Deteksi Abnormality Arus Pada Smart Charging Station Menggunakan Metode K-Nearest Neighbor

Isvaldy, Ariffitra (2023) Deteksi Abnormality Arus Pada Smart Charging Station Menggunakan Metode K-Nearest Neighbor. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 10311910000071_Undergraduate-Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (3MB) | Request a copy

Abstract

Pada Smart Charging Station belum terdapat sistem monitoring arus secara real-time dan memberikan early warning system apabila terdapat over current. Hal ini dapat mengakibatkan terjadinya kerusakan pada hardware apabila tidak segera di tangani dan dapat mengakibatkan cost maintenance yang sangat tinggi. Pada penelitian ini dibuatlah sebuah early warning system berbasis website yang dapat memonitoring arus yang ditampilkan dalam bentuk chart dengan menggunakan metode K-Nearest Neighbor untuk mendeteksi abnormality arus pada sistem Smart Charging Station. K-Nearest Neighbor merupakan algoritma klasifikasi yang bekerja dengan mengambil sejumlah K data terdekat ( tetangganya ) sebagai acuan untuk menentukan kelas dari data baru. Algoritma ini mengklasifikasikan data berdasarkan similarity atau kemiripan atau kedekatannya terhadap data lainnya. K-Nearest Neighbor dapat digunakan untuk mengklasifikasi hasil data arus dan menemukan pola abnormality yang mungkin terjadi. Dengan demikian K-Nearest Neighbor dapat digunakan untuk deteksi dini ketidaknormalan pada arus listrik di Smart Charging Station dengan akurasi sebesar 90%. Penelitian ini dapat memonitoring arus secara real-time dan memberikan peringatan dini untuk mengurangi cost maintenance dan kerusakan pada hardware.
====================================================================================================================================
In the Smart Charging Station there is no real-time current monitoring system and provides an early warning system if there is over current. This can result in damage to the hardware if not handled immediately and can result in very high maintenance costs. In this study, a website-based early warning system was created that can monitor the current displayed in the form of a chart using the K-Nearest Neighbor method to detect current abnormalities in the Smart Charging Station system. K-Nearest Neighbor is a classification algorithm that works by taking a number of K closest data ( neighbors ) as a reference to determine the class of new data. This algorithm classifies data based on similarity or closeness to other data. K-Nearest Neighbor can be used to classify the results of current data and find patterns of abnormality that may occur. Thus K-Nearest Neighbor can be used for early detection of abnormalities in electric current at Smart Charging Station with an accuracy of 100% with a value of k = 5 calculated by Elbow Method with WCSS calculation. This research can monitor the current in real-time and provide early warning to reduce maintenance costs and damage to hardware.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Kata Kunci : K-Nearest Neighbor, Early Warning System, Smart Charging Station
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1007 Electric power systems control T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1087 Photovoltaic power generation T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2861 Electric relays T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK2921 Lithium cells. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3070 Automatic control T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7878 Electronic instruments
Divisions:	Faculty of Vocational > 36304-Automation Electronic Engineering
Depositing User:	Isvaldy Ariffitra
Date Deposited:	15 Aug 2023 05:59
Last Modified:	15 Aug 2023 05:59
URI:	http://repository.its.ac.id/id/eprint/104183

Actions (login required)

View Item