Applied Mathematics and Nonlinear Sciences
Journal license

Journal

Applied Mathematics and Nonlinear Sciences


Volume
& Issue

Volume 6, Issue 2


Published
on

September 5, 2022


Pages

823-834


DOI

Article

Ultra-short-term power forecast of photovoltaic power station based on VMD–LSTM model optimised by SSA

Check for updates


Authors

Jing Yizhou Affiliation:
College of Electrical Engineering & New Energy, China Three Gorges University, Yichang, Hubei, China
, Yang Siqi Affiliation:
College of Electrical Engineering & New Energy, China Three Gorges University, Yichang, Hubei, China
and Zhang Kegeng Affiliation:
College of Electrical Engineering & New Energy, China Three Gorges University, Yichang, Hubei, China


Abstract

The paper takes the data of a 50 MW photovoltaic power generation system as a sample, divides the weather conditions into two categories according to whether there is a sudden change, optimises the decomposition number K and penalty factor of variational mode decomposition (VMD) by using the sparrow intelligent algorithm, decomposes the power sequence in a power mode by using the optimised VMD decomposition method and sends all sub-components to a long short-term memory (LSTM) network for prediction.


Keywords

photovoltaic power station, sparrow algorithm, long-term memory neural network, ultra-short term, power prediction


Citation

Yizhou, J., Siqi, Y., & Kegeng, Z. (2021). Ultra-short-term power forecast of photovoltaic power station based on VMD–LSTM model optimised by SSA. Applied Mathematics and Nonlinear Sciences, 6(2), 823–834. https://doi.org/10.2478/amns.2021.2.00246

Published by: Engineering Journals

Engineering Journals Logo