Peramalan Beban Listrik Di Jawa Timur Menggunakan Metode Arima Dan Adaptive Neuro Fuzzy Inference System (ANFIS)

La Zulfa, Indana (2015) Peramalan Beban Listrik Di Jawa Timur Menggunakan Metode Arima Dan Adaptive Neuro Fuzzy Inference System (ANFIS). Undergraduate thesis, Institut Technology Sepuluh Nopember.

[img]
Preview
Text
1311100076-Undergraduate Thesis.pdf - Published Version

Download (4MB) | Preview

Abstract

Listrik merupakan salah satu sumber energi utama yang digunakan hampir pada seluruh aspek kehidupan. Faktanya, kebutuhan energi listrik semakin berkembang seiring dengan adanya kemajuan pembangunan di bidang teknologi, industri, dan informasi. Perkembangan dalam berbagai bidang tersebut dapat menimbulkan permasalahan kualitas dan kuantitas daya listrik yang dihantarkan. Oleh karena itu, ramalan konsumsi listrik untuk beberapa waktu ke depan berdasarkan data konsumsi listrik waktu sebelumnya diperlukan sebagai bahan perencanaan pendistribusian listrik yang lebih efisien. Tujuan dari penelitian yaitu meramalkan konsumsi listrik pukul 05:00, 13:00, dan 18:30 di Jawa Timur dengan metode ARIMA dan ANFIS. Kriteria pemilihan model terbaik berdasarkan pada nilai RMSE, SMAPE, dan MAPE pada data out sample. Hasil dari analisis menunjukkan bahwa metode ARIMA memberikan tingkat keakuratan yang lebih baik untuk meramalkan konsumsi listrik di Jawa Timur pukul 05:00, 13:00, dan 18:30 dibandingkan dengan metode ANFIS. =================================================================================================== Electricity is one of the main sources of energy that is used almost in all aspects of life. In fact, the electrical energy was a developing along with the lack of progress development in field of technology, industry, and information. The development of the various fields could lead to quality and quantity problems that transmit power. Thus the electricity consumption for some time to future based on data electricity consumption previous times needed as material for planning distribute electrical energy that is more efficient. The purpose of this research is to forecast electricity consumption at 05:00, 1:00 pm, and 6:30 pm in East Java by using ARIMA and ANFIS. Selection Criteria best models based on the value RMSE, SMAPE, and MAPE in data out samples. The analysis of the result shows that method ARIMA gives high accuracy that it is better to predict electricity consumption in East Java at 05:00, 1:00 pm, and 6:30 pm than ANFIS method.

Item Type: Thesis (Undergraduate)
Additional Information: RSSt 519.535 Zul p
Uncontrolled Keywords: ANFIS, ARIMA, Listrik, MAPE, Ramalan, RMSE, SMAPE.
Subjects: H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models.
Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis.
Divisions: Faculty of Mathematics and Science > Statistics > (S1) Undergraduate Theses
Depositing User: Mr. Tondo Indra Nyata
Date Deposited: 30 May 2018 05:27
Last Modified: 30 May 2018 05:27
URI: http://repository.its.ac.id/id/eprint/51958

Actions (login required)

View Item View Item