Related Experiment Video
Updated: Jun 22, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
732
Forecasting a Short-Term Photovoltaic Power Model Based on Improved Snake Optimization, Convolutional Neural Network,
Yonggang Wang1, Yilin Yao1, Qiuying Zou1
1College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China.
Sensors (Basel, Switzerland)
|June 27, 2024
Summary
This study enhances short-term photovoltaic power forecasting accuracy using K-means clustering and an improved snake optimization algorithm with a convolutional neural network-bidirectional long short-term memory network. The integrated model achieves high prediction precision across various weather conditions.
Area of Science:
- Renewable Energy Systems
- Artificial Intelligence in Energy
- Grid Integration
Background:
- Accurate short-term photovoltaic power forecasting is crucial for electrical grid stability and operation.
- Existing forecasting methods may lack precision under diverse weather conditions.
Purpose of the Study:
- To propose an advanced method for enhancing the precision of short-term photovoltaic power prediction.
- To improve the adaptability of forecasting models across sunny, cloudy, and rainy weather scenarios.
Main Methods:
- K-means clustering to categorize weather into sunny, cloudy, and rainy scenarios.
- Pearson correlation coefficient for input feature selection.
- An improved snake optimization algorithm (with Tent chaotic mapping, lens imaging backward learning, adaptive perturbation) to optimize a convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) network.
Main Results:
- The proposed CNN-BiLSTM model, optimized by the enhanced snake algorithm, demonstrated high predictive accuracy.
- Achieved regression coefficients of 0.99216 (sunny), 0.95772 (cloudy), and 0.93163 (rainy) days.
- The method showed superior prediction precision and adaptability under various weather conditions.
Conclusions:
- The integrated K-means clustering, improved snake optimization, and CNN-BiLSTM model significantly enhances short-term photovoltaic power forecasting.
- This approach offers a robust solution for reliable grid integration of photovoltaic power generation.
