Paper
5 June 2024 Prediction method of output power of new energy distribution network based on improved BP neural network
Jingfeng Zhu, Qiyi Zhu
Author Affiliations +
Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131635I (2024) https://doi.org/10.1117/12.3030265
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China
Abstract
Because the factors affecting the output power of new energy distribution network are relatively low and complex, control the error of its prediction results effectively is very hard to realize. Therefore, the method of this paper is proposed. From three aspects of natural environment, equipment and power demand, this paper analyzes the composition of affecting factors and the specific impact mode, and takes them as the input. After establishing the corresponding relationship between the input layer and the hidden layer using Logistic chaotic mapping, the gradient descent method is used to adjust the connection threshold of each layer until the error function converges, it will be used as the new energy distribution network output power prediction model to achieve power prediction. In the test results, the error of the prediction method not only shows a high stability, but also remains at a low level, with the corresponding maximum error of only 1.27%.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Jingfeng Zhu and Qiyi Zhu "Prediction method of output power of new energy distribution network based on improved BP neural network", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131635I (5 June 2024); https://doi.org/10.1117/12.3030265
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Solar energy

Neural networks

Photovoltaics

Solar cells

Quantum networks

Wind energy

Neurons

Back to Top