MACHINE LEARNING IMPLEMENTATION FOR LOST DATA PREDICTION IN RST POWER MONITORING SYSTEM WITH MATLAB APPLICATION

Nainggolan, Adhyaksa (2022) MACHINE LEARNING IMPLEMENTATION FOR LOST DATA PREDICTION IN RST POWER MONITORING SYSTEM WITH MATLAB APPLICATION. Tugas Akhir thesis, University of Technology.

[img] Text
5190721002_Adhyaksa Nainggolan.pdf
Download (128kB)

Abstract

ABSTRACT Neural Networks (artificial neural networks) are systems of parallel processors connected to each other in the form of directed graphs. According to the chart each neuron of the network is represented as a node. This connection provides a hierarchical structure that tries to imitate the physiology of the brain, seeking new models of processing to solve certain problems in the real world. Incorrect invoices due to missing data are very detrimental to society, the accuracy and completeness of the data will certainly be very important and very needed as a tool help for the industrial community in forecasting electrical energy consumption when measuring instruments fail so as to minimize errors in estimating electrical energy consumption. Then the Backpropagation artificial neural network method is used to train the data, also find a network architecture that has a mape that is below 10%. The software used is Matlab 2020 B, through starting the data is grouped, namely input data and output data and then determines the composition of training, validation, and testing, in this training using the composition of 80%, 10%, 10%. The next step is to determine the network architecture for data training, there are 5 mo The network architecture del used is 2-5-1 ,2-10-1,2-18-1,2-20-1,2-25-1. The result of this study is the training of artificial neural networks for R, S, and T phase data has been running well with the best architecture on the 2-18-1 model with a mape value of 7.062144%. Keywords: Backpropagation, Matlab, Artificial Neural Networks, Perama

Item Type: Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Sains Dan Teknologi > S1 Teknik Elektro
Depositing User: Kaprodi Teknik Elektro
Date Deposited: 07 Apr 2022 04:28
Last Modified: 07 Apr 2022 04:28
URI: http://eprints.uty.ac.id/id/eprint/9480

Actions (login required)

View Item View Item
UTY Open Access is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.