retrieved the greates error was 1,02% and MSE is worth 4,84748x10-5 < 5x10-5 . with error of it, then the level of truth of prediction on RBFNN reached 98,98%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Kestabilan tegangan, NN, Radial Base Function Neural Network (RBFNN), ETAP.
Subjects: T Technology > T Technology (General) > T57.5 Data Processing
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1010 Electric power system stability. Electric filters, Passive.
Divisions: Faculty of Electrical Technology > Electrical Engineering > (S1) Undergraduate Theses
Depositing User: Hasbullah Maulana Riza
Date Deposited: 10 Oct 2018 04:58
Last Modified: 10 Oct 2018 04:58
URI: http://repository.its.ac.id/id/eprint/52662

Actions (login required)

View Item View Item