Young, Jian Jeraus (2024) Evaluasi pendekatan hybrid prophet-lstm dalam peramalan permintaan listrik: studi kasus britania raya. Bachelor thesis, Universitas Pelita Harapan.
![Title [thumbnail of Title]](http://repository.uph.edu/style/images/fileicons/text.png)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (174kB)
![Abstract [thumbnail of Abstract]](http://repository.uph.edu/style/images/fileicons/text.png)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (475kB)
![ToC [thumbnail of ToC]](http://repository.uph.edu/style/images/fileicons/text.png)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (927kB)
![Chapter 1 [thumbnail of Chapter 1]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (873kB)
![Chapter 2 [thumbnail of Chapter 2]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter 3 [thumbnail of Chapter 3]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
![Chapter 4 [thumbnail of Chapter 4]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (5MB)
![Chapter 5 [thumbnail of Chapter 5]](http://repository.uph.edu/style/images/fileicons/text.png)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (506kB)
![Bibliography [thumbnail of Bibliography]](http://repository.uph.edu/style/images/fileicons/text.png)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (594kB)
![Appendices [thumbnail of Appendices]](http://repository.uph.edu/style/images/fileicons/text.png)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.
Download (1MB)
Abstract
Listrik memainkan peran penting dalam menopang ekonomi modern, mulai dari
industri hingga kebutuhan rumah tangga. Peningkatan signifikan dalam permintaan
listrik menuntut peramalan beban yang akurat untuk mendukung pengelolaan
pasokan dan permintaan secara efektif. Penelitian ini mengusulkan pendekatan
hibrida dengan menggabungkan model Long Short-Term Memory (LSTM) dan
Prophet untuk meramalkan konsumsi listrik di Britania Raya. LSTM efektif
menangkap pola kompleks pada data deret waktu, sementara Prophet menawarkan
penanganan tren musiman dan pencilan yang fleksibel. Dengan menggunakan data
sekunder dari National Grid ESO (2009–2024), model hibrida ini dievaluasi
berdasarkan metrik Root Mean Square Error (RMSE) dan Mean Absolute
Percentage Error (MAPE). Pendekatan hibrida menghasilkan RMSE sebesar
3738.62 MW dan MAPE 12.75%, yang lebih baik dibandingkan Prophet (RMSE
4324.75 MW, MAPE 20.65%) dan ARIMA (RMSE 4556.37 MW, MAPE 16.63%).
Temuan ini menunjukkan bahwa pendekatan hibrida Prophet-LSTM dapat
meningkatkan akurasi peramalan beban listrik secara signifikan. Penelitian ini
memberikan kontribusi pada pengelolaan energi yang lebih efisien dan
menawarkan referensi untuk pengembangan metode peramalan beban listrik yang
lebih andal di masa depan./ Electricity plays a crucial role in sustaining the modern economy, from industrial
operations to household needs. The significant increase in electricity demand
necessitates accurate load forecasting to support supply and demand management
by energy providers. This study proposes a hybrid approach by combining Long
Short-Term Memory (LSTM) and Prophet models to forecast electricity
consumption in the United Kingdom. LSTM excels at capturing complex patterns
in time series data, while Prophet offers flexible handling of seasonal trends and
outliers. By leveraging the strengths of both methods, this research evaluates the
Prophet-LSTM hybrid approach using metrics such as Root Mean Square Error
(RMSE) and Mean Absolute Percentage Error (MAPE). Secondary data from
National Grid ESO (2009–2024) is utilized to build and test the model. The hybrid
model produces RMSE and MAPE at 3738.62 MW and 12.75% respectively, which
performed better than Prophet (RMSE 4324.75 MW, MAPE 20.65%) and ARIMA
(RMSE 4556.37 MW, MAPE 16.63%). The findings are expected to make a
significant contribution to energy management and serve as a critical reference for
the development of more accurate load forecasting methods in the future.
Item Type: | Thesis (Bachelor) |
---|---|
Creators: | Creators NIM Email ORCID Young, Jian Jeraus NIM03081210009 jianjerausyoung37@gmail.com UNSPECIFIED |
Contributors: | Contribution Contributors NIDN/NIDK Email Thesis advisor Mitra, Aditya Rama NIDN0305096901 aditya.mitra@uph.edu |
Uncontrolled Keywords: | Prediksi listrik; pembelajaran hibrida; listrik; prophet; longshort term memory |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems Current > Faculty/School - UPH Medan > School of Information Science and Technology > Information Systems |
Depositing User: | Jian Jeraus Young |
Date Deposited: | 25 Apr 2025 01:31 |
Last Modified: | 25 Apr 2025 01:31 |
URI: | http://repository.uph.edu/id/eprint/68176 |