A comparative analysis of LSTM, SVM, and GSTANN models for enhancing solar power prediction

M. Helmy, Muhammad Fareezy Fahmy and Yusoff, Siti Hajar and Mansor, Hasmah and Gunawan, Teddy Surya and Chowdhury, Israth Jahan and Mohd Sapihie, Siti Nadiah (2024) A comparative analysis of LSTM, SVM, and GSTANN models for enhancing solar power prediction. In: IEEE 10th International Conference on Smart Instrumentation, Measurement and Applications, 30-31 July 2024, Bandung, Indonesia.

PDF - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Solar power prediction is crucial for integrating renewable energy into the grid, but current methods often struggle with accuracy due to the limitations of machine learning algorithms. This study aims to enhance prediction accuracy by comparing the performance of Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) models using datasets from Hebei, China. The main objective is identifying the most effective algorithm for precise solar power forecasting. The methodology involves training both models on historical solar power data and evaluating their performance against the Graph Spatial-Temporal Attention Neural Network (GSTANN) benchmark. The SVM model was selected for its superior metrics, achieving an MAE (Mean Absolute Error) of 0.5587, RMSE of 0.9741, and a training time of 0.0157 seconds. Results show that SVM outperforms GSTANN in 45 and 60- minute intervals, with MAE, MAPE, and RMSE improvements of up to 68.62%, 42.65%, and 69.44%, respectively. These findings suggest that SVM offers a more reliable solution for solar power prediction, providing valuable insights for further model enhancements.

Item Type:	Proceeding Paper (Slide Presentation)
Uncontrolled Keywords:	Solar Power Predictions, Machine Learning, Support Vector Machine, Long Short-Term Memory, Graph Spatial-Temporal Attention Neural Network
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK1001 Production of electric energy. Powerplants T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK3001 Distribution or transmission of electric power. The electric power circuit
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering > Department of Electrical and Computer Engineering Kulliyyah of Engineering
Depositing User:	dr siti hajar yusoff
Date Deposited:	22 Oct 2024 12:28
Last Modified:	22 Oct 2024 12:28
URI:	http://irep.iium.edu.my/id/eprint/115179

Actions (login required)

View Item