Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy

Tiandong Ma; Feng Li; Renlong Gao; Siyu Hu; Wenwen Ma

doi:10.1016/j.gloei.2024.11.010

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy

Clean Energy Development | 更新时间：2026-09-20

- Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy
- Global Energy Interconnection Vol. 7, Issue 6, Pages: 825-835(2024)
- 作者机构：
  
  1. State Grid Ningxia Electric Power Co., Ltd,Yinchuan,PR China,750001
  2. China Electric Power Research Institute,Beijing,PR China,100192
- 作者简介：
- 基金信息：
- DOI：10.1016/j.gloei.2024.11.010
  CLC：
- Online First：16 December 2024，
  
  Published：16 December 2024
- 稿件说明：
移动端阅览
Tiandong Ma, Feng Li, Renlong Gao, et al. Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy[J]. Global Energy Interconnection, 2024, 7(6): 825-835.
DOI：

Tiandong Ma, Feng Li, Renlong Gao, et al. Short-term photovoltaic power forecasting based on a new hybrid deep learning model incorporating transfer learning strategy[J]. Global Energy Interconnection, 2024, 7(6): 825-835. DOI： 10.1016/j.gloei.2024.11.010.

摘要

Abstract

The accurate prediction of photovoltaic (PV) power generation is an important basis for hybrid grid scheduling. With the expansion of the scale of PV power plants and the popularization of distributed PV

this study proposes a multilayer PV power generation prediction model based on transfer learning to solve the problems of the lack of data on new PV bases and the low accuracy of PV power generation prediction. The proposed model

called DRAM

concatenates a dilated convolutional neural network (DCNN) module with a bidirectional long short-term memory (BiLSTM) module

and integrates an attention mechanism. First

the processed data are input into the DCNN layer

and the dilation convolution mechanism captures the spatial features of the wide sensory field of the input data. Subsequently

the temporal characteristics between the features are extracted in the BiLSTM layer. Finally

an attention mechanism is used to strengthen the key features by assigning weights to efficiently construct the relationship between the features and output variables. In addition

the power prediction accuracy of the new PV sites was improved by transferring the pre-trained model parameters to the new PV site prediction model. In this study

the pre-training of models using data from different source domains and the correlations between these pre-trained models and the target domain were analyzed.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Negative electricity prices in electricity markets: causes, impacts,and response strategies

Forecasting the average daily and during the hours of maximum electric load based on the data of the average monthly electricity consumption with single and other energy sources

Adaptive power and virtual resistance cooperation control strategy of VSG-based GFM converters for grid transient stability enhancement

EV＄{7*7}AL

Distribution network data asset protection considering multiple topology and multi-dimensional knowledge graph

Related Author

No data

Related Institution

No data

AI问答

⁰