Short-term photovoltaic power prediction based on VMD-SSA-LSTM

Tingyi Zhang; Shaowu Li; Jinbiao Chen; Xuwen Liu; Weihao Guo

doi:10.1117/12.3033860

5 July 2024 Short-term photovoltaic power prediction based on VMD-SSA-LSTM

Tingyi Zhang, Shaowu Li, Jinbiao Chen, Xuwen Liu, Weihao Guo

Proceedings Volume 13183, International Conference on Optoelectronic Information and Functional Materials (OIFM 2024); 131830C (2024) https://doi.org/10.1117/12.3033860
Event: The 3rd International Conference on Optoelectronic Information and Functional Materials (OIFM 2024), 2024, Wuhan, China

Abstract

Photovoltaic power prediction is crucial for maintaining the safe, stable operation, and economic benefits of the power grid. However, the long short-term memory (LSTM) neural network faces limitations in parameter selection, affecting its effectiveness in photovoltaic power prediction. Additionally, photovoltaic power data exhibits volatility and non-stationarity, leading to inaccurate predictions. To address these issues, this paper proposes a coupled model named VMD-SSA-LSTM, which combines variational mode decomposition (VMD), sparrow search algorithm (SSA), and LSTM. The model initially employs VMD to decompose photovoltaic power data, reducing the impact of volatility and non-stationarity on prediction results. Subsequently, SSA is used to optimize LSTM parameters. Finally, the predicted values from each sequence are summed to obtain the photovoltaic power prediction. Simulation experiments demonstrate the model's high adaptability in short-term photovoltaic power prediction. Compared to the LSTM model, the VMD-SSA-LSTM model exhibits superior performance in prediction accuracy, stability, and robustness. Therefore, this model provides an effective solution to enhance the accuracy of photovoltaic power prediction, contributing to the safety, stability, and economic efficiency of power grid operation.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tingyi Zhang, Shaowu Li, Jinbiao Chen, Xuwen Liu, and Weihao Guo "Short-term photovoltaic power prediction based on VMD-SSA-LSTM", Proc. SPIE 13183, International Conference on Optoelectronic Information and Functional Materials (OIFM 2024), 131830C (5 July 2024); https://doi.org/10.1117/12.3033860

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available