Claim Missing Document
Check
Articles

Found 1 Documents
Search

Artificial Neural Network Based Evaluation of Wind Energy Potential for Small-Scale Renewable Power Generation in Wufeng, Taiwan Rahman, Haidar; Akbar, Ahzami Fadilah
Jurnal Internasional Teknik, Teknologi dan Ilmu Pengetahuan Alam Vol 7 No 2 (2025): International Journal of Engineering, Technology and Natural Sciences
Publisher : Universitas Teknologi Yogyakarta, Yogyakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46923/ijets.v7i2.581

Abstract

This study investigates the wind energy potential in the Wufeng area of Taichung, Taiwan, with the aim of supporting the development of small-scale renewable wind power generators. Specifically, it seeks to evaluate wind patterns and meteorological parameters over a three-year period and to identify the most accurate predictive model for wind speed and energy output. A quantitative research methodology was employed, analyzing weather data using multiple regression algorithms, including Linear Regression, Lasso Regression, Ridge Regression, Support Vector Regression (SVR), Dynamic Thermal Rating (DTR), and Artificial Neural Network (ANN). The performance of these models was compared through data training and testing, with the ANN demonstrating the highest predictive accuracy. Using this model, the maximum expected wind speed was determined to be 5.56 m/s, corresponding to a potential energy output of 992.57 watts over a one-week period, indicating that the region is suitable for small-scale wind power development. However, the study is limited by its reliance on short-term data, which may not capture seasonal variations, economic feasibility, or operational constraints of wind power systems. Therefore, future research should incorporate long-term wind monitoring, feasibility assessments, and pilot projects to evaluate the practical performance and reliability of small-scale wind turbines in the Wufeng region.