Skripsi

PREDIKSI PENGGUNAAN LISTRIK PADA SEBUAH RUMAH MENGGUNAKAN LONG SHORT-TERM MEMORY

---

Penilaian

---

Prediction, also known as forecasting, is the process of estimating events that will occur in the future. In this research, software is developed that can predict electricity usage in a house using the Long Short-term Memory method, which is a Recurrent Neural System designed to overcome vanishing gradient problem. In this research, the model training is done with 2 configurations: split train-validation data into 80%-20%, split cross validation, for 2 model architectures: 2 layer LSTM and 3 layer LSTM each trained with 100, 150, and 200 epochs to see which configuration produces a model with the lowest prediction error. The results showed that the model trained using the split cross validation configuration epoch 150 with 3 layer LSTM had the lowest prediction error among the other configurations with an RMSE of 3.616.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307003784	T127129	T1271292023	Central Library (REFERENS)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1271292023

Publisher

Indralaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

-

Language

Indonesia

ISBN/ISSN

-

Classification

xvii, 60 hlm.; ilus.; 29 cm

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Perangkat Lunak
Jurusan Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

ANUG

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment