Mubarok, Rafsanjani Ibnu (2024) Prediksi Konsumsi Daya Listrik Air Conditioner Terhadap Perubahan Temperatur dan Kelembapan Udara Luar Ruangan Menggunakan Neural Network. Diploma thesis, Institut Teknologi Sepuluh Nopember.
Text
10311910000080-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy |
Abstract
Perkembangan dan teknologi zaman sekarang semakin maju, hal ini menyebabkan meningkatnya penguunaan alat elektronik. Pemahaman tentang pola konsumsi daya listrik menjadi sangat penting untuk mengelola dan mengurangi pemborosan listrik yang berlebih. Menggunakan mikrokntroler berfungsi untuk mendapatkan data pada temperatur, kelembapan dan daya listrik. Studi ini menggunakan dataset konsumsi daya listrik dan dibantu menggunakan kecerdasan buatan (AI) dan jaringan syaraf tiruan (neural network). Model prediksi ini diharapkan dapat membantu pengguna atau mitra dalam mengelola konsumsi daya listrik secara efisien dan mendukung upaya penghematan energi secara keseluruhan. Hasil penelitian ini menunjukkan bahwa penggunaan air conditioner secara signifikan mempengaruhi lonjakan daya listrik. Hasil penelitian menunjukkan pengaruh signifikan penggunaan air conditioner terhadap lonjakan daya listrik. Pada pengujian sensor DHT22 dan PZEM-004T, didapatkan nilai error yaitu 0,78% untuk temperatur 0,67% untuk kelembapan, selanjutnya 0,563% untuk arus dan 0,11% untuk tegangan. Model neural network yang dikembangkan berhasil memprediksi daya listrik dengan hasil uji yang menunjukkan nilai MSE 0,0172 dan MAPE 1,4492%. Evaluasi lebih lanjut menggunakan metode cross
validation 5-fold pada model ini menghasilkan rata-rata MSE sebesar 0,0315, RMSE 0,1738, MAPE 1,8663%, dan akurasi 96,3934%.
=================================================================================================================================
The development and technology of today is increasingly advanced, this has led to increased use of electronic devices. Understanding the pattern of electrical power
consumption is very important to manage and reduce excessive waste of electricity. Using a microcontroller to obtain data on temperature, humidity and electrical power. This study uses a dataset of electric power consumption and is assisted by artificial intelligence (AI) and neural networks. This prediction model is expected to help users or partners in managing electric power consumption efficiently and support overall energy saving efforts. The results of this study show that the use of air conditioners significantly affects the surge in electricity. The results showed a significant effect of the use of air conditioners on electric power surges. In testing the DHT22 and PZEM-004T sensors, the error value is 0.78% for temperature 0.67% for humidity, then 0.563% for current and 0.11% for voltage. The neural network model developed successfully predicts electrical power with test results showing an MSE value of 0.0172 and MAPE of 1.4492%. Further evaluation using the 5-fold cross validation method on this model resulted in an average MSE of 0.0315, RMSE of 0.1738, MAPE of 1.8663%, and accuracy of 96.3934%.
Item Type: | Thesis (Diploma) |
---|---|
Uncontrolled Keywords: | Prediksi, Temperatur, Daya listrik, Kecerdasan buatan, Air Conditioner, Prediction, Temperature, Electric power, Artificial intelligence, Air Conditioner |
Subjects: | T Technology > T Technology (General) > T174 Technological forecasting T Technology > TA Engineering (General). Civil engineering (General) > TA1573 Detectors. Sensors T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK351 Electric measurements. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK4035.R4 Refrigeration and refrigerating machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7888.3 Digital computers |
Divisions: | Faculty of Vocational > 36304-Automation Electronic Engineering |
Depositing User: | Rafsanjani Ibnu Mubarok |
Date Deposited: | 27 Sep 2024 02:00 |
Last Modified: | 27 Sep 2024 02:00 |
URI: | http://repository.its.ac.id/id/eprint/115702 |
Actions (login required)
View Item |