Wind Energy Prediction Using Hybrid LSTM and CNN Approaches
Authors:
- Rakhi BiswasRBRakhi Biswas
- Sunit JanaSJSunit Jana
- Koushik PalKPKoushik Pal
- Debasmita BasakDBDebasmita Basak
- Disha DasDDDisha Das
- Anirban GhosalAGAnirban Ghosal
- 24 June 2025
- journal article
- Published by Naksh Solutions in International Journal of Advanced Research in Science, Communication and Technology
- p. 225-228
Abstract
Maintaining grid stability and optimizing energy dispatch depend heavily on accurate wind energy forecasting. The complex temporal and spatial fluctuations present in wind patterns are frequently difficult to model using conventional statistical and stand-alone machine learning models. This work presents a new hybrid deep learning framework that combines Long Short-Term Memory (LSTM) networks for temporal dependency capture and Convolutional Neural Networks (CNN) for spatial feature extraction in a synergistic manner. By utilizing real-world wind power datasets, the suggested model outperforms traditional methods, such as CNN, standalone LSTM, and classical regressors, resulting in a significant decrease in both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The outcomes highlight the framework's efficacy and scalability, providing a solid way to support the integration of renewable energy sources into contemporary power systemsKeywords
This publication has 9 references indexed in Scilit:
- Advances in solar forecasting: Computer vision with deep learningAdvances in Applied Energy, 2023
- SOLAR ENERGY FORECASTING WITH DEEP LEARNING TECHNIQUEEngineering Science & Technology Journal, 2023
- Solar Energy Production Forecasting Based on a Hybrid CNN-LSTM-Transformer ModelMathematics, 2023
- Renewable Energy in Indonesia: Current Status, Potential, and Future DevelopmentSustainability, 2023
- Short-Term Photovoltaic Power Forecasting Based on Historical Information and Deep Learning MethodsSensors, 2022
- Solar Power Forecasting Using CNN-LSTM Hybrid ModelEnergies, 2022
- Wind power prediction based on PSO-KalmanEnergy Reports, 2022
- Photovoltaic power prediction of LSTM model based on Pearson feature selectionEnergy Reports, 2021
- Wind power day-ahead prediction with cluster analysis of NWPRenewable and Sustainable Energy Reviews, 2016