Photovoltaic power forecasting with an ensemble multi-input deep learning approach
Photovoltaic power forecasting with an ensemble multi-input deep learning approach
The inherent intermittency of solar power due to meteorological factors presents a significant challenge in integrating them into grids on large scales. An accurate Photovoltaic (PV) power generation forecasting effectively supports achieving optimal planning and operational stability of power systems. Motivated by satisfactory performance of deep learning methods in the energy sector, an ensemble multi-input deep learning method combining three-dimensional convolution (Conv3D) networks and bidirectional long short-term memory (BiLSTM) networks is proposed in this study. First, one-dimensional (vector) PV power production and atmosphere parameters series are rearranged into a bi-dimensional matrix (2D image) and stacked in the third dimension (3D image) to preserve dependency between the input data. Then, the Conv3D network is utilized to extract non-linear spatial features of the 3D image. Finally, the BiLSTM network is implemented to learn the long-term dependencies of the extracted spatial features. The proposed method is utilized for one-day, three-day, five-day, and seven-day ahead PV power forecasting with one-hour intervals for Tennent operators, Germany dataset. Experimental results show reduced prediction error compared to two-dimensional Convolution (Conv2D), Conv3D, long short-term memory (LSTM), BiLSTM, Conv-LSTM, and ConvLSTM networks.
Bidirectional long short-term memory networks, Convolution neural networks, Deep learning, PV power forecasting
Dehghan, Fariba
e0863ef3-0a6c-467f-87ed-824cbd16408c
4 April 2023
Dehghan, Fariba
e0863ef3-0a6c-467f-87ed-824cbd16408c
Dehghan, Fariba
,
Mohsen Parsa Moghaddam and Maryam Imani
(2023)
Photovoltaic power forecasting with an ensemble multi-input deep learning approach.
In 2023 8th International Conference on Technology and Energy Management (ICTEM).
IEEE..
(doi:10.1109/ICTEM56862.2023.10084013).
Record type:
Conference or Workshop Item
(Paper)
Abstract
The inherent intermittency of solar power due to meteorological factors presents a significant challenge in integrating them into grids on large scales. An accurate Photovoltaic (PV) power generation forecasting effectively supports achieving optimal planning and operational stability of power systems. Motivated by satisfactory performance of deep learning methods in the energy sector, an ensemble multi-input deep learning method combining three-dimensional convolution (Conv3D) networks and bidirectional long short-term memory (BiLSTM) networks is proposed in this study. First, one-dimensional (vector) PV power production and atmosphere parameters series are rearranged into a bi-dimensional matrix (2D image) and stacked in the third dimension (3D image) to preserve dependency between the input data. Then, the Conv3D network is utilized to extract non-linear spatial features of the 3D image. Finally, the BiLSTM network is implemented to learn the long-term dependencies of the extracted spatial features. The proposed method is utilized for one-day, three-day, five-day, and seven-day ahead PV power forecasting with one-hour intervals for Tennent operators, Germany dataset. Experimental results show reduced prediction error compared to two-dimensional Convolution (Conv2D), Conv3D, long short-term memory (LSTM), BiLSTM, Conv-LSTM, and ConvLSTM networks.
This record has no associated files available for download.
More information
Published date: 4 April 2023
Keywords:
Bidirectional long short-term memory networks, Convolution neural networks, Deep learning, PV power forecasting
Identifiers
Local EPrints ID: 505449
URI: http://eprints.soton.ac.uk/id/eprint/505449
PURE UUID: 9f086502-b48f-4f5c-b4f0-00cadae5b28e
Catalogue record
Date deposited: 08 Oct 2025 16:55
Last modified: 09 Oct 2025 02:22
Export record
Altmetrics
Contributors
Author:
Fariba Dehghan
Corporate Author: Mohsen Parsa Moghaddam
Corporate Author: Maryam Imani
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics