Penerapan Time Series Regression, Double Seasonal ARIMA, dan Long Short-Term Memory untuk Peramalan Beban Konsumsi Listrik Jangka Pendek Region Jawa Timur

Afghan, Hafez (2023) Penerapan Time Series Regression, Double Seasonal ARIMA, dan Long Short-Term Memory untuk Peramalan Beban Konsumsi Listrik Jangka Pendek Region Jawa Timur. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 062119400000180-Undergraduated_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (11MB) | Request a copy

Abstract

PT PLN perlu membangkitkan listrik untuk didistribusikan ke pelanggan. Masalah utamanya adalah beban listrik harus diperkirakan dengan tepat, karena listrik bersifat tidak dapat disimpan. Jika listrik yang dibangkitkan lebih dari konsumsi pelanggan maka akan terbuang dan daya pembangkit listrik perlu diturunkan, sedangkan listrik yang dibangkitkan kurang dari konsumsi pelanggan maka dapat terjadi pemadaman listrik dan menunggu pengoperasian pembangkit cadangan. Penelitian ini menggunakan metode peramalan time series regression, double seasonal ARIMA dan long short-term memory. Hasil analisis menunjukkan sMAPE out sample model terbaik dari metode time series regression, double seasonal ARIMA dan long short-term memory adalah berturut-turut 0,6436%, 0,5504%, dan 0,9713%. Maka model double seasonal ARIMA ([2,10,11,12,15,16,17,18,19,20,21,22,23],1,[1,2,3,7,8,30,34,35,39,40,41,42,43,44,45,46,47,48]) (0,1,1)48 (0,1,1)336 merupakan model terbaik dalam meramalkan beban konsumsi listrik region Jawa Timur karena memiliki sMAPE out sample terendah. Berdasarkan model terbaik tersebut, ditentukan kemampuan pembangkit listrik, agar dapat menyediakan kebutuhan listrik bagi masyarakat. Diperoleh bahwa kemampuan pembangkit dapat menyediakan kebutuhan listrik sebesar 98,981% dari total keseluruhan waktu observasi. Sedangkan 1,019% sisanya tidak tertutupi karena adanya outlier sehingga kemampuan pembangkit tidak dapat memprediksi adanya lonjakan kebutuhan listrik di waktu tertentu. Walaupun demikian, kemampuan pembangkit yang ditentukan telah sangat baik dalam menyediakan listrik bagi masyarakat.
================================================================================================================================
PT PLN needs to generate and distribute electricity toward customer. The main matter, electricity must accurately estimate, because electricity is non-storable. If electricity is generated more than customer’s consumption then it will be wasted and the power of generator should be lowered. However, if electricity is generated less than customer’s consumption then it may cause power outage and waiting for backup-plant operation. This research using time series regression, double seasonal ARIMA and long-short term memory to forecast electric demand. The analyze obtains sMAPE out sample’s best model of each method respectively are 0.6436%, 0.5504% and 0.9713%. Double seasonal ARIMA ([2,10,11,12,15,16,17,18,19,20,21,22,23],1,[1,2,3,7,8,30,34,35,39,40,41,42,43,44,45,46,47,48]) (0,1,1)48 (0,1,1)336 is the best forecasting model as lowest sMAPE out sample value. Based on that model, power generation is calculated for that can provide electricity needs. It obtains power generation that provide 98.981% electricity needs from total observation. While the rest 1.019% not covered because outliers, in this case power generation cannot predict the peak of electricity demand by times. Nevertheless, obtained power generation can provide electricity demand properly.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Double Seasonal ARIMA, Electricity Load Demand, LSTM, Power Generation, Time Series Regression, Beban Listrik, Double Seasonal ARIMA, Kemampuan Pembangkit, LSTM, Time Series Regression
Subjects:	H Social Sciences > HA Statistics > HA30.3 Time-series analysis Q Science > Q Science (General) Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Hafez Afghan
Date Deposited:	11 Aug 2023 07:47
Last Modified:	11 Aug 2023 07:47
URI:	http://repository.its.ac.id/id/eprint/104575

Actions (login required)

View Item