CD Skripsi

Prediksi Kebutuhan Listrik Pelanggan Di Kota Duri Menggunakan Backpropagation Pada Metode Artificial Neural Network

---

Electricity demand continues to increase every year, necessitating a reliable prediction system to support effective energy planning and management. This study aims to predict customer electricity demand, particularly in the residential sector in Duri City, using the Artificial Neural Network (ANN) method with the Backpropagation algorithm, and to determine the accuracy of this method in predicting customer electricity demand. The data used consists of historical electricity consumption data from residential customers in Duri City and the average temperature of Riau Province over the past 60 months. In this study, the dataset was divided into 90% for training data and 10% for testing data. The ANN model was designed using several parameters such as the number of hidden layer neurons (32), learning rate (0.0001), and number of epochs (50) to obtain the best prediction results. The model's performance was evaluated using the Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) metrics. The results showed that the RMSE value (0.0524) fell into the good accuracy category, and the MAPE percentage (5.60%) fell into the very good accuracy category. It can be concluded that the model successfully predicted electricity demand for customers in Duri City.

Keywords : Artificial Neural Network, Backpropagation, Duri City, Electricity
Demand Prediction, Residential Sector

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2103110837

Penerbit

Pekanbaru : Universitas Riau FMIPA Sistem Informasi., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2103110837

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SISTEM INFORMASI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Mutia

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar