Model Prediksi Permintaan Batu Bara Menggunakan Metode Machine Learning (Study kasus PLTU Balikpapan)

Febriani, Kristina (2024) Model Prediksi Permintaan Batu Bara Menggunakan Metode Machine Learning (Study kasus PLTU Balikpapan). Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032221079-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 July 2026. Download (2MB) | Request a copy

Abstract

Peramalan kebutuhan permintaan batu bara penting untuk dilakukan agar dapat meminimalkan biaya operasional. Dengan adanya peramalan akan membantu perusahaan dalam menentukan jumlah dan waktu yang tepat untuk pemesanan batu bara dari pemasok. Penelitian tentang peramalan batu bara di Indonesia umumnya menggunakan pendekatan statistika dan belum melakukan analisis kinerja model peramalan yang lain. Penelitian ini bertujuan melakukan peramalan kebutuhan batu bara dengan menggunakan metode statistika dan machine learning yaitu ARIMA, Exponential Smoothing, Support Vector Regression (SVR), Recurrent Neural Network (RNN) dan Long Short-Term Memory (LSTM). Metode evaluasi yang digunakan untuk menganalisis kinerja peramalan yaitu Mean Absolute Error (MAE) dan Mean Absolute Percentage Error (MAPE). Data permintaan baru bara yang digunakan sebanyak 1097 data harian diambil dari Januari 2021 sampai dengan Desember 2022 yang berbentuk timeseries dan bersifat stasioner yang telah diuji menggunakan Augmented Dickey-Fuller (ADF). Hasil uji coba menunjukkan bahwa model ARIMA dengan nilai MAPE 5.11%, MAE 2.91 dan R-Square 0.925, Exponential Smoothing MAPE 1.07%, MAE 0.55 dan R-Square 0.997, SVR dengan nilai MAPE 5.48%, MAE 3.16 dan R-Square 0.88, RNN dengan nilai MAPE 5.19%, MAE 2.91 dan R-Square 0.896, LSTM dengan nilai MAPE 4.83%, MAE 2.84 dan R-Square 0.897. Dari hasil pengujian didapatkan bahwa exponential smoothing memiliki nilai error yang paling kecil diantara model lain. Dengan hasil peramalan yang memiliki tingkat error yang kecil maka dapat membantu manajemen dalam pengambilan keputusan untuk dapat meminimalkan biaya dalam pemesanan batu bara dan manajemen pergudangan
=====================================================================================================================================
Forecasting coal demand needs is important to minimize operational costs. Forecasting will help companies determine the right amount and time to order coal from suppliers. Research on coal forecasting in Indonesia generally uses a statistical approach and has not analyzed the performance of other forecasting models. This research aims to forecast coal demand using statistical and machine learning methods, namely ARIMA, Exponential Smoothing, Support Vector Regression (SVR), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). The evaluation methods used to analyze forecasting performance are Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). The new coal demand data used is 1097 daily data taken from January 2021 to December 2022 in the form of a timeseries and is stationary which has been tested using Augmented Dickey-Fuller (ADF). The test results show that the ARIMA model has a MAPE value of 5.11%, MAE 2.91 and R-Square 0.925, Exponential Smoothing MAPE 1.07%, MAE 0.55 and R-Square 0.997, SVR with a MAPE value of 5.48%, MAE 3.16 and R-Square 0.88, RNN with a MAPE value of 5.19%, MAE 2.91 and R-Square 0.896, LSTM with a MAPE value of 4.83%, MAE 2.84 and R-Square 0.897. From the test results it was found that exponential smoothing had the smallest error value among other models. With forecasting results that have a small error rate, it can help management in making decisions to minimize costs in coal ordering and warehousing management

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Peramalan, ARIMA, Exponential smoothing, SVR, RNN, LSTM, Forecasting; Forecasting, ARIMA, Exponential smoothing, SVR, RNN, LSTM, Forecasting
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.6 Management information systems
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Kristina Febriani
Date Deposited:	02 Feb 2024 02:45
Last Modified:	02 Feb 2024 02:45
URI:	http://repository.its.ac.id/id/eprint/105923

Actions (login required)

View Item