Photovoltaic Power Prediction Using Empirical Mode Decomposition Algorithm and Integrated Neural Network

Aiming at the low accuracy of photovoltaic power prediction, a photovoltaic power prediction algorithm based on empirical mode decomposition algorithm and integrated neural network is proposed. First, the empirical mode decomposition algorithm decomposes the historical photovoltaic power data into a...

Full description

Saved in:
Bibliographic Details
Published in2021 International Conference on Artificial Intelligence and Electromechanical Automation (AIEA) pp. 35 - 38
Main Authors Tan, Wenan, Wang, Yiting
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2021
Subjects
Clouds
Empirical mode decomposition
integrated neural network
Neural networks
Photovoltaic systems
power prediction
Prediction algorithms
Predictive models
Time series analysis
Online AccessGet full text

Cover

More Information
Summary:Aiming at the low accuracy of photovoltaic power prediction, a photovoltaic power prediction algorithm based on empirical mode decomposition algorithm and integrated neural network is proposed. First, the empirical mode decomposition algorithm decomposes the historical photovoltaic power data into a series of stationary sequences, and then a prediction model is constructed using multiple backpropagation (BP) neural networks. Finally, these models' predicted values are weighted and fused, forming the final photovoltaic power prediction algorithm. The experimental results show that the proposed model herein has higher prediction accuracy and fewer prediction errors than the single BP neural network model and the Autoregressive Integrated Moving Average (ARIMA) model.
DOI:10.1109/AIEA53260.2021.00015