Work

Comparative Analysis of ARIMA and LSTM for Forecasting Maximum Wind Speed in Kupang City, East Nusa Tenggara

Year: 2024

Type: article

Abstract: This study compares the Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) models for predicting maximum wind speed based on accuracy measured by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Based on the results of the research, the LSTM model is better than the ARIMA model in predicting maximum wind speed in Kupang City, East Nusa Tenggara Province. The best LSTM model has hyperparameters of 200 epochs; batch size of 32; learning rate of 0,001; and 8 neurons. Based on the evaluation results of predicted data against actual data, the MAPE value of the LSTM model is 19,40%. The benefit of this research is that it can contribute to the literature on the development of wind utilization as a basis for building power plants on small islands as a renewable resource, particularly in Kupang City, East Nusa Tenggara.

Source: Jambura Journal of Mathematics

DOI: 10.37905/jjom.v6i2.25834

Authors: Indah Magfirrah, Meisyatul Ilma, Khairil Anwar Notodiputro, Yenni Angraini, Laily Nissa Atul Mualifah

Institution: IPB University

Language: English

Topic: Energy Load and Power Forecasting

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Climate action

Open Access status: gold

Estimated APC paid: $42