Alpian, Ridho (2026) Sistem Pemantauan dan Pengendalian Konsumsi Daya Listrik Berbasis Internet of Things dengan Algoritma K-Nearest Neighbor (KNN). Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (175kB) |
|
Text (Bab 1 Pendahuluan)
Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (184kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (403kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (2MB) | Request a copy |
Abstract
Increasing household electricity consumption without adequate monitoring can lead to energy waste and higher electricity costs. This study aims to design and implement an Internet of Things (IoT)-based electricity consumption monitoring and control system using the K-Nearest Neighbor (KNN) algorithm. The system is developed using an ESP32 microcontroller, a PZEM-004T v3.0 sensor, Firebase Realtime Database, a Flutter-based mobile application, and a Flask- and scikit-learn-based backend system to run the KNN model. The dataset was collected from three rooms over a period of seven days with a three-minute sampling interval. The data were labeled using a quantile-based classification method, resulting in three consumption categories: Normal, Warning, and Wasteful. The KNN model was trained using voltage and current features, with 70% of the data used for training and 30% for testing. The experimental results achieved classification accuracies of 97.30% in the kitchen, 98.43% in the living room, and 97.16% in the bedroom. The system successfully performs real-time electricity consumption monitoring, sends automatic notifications, and enables remote control of electrical devices. Furthermore, the analysis showed that energy consumption after system implementation was 17.08% lower than before implementation during the observation period. Therefore, the proposed system can assist users in monitoring electricity usage and support household energy-saving efforts.
Actions (login required)
 |
View Item |
