Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63326
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science
Deogiri Institute of Engineering and Management Studies, Chhatrapati Sambhajinagar
Computer Science
Deogiri Institute of Engineering and Management Studies, Chhatrapati Sambhajinagar
Wind energy has become one of the most important renewable energy sources for sustainable power generation. However, the irregular and changing nature of wind creates challenges in maintaining stable electricity production. Accurate short-term wind power prediction helps power systems improve grid stability, energy management, and operational efficiency. Machine learning techniques have recently gained significant attention because of their ability to learn patterns from large datasets and improve prediction accuracy. This review paper presents an overview of short-term wind power prediction methods based on machine learning. The paper discusses different preprocessing methods, feature engineering techniques, and forecasting models used in recent studies. A review of ten research papers is also presented to understand the current progress in this field. Furthermore, the paper identifies major research gaps such as data uncertainty, model complexity, and lack of generalized frameworks. Finally, the study concludes that hybrid and deep learning models provide better forecasting performance, but further research is required to improve accuracy, scalability, and real-time implementation.
KEYWORDS
Short-term wind power prediction is important for improving the stability and efficiency of renewable energy systems. Machine learning and deep learning techniques have significantly improved forecasting accuracy compared to traditional statistical methods. Different models such as SVM, Random Forest, CNN, and LSTM have shown strong performance in handling nonlinear wind data. Hybrid models that combine decomposition methods, optimization techniques, and deep learning algorithms provide the best forecasting results. However, challenges such as computational complexity, poor generalization, and real-time implementation still exist. Future research should focus on lightweight, adaptive, and scalable forecasting models for practical industrial use.
[1] Meng, X., et al. (2022). Short-term wind power forecasting using EEMD and RGRU networks. Energy Reports. [2] Ouyang, T., et al. (2017). Wind power forecasting using SVM and feature engineering methods. Renewable Energy. [3] Yan, J., & Ouyang, T. (2019). Wind power prediction using boosted trees and logistic regression. Energy Conversion and Management. [4] Zhou, H., et al. (2019). LSTM-based wind power forecasting with clustering techniques. Applied Energy. [5] Bokde, N., et al. (2019). Hybrid EMD-CNN-LSTM model for wind power prediction. Renewable and Sustainable Energy Reviews. [6] Yang, Y., et al. (2024). CNN-LSTM hybrid framework for short-term wind forecasting. Energy Reports. [7] Liu, W., et al. (2024). Wavelet decomposition and LSTM-based wind power prediction. Sustainable Energy Technologies. [8] Hanifi, S., et al. (2024). Deep learning optimization techniques for wind forecasting. Renewable Energy. [9] Alkesaiberi, A., et al. (2022). Ensemble learning and Bayesian optimization for wind forecasting. Energy Systems. [10] Li, X., et al. (2020). Wavelet-SVM approach for short-term wind power forecasting. Electric Power Systems Research.
Publication Date
5/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...