View in EDS

A novel bimodal feature fusion network-based deep learning model with intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting.

Saved in:
Bibliographic Details
Title: A novel bimodal feature fusion network-based deep learning model with intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting.
Authors: Liu, Zhi-Feng1 (AUTHOR) liuzhifeng@tust.edu.cn, Chen, Xiao-Rui1 (AUTHOR) 21021127@mail.tust.edu.cn, Huang, Ya-He1 (AUTHOR) huangyahe@mail.tust.edu.cn, Luo, Xing-Fu1 (AUTHOR) fu406699@mail.tust.edu.cn, Zhang, Shu-Rui1 (AUTHOR) zsr030923@mail.tust.edu.cn, You, Guo-Dong1 (AUTHOR) yougdtust@126.com, Qiang, Xiao-Yong2 (AUTHOR), Kang, Qing2 (AUTHOR) kq1301@163.com
Source: Energy. Sep2024, Vol. 303, pN.PAG-N.PAG. 1p.
Subjects: Deep learning, Outlier detection, Differential evolution, Optimization algorithms, Forecasting, Carbon offsetting, Carbon emissions
Abstract: Under the goals of carbon neutrality and peak carbon emissions, photovoltaic (PV) power generation is widely valued for its clean and green characteristics. However, the uncertainty and randomness of PV power pose challenges to energy management. Therefore, this study proposed a novel bimodal feature fusion network-based deep learning model with an intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting. First, a threshold-guided iNNE-based outlier detection and repair method is designed for preprocessing PV data. Second, a bimodal feature fusion network was proposed to extract global and local features from PV power sequences, and the environmental factors-based rime optimization algorithm with growth mutation strategy and humidity perception mechanism was devised to optimize model's hyperparameters. Additionally, a photovoltaic power interval prediction model with a volatility segmentation strategy was introduced. Finally, the effectiveness of the proposed model, algorithm, and strategies was validated using measured datasets. The results demonstrated that under various weather conditions, the proposed model achieved point prediction evaluation metrics with an R2 exceeding 98 % and a prediction interval evaluation metric with a Prediction Interval Coverage Probability of 85.07 %. The obtained outcomes contribute to providing a basis for decision-making in the scientific scheduling and management of PV power systems. • The proposal of a bimodal feature fusion network-based deep learning model. • The proposal of a threshold-guided iNNE-based outlier detection and repair method. • The proposal of EFRIME with growth mutation and humidity perception mechanism. • The introduction of the TAP-MSIP model with the VSS strategy. [ABSTRACT FROM AUTHOR]
Copyright of Energy is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Under the goals of carbon neutrality and peak carbon emissions, photovoltaic (PV) power generation is widely valued for its clean and green characteristics. However, the uncertainty and randomness of PV power pose challenges to energy management. Therefore, this study proposed a novel bimodal feature fusion network-based deep learning model with an intelligent fusion gate mechanism for short-term photovoltaic power point-interval forecasting. First, a threshold-guided iNNE-based outlier detection and repair method is designed for preprocessing PV data. Second, a bimodal feature fusion network was proposed to extract global and local features from PV power sequences, and the environmental factors-based rime optimization algorithm with growth mutation strategy and humidity perception mechanism was devised to optimize model's hyperparameters. Additionally, a photovoltaic power interval prediction model with a volatility segmentation strategy was introduced. Finally, the effectiveness of the proposed model, algorithm, and strategies was validated using measured datasets. The results demonstrated that under various weather conditions, the proposed model achieved point prediction evaluation metrics with an R2 exceeding 98 % and a prediction interval evaluation metric with a Prediction Interval Coverage Probability of 85.07 %. The obtained outcomes contribute to providing a basis for decision-making in the scientific scheduling and management of PV power systems. • The proposal of a bimodal feature fusion network-based deep learning model. • The proposal of a threshold-guided iNNE-based outlier detection and repair method. • The proposal of EFRIME with growth mutation and humidity perception mechanism. • The introduction of the TAP-MSIP model with the VSS strategy. [ABSTRACT FROM AUTHOR]
ISSN:03605442
DOI:10.1016/j.energy.2024.131947