A novel method based on time series ensemble model for hourly photovoltaic power prediction

Zenan Xiao, Xiaoqiao Huang, Jun Liu, Chengli Li and Yonghang Tai

Energy, 2023, vol. 276, issue C

Abstract: Photovoltaic (PV) power generation technology is more and more widely used in smart grids. Accurate prediction of PV power is very important for managing and planning of the power grid system. However, solar energy has great randomness, intermittency, and uncertainty, which makes it difficult for the existing photovoltaic power prediction methods to achieve satisfactory prediction accuracy. To improve the comprehensive prediction performance of the model, this work proposes a reliable photovoltaic power prediction model based on neural-prophet (NP), convolutional neural network (CNN), and long short-term memory (LSTM) models. In this paper, multiple components of the NP are used to model the PV data and finish the preliminary prediction, then multiple features from NP combined with meteorological data are sent to the CNN-LSTM model, then used CNN-LSTM to extract the internal characteristics of the trend and seasonal variables of the PV data to achieves more accurate forecasting results. Finally, there are several evaluation indicators such as root mean square error (RMSE) and mean absolute error (MAE) to verify the performance of the proposed model. The results show that compared with the traditional LSTM model, CNN model, and the single NP model, the model proposed in this paper has a better effect on PV power prediction. The RMSE and MAE of the proposed model reached 0.987 kW and 0.563 kW, respectively.

Keywords: Photovoltaic power forecasting; Neural-prophet model; Long short-term memory; Hybrid forecasting model (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (14)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223009362
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:276:y:2023:i:c:s0360544223009362

DOI: 10.1016/j.energy.2023.127542

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().