Year: 2024
Type: article
Abstract: The increasing demand for sustainable energy sources has led to a great deal of study on optimizing wind energy systems. This study proposes a hybrid model that combines recurrent neural networks (RNN) and particle swarm optimization (PSO) to increase the efficiency of wind power forecasting and energy generation. Using previous data and meteorological conditions, the RNN is used to anticipate wind power output. The RNN's parameters are optimized via the PSO algorithm. The suggested model addresses the variable and irregular character of wind patterns in an effort to maximize energy output and enhance wind power forecasts through the integration of many methodologies. The hybrid model's performance is evaluated using actual wind farm data; the findings demonstrate a significant improvement in forecast accuracy and computing efficiency over traditional methods. This work demonstrates how advanced computational techniques and machine learning models can be used to enhance renewable energy systems and contribute to the development of safer and more effective wind energy solutions. Keywords - Particle Swarm Optimization, Recurrent Neural Networks, Wind Energy, Wind Power Forecasting, Renewable Energy
DOI: 10.55041/ijsrem40377
Institution: Parul University
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4405919784