Two-stage photovoltaic power forecasting method with an optimized transformer

Yanhong Ma; Feng Li; Hong Zhang; Guoli Fu; Min Yi

doi:10.1016/j.gloei.2024.11.011

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

Two-stage photovoltaic power forecasting method with an optimized transformer

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

- Two-stage photovoltaic power forecasting method with an optimized transformer
- Two-stage photovoltaic power forecasting method with an optimized transformer
- 全球能源互联网(英文) 2024年7卷第6期页码：812-824
- 作者机构：
  
  1. State Grid Gansu Electric Power Company,Lanzhou,PR China,730000
  2. School of Electrical & Information Engineering, Lanzhou University of Technology,Lanzhou,PR China,730050
  3. School of Computer & Communication, Lanzhou University of Technology,Lanzhou,PR China,730050
- 作者简介：
- 基金信息：
- DOI：10.1016/j.gloei.2024.11.011
  中图分类号：
- 网络首发：2024-12-16，
  
  纸质出版：2024-12-16
- 稿件说明：
移动端阅览
Yanhong Ma, Feng Li, Hong Zhang, 等. Two-stage photovoltaic power forecasting method with an optimized transformer[J]. 全球能源互联网(英文), 2024,7(6):812-824.

Yanhong Ma, Feng Li, Hong Zhang, et al. Two-stage photovoltaic power forecasting method with an optimized transformer[J]. Global Energy Interconnection, 2024, 7(6): 812-824.
Yanhong Ma, Feng Li, Hong Zhang, 等. Two-stage photovoltaic power forecasting method with an optimized transformer[J]. 全球能源互联网(英文), 2024,7(6):812-824. DOI： 10.1016/j.gloei.2024.11.011.

Yanhong Ma, Feng Li, Hong Zhang, et al. Two-stage photovoltaic power forecasting method with an optimized transformer[J]. Global Energy Interconnection, 2024, 7(6): 812-824. DOI： 10.1016/j.gloei.2024.11.011.

摘要

Abstract

urate photovoltaic (PV) power forecasting ensures the stability and reliability of power systems. To address the complex characteristics of nonlinearity

volatility

and periodicity

a novel two-stage PV forecasting method based on an optimized transformer architecture is proposed. In the first stage

an inverted transformer backbone was utilized to consider the multivariate correlation of the PV power series and capture its non-linearity and volatility. ProbSparse attention was introduced to reduce high-memory occupation and solve computational overload issues. In the second stage

a weighted series decomposition module was proposed to extract the periodicity of the PV power series

and the final forecasting results were obtained through additive reconstruction. Experiments on two public datasets showed that the proposed forecasting method has high accuracy

robustness

and computational efficiency. Its RMSE improved by 31.23% compared with that of a traditional transformer

and its MSE improved by 12.57% compared with that of a baseline model.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Enhancing photovoltaic power prediction using a CNN-LSTM-attention hybrid model with Bayesian hyperparameter optimization

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

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

Research on benefit coordination mechanism in renewable energy multi-energy complementary systems

Multi-scenario coordinated operation strategy of battery-hydrogen hybrid energy storage system for pure photovoltaic VSC-HVDC converter station